npm - @agent-native/core - Versions diffs - 0.98.16 → 0.99.0 - Mend

@agent-native/core 0.98.16 → 0.99.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (546) hide show

package/dist/cli/skills-content/design-exploration-skill.js CHANGED Viewed

@@ -92,7 +92,7 @@ separate those jobs; use it, and hold this bar:
 ## Cross-App Use
-- Hosted default: connect \`https://design.agent-native.com/_agent-native/mcp\`.
+- Hosted default: connect \`https://design.agent-native.com/mcp\`.
   Do not put shared secrets in skill files.
 - For CLI/code-editor clients, keep any \`npx @agent-native/core@latest connect\` command
   running until browser authorization finishes. Stopping it early can leave the

package/dist/cli/skills-content/design-exploration-skill.js.map CHANGED Viewed

	@@ -1 +1 @@
1	- {"version":3,"file":"design-exploration-skill.js","sourceRoot":"","sources":["../../../src/cli/skills-content/design-exploration-skill.ts"],"names":[],"mappings":"AAAA,MAAM,CAAC,MAAM,2BAA2B,GAAG;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CAqH1C,CAAC","sourcesContent":["export const DESIGN_EXPLORATION_SKILL_MD = `---\nname: design-exploration\ndescription: >-\n Use Design for UI/UX exploration, side-by-side design directions,\n interactive prototype previews, user selection, iteration, and design-to-code\n handoff through the hosted Design MCP app.\nmetadata:\n visibility: exported\n---\n\n# Design Exploration\n\nUse the Design app when a workflow needs visual UI exploration, prototype\niteration, or a human-in-the-loop choice among design directions.\n\n## Choose The Path\n\n- Use \\`create-design\\` first to create a project shell. Do not report the\n design as ready until it has renderable HTML.\n- For open-ended UX exploration, generate distinct, compact, complete HTML\n directions (2-5, three by default) and call \\`present-design-variants\\`. Each\n direction should be one representative screen or directional snapshot, not a\n full app per variant. Design saves every option as a normal screen on the\n overview board and renders an inline chat choice with one button per screen\n name. After the user picks, delete the unchosen variant screens and continue\n from the kept screen by first calling \\`get-design-snapshot\\` with that\n screen's \\`fileId\\`, then calling \\`edit-design\\` on that same \\`fileId\\` in a\n bounded single-file pass. Use \\`mode: \"replace-file\"\\` when expanding the\n representative placeholder into the full chosen direction. Do not call\n \\`generate-design\\` after a variant pick.\n- If the chat choice buttons are not available in the host, ask the user to\n tell you the screen name they prefer. The variants are already real screens\n on the board, so do not ask them to paste HTML or copy a generated handoff\n summary.\n- For direct refinements to an already chosen direction, call\n \\`get-design-snapshot\\`, edit from the current tuned HTML, and use\n \\`edit-design\\` for surgical changes or \\`mode: \"replace-file\"\\` for a bounded\n selected-file replacement. Use \\`generate-design\\` for new files only.\n- Use \\`export-coding-handoff\\` when the user wants to implement the chosen\n design in a codebase.\n\n## Exploration Defaults\n\n1. Default to three variants unless the user asks for a different count\n (\\`present-design-variants\\` accepts 2-5; three is the sweet spot).\n2. Make variants structurally and stylistically distinct, not just color swaps.\n3. Each variant must be a compact, complete standalone HTML document that\n renders without a build step.\n4. For product UI redesigns, prefer cleaner hierarchy, progressive disclosure,\n and realistic controls over decorative mockups.\n5. After \\`present-design-variants\\`, wait for the user's pick before\n generating the next version. Keep the chosen screen, delete the other\n variant screens, call \\`get-design-snapshot\\` with \\`fileId\\` for the kept\n screen, then call \\`edit-design\\` on that same \\`fileId\\` in a bounded pass.\n Use \\`mode: \"replace-file\"\\` when expanding the representative placeholder\n into the full chosen direction. Do not call \\`generate-design\\` after a\n variant pick. Stop after the first successful \\`edit-design\\` save.\n\n## Design Quality Bar\n\nGeneric \"AI slop\" comes from letting one prompt set taste, explore, and emit code\nat once — so the model returns the training-average (Inter, an indigo/violet\ngradient, a centered hero, three rounded cards). The variant flow above exists to\nseparate those jobs; use it, and hold this bar:\n\n- Before generating, name the concrete audience, the screen's primary job, and\n the visual thesis. If the brief is vague, make a reasonable choice and state\n it instead of producing a generic dashboard/landing-page default.\n- Refuse the defaults, and pair every \"don't\" with a \"do\" (banning Inter alone\n just makes you reach for Roboto). Avoid Inter/Roboto/system fonts, the\n indigo/violet slop palette (\\`#6366F1\\`/\\`#8B5CF6\\`/\\`#A855F7\\`) and purple-on-white\n gradients, and centered-hero + three-icon-card layouts; instead pick a\n distinctive font pairing, one non-default palette family with a single decisive\n accent, and an asymmetric layout with a clear focal point.\n- Make each direction distinct in structure and behavior, not just palette.\n Give every variant one memorable signature choice, then keep the surrounding\n chrome disciplined. Even your creative picks converge (Space Grotesk\n everywhere) — vary deliberately so two directions never share a fingerprint.\n- For existing products, inspect the current screen, design system, tokens, and\n component language before inventing a new direction. Treat any drift back to a\n default as a missing token to pin, and vary layout per screen so on-brand does\n not become same-in-your-colors.\n- Treat copy, data, and imagery as design material. Use realistic domain\n content and first-party/generated assets when images matter; avoid lorem\n ipsum, vague SaaS filler, and decorative placeholder boxes.\n- Build to a quiet quality floor: responsive desktop/mobile layout, visible\n keyboard focus, useful loading/empty/error states for app UI, and reduced\n motion support when custom motion is present.\n- After broad generation or refinement, inspect the rendered Design surface or\n a screenshot-capable host before calling it ready. Fix obvious hierarchy,\n overflow, contrast, broken interaction, and placeholder-content issues first.\n\n## Cross-App Use\n\n- Hosted default: connect \\`https://design.agent-native.com/~~_agent-native/~~mcp\\`.\n Do not put shared secrets in skill files.\n- For CLI/code-editor clients, keep any \\`npx @agent-native/core@latest connect\\` command\n running until browser authorization finishes. Stopping it early can leave the\n browser approved but the local MCP config unwritten. Restart or reload the\n agent client after installing or connecting if Design tools do not appear in\n the live session.\n- Dispatch can expose Design alongside other apps. Use Design for UI/UX design\n tasks, Assets for image/media selection, Slides for decks, and so on.\n- Keep the loop visual: surface the inline MCP App or the returned \"Open\n design\" link instead of pasting large HTML blobs into chat.\n- If a Design tool call returns \\`Session terminated\\`, \\`needs auth\\`, or\n another connector/session error, do not keep retrying the tool. Stop and give\n the user the reconnect step: in Claude Code run \\`/mcp\\` and choose\n Authenticate/Reconnect for the Design connector; from any terminal run\n \\`npx -y @agent-native/core@latest reconnect https://design.agent-native.com\\` — this\n re-authenticates WITHOUT reinstalling. Never reinstall from scratch just to fix\n auth. Continue once the connector is available.\n- Do not hand-roll MCP HTTP requests with curl from the agent session. Use the\n host-exposed Design tools after restart/reload, or use the returned\n browser/deep-link fallback.\n- If you inspect local MCP config, redact \\`Authorization\\`, \\`http_headers\\`,\n and token values. Never paste bearer tokens into chat or logs.\n`;\n"]}
1	+ {"version":3,"file":"design-exploration-skill.js","sourceRoot":"","sources":["../../../src/cli/skills-content/design-exploration-skill.ts"],"names":[],"mappings":"AAAA,MAAM,CAAC,MAAM,2BAA2B,GAAG;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CAqH1C,CAAC","sourcesContent":["export const DESIGN_EXPLORATION_SKILL_MD = `---\nname: design-exploration\ndescription: >-\n Use Design for UI/UX exploration, side-by-side design directions,\n interactive prototype previews, user selection, iteration, and design-to-code\n handoff through the hosted Design MCP app.\nmetadata:\n visibility: exported\n---\n\n# Design Exploration\n\nUse the Design app when a workflow needs visual UI exploration, prototype\niteration, or a human-in-the-loop choice among design directions.\n\n## Choose The Path\n\n- Use \\`create-design\\` first to create a project shell. Do not report the\n design as ready until it has renderable HTML.\n- For open-ended UX exploration, generate distinct, compact, complete HTML\n directions (2-5, three by default) and call \\`present-design-variants\\`. Each\n direction should be one representative screen or directional snapshot, not a\n full app per variant. Design saves every option as a normal screen on the\n overview board and renders an inline chat choice with one button per screen\n name. After the user picks, delete the unchosen variant screens and continue\n from the kept screen by first calling \\`get-design-snapshot\\` with that\n screen's \\`fileId\\`, then calling \\`edit-design\\` on that same \\`fileId\\` in a\n bounded single-file pass. Use \\`mode: \"replace-file\"\\` when expanding the\n representative placeholder into the full chosen direction. Do not call\n \\`generate-design\\` after a variant pick.\n- If the chat choice buttons are not available in the host, ask the user to\n tell you the screen name they prefer. The variants are already real screens\n on the board, so do not ask them to paste HTML or copy a generated handoff\n summary.\n- For direct refinements to an already chosen direction, call\n \\`get-design-snapshot\\`, edit from the current tuned HTML, and use\n \\`edit-design\\` for surgical changes or \\`mode: \"replace-file\"\\` for a bounded\n selected-file replacement. Use \\`generate-design\\` for new files only.\n- Use \\`export-coding-handoff\\` when the user wants to implement the chosen\n design in a codebase.\n\n## Exploration Defaults\n\n1. Default to three variants unless the user asks for a different count\n (\\`present-design-variants\\` accepts 2-5; three is the sweet spot).\n2. Make variants structurally and stylistically distinct, not just color swaps.\n3. Each variant must be a compact, complete standalone HTML document that\n renders without a build step.\n4. For product UI redesigns, prefer cleaner hierarchy, progressive disclosure,\n and realistic controls over decorative mockups.\n5. After \\`present-design-variants\\`, wait for the user's pick before\n generating the next version. Keep the chosen screen, delete the other\n variant screens, call \\`get-design-snapshot\\` with \\`fileId\\` for the kept\n screen, then call \\`edit-design\\` on that same \\`fileId\\` in a bounded pass.\n Use \\`mode: \"replace-file\"\\` when expanding the representative placeholder\n into the full chosen direction. Do not call \\`generate-design\\` after a\n variant pick. Stop after the first successful \\`edit-design\\` save.\n\n## Design Quality Bar\n\nGeneric \"AI slop\" comes from letting one prompt set taste, explore, and emit code\nat once — so the model returns the training-average (Inter, an indigo/violet\ngradient, a centered hero, three rounded cards). The variant flow above exists to\nseparate those jobs; use it, and hold this bar:\n\n- Before generating, name the concrete audience, the screen's primary job, and\n the visual thesis. If the brief is vague, make a reasonable choice and state\n it instead of producing a generic dashboard/landing-page default.\n- Refuse the defaults, and pair every \"don't\" with a \"do\" (banning Inter alone\n just makes you reach for Roboto). Avoid Inter/Roboto/system fonts, the\n indigo/violet slop palette (\\`#6366F1\\`/\\`#8B5CF6\\`/\\`#A855F7\\`) and purple-on-white\n gradients, and centered-hero + three-icon-card layouts; instead pick a\n distinctive font pairing, one non-default palette family with a single decisive\n accent, and an asymmetric layout with a clear focal point.\n- Make each direction distinct in structure and behavior, not just palette.\n Give every variant one memorable signature choice, then keep the surrounding\n chrome disciplined. Even your creative picks converge (Space Grotesk\n everywhere) — vary deliberately so two directions never share a fingerprint.\n- For existing products, inspect the current screen, design system, tokens, and\n component language before inventing a new direction. Treat any drift back to a\n default as a missing token to pin, and vary layout per screen so on-brand does\n not become same-in-your-colors.\n- Treat copy, data, and imagery as design material. Use realistic domain\n content and first-party/generated assets when images matter; avoid lorem\n ipsum, vague SaaS filler, and decorative placeholder boxes.\n- Build to a quiet quality floor: responsive desktop/mobile layout, visible\n keyboard focus, useful loading/empty/error states for app UI, and reduced\n motion support when custom motion is present.\n- After broad generation or refinement, inspect the rendered Design surface or\n a screenshot-capable host before calling it ready. Fix obvious hierarchy,\n overflow, contrast, broken interaction, and placeholder-content issues first.\n\n## Cross-App Use\n\n- Hosted default: connect \\`https://design.agent-native.com/mcp\\`.\n Do not put shared secrets in skill files.\n- For CLI/code-editor clients, keep any \\`npx @agent-native/core@latest connect\\` command\n running until browser authorization finishes. Stopping it early can leave the\n browser approved but the local MCP config unwritten. Restart or reload the\n agent client after installing or connecting if Design tools do not appear in\n the live session.\n- Dispatch can expose Design alongside other apps. Use Design for UI/UX design\n tasks, Assets for image/media selection, Slides for decks, and so on.\n- Keep the loop visual: surface the inline MCP App or the returned \"Open\n design\" link instead of pasting large HTML blobs into chat.\n- If a Design tool call returns \\`Session terminated\\`, \\`needs auth\\`, or\n another connector/session error, do not keep retrying the tool. Stop and give\n the user the reconnect step: in Claude Code run \\`/mcp\\` and choose\n Authenticate/Reconnect for the Design connector; from any terminal run\n \\`npx -y @agent-native/core@latest reconnect https://design.agent-native.com\\` — this\n re-authenticates WITHOUT reinstalling. Never reinstall from scratch just to fix\n auth. Continue once the connector is available.\n- Do not hand-roll MCP HTTP requests with curl from the agent session. Use the\n host-exposed Design tools after restart/reload, or use the returned\n browser/deep-link fallback.\n- If you inspect local MCP config, redact \\`Authorization\\`, \\`http_headers\\`,\n and token values. Never paste bearer tokens into chat or logs.\n`;\n"]}

package/dist/cli/skills-content/help.d.ts CHANGED Viewed

@@ -1,2 +1,2 @@
-export declare const HELP = "npx @agent-native/core@latest skills\n\nUsage:\n  npx @agent-native/core@latest skills list\n  npx @agent-native/core@latest skills status [assets|content|design-exploration|visual-edit|visual-plan|visual-recap|visualize-repo|context-xray|scaffold] [--client codex|claude-code|pi|all] [--scope user|project] [--json]\n  npx @agent-native/core@latest skills update [assets|content|design-exploration|visual-edit|visual-plan|visual-recap|visualize-repo|context-xray|scaffold] [--client codex|claude-code|pi|all] [--scope user|project] [--dry-run] [--json]\n  npx @agent-native/core@latest skills add assets|content|design-exploration|visual-edit|visual-plan|visual-recap|visualize-repo|context-xray [--client codex|claude-code|cowork|cursor|opencode|github-copilot|all] [--scope user|project] [--mode hosted|local-files|self-hosted] [--mcp-url <url>] [--no-connect] [--with-github-action] [--yes] [--dry-run] [--json]\n  npx @agent-native/core@latest skills add <manifest-or-app-dir|skill-repo> [--skill <name>] [--client ...] [--yes]\n\nExamples:\n  npx @agent-native/core@latest skills add assets\n  npx @agent-native/core@latest skills add content --mode local-files\n  npx @agent-native/core@latest skills add design-exploration\n  npx @agent-native/core@latest skills add visual-edit\n  npx @agent-native/core@latest skills add visual-plan\n  npx @agent-native/core@latest skills add visual-recap\n  npx @agent-native/core@latest skills add visualize-repo\n  npx @agent-native/core@latest skills add visual-recap --with-github-action\n  npx @agent-native/core@latest skills add visual-plan --mode local-files\n  npx @agent-native/core@latest skills add visual-plan --mode self-hosted --mcp-url https://my-plan-app.example.com\n  npx @agent-native/core@latest skills status visual-plan\n  npx @agent-native/core@latest skills update visual-plan\n  npx @agent-native/core@latest skills update scaffold --project\n  npx @agent-native/core@latest skills add visual-plan --no-connect\n  npx @agent-native/core@latest skills add context-xray --client all\n  npx @agent-native/core@latest skills add assets --client claude-code\n  npx @agent-native/core@latest skills add assets --mcp-url https://my-app.ngrok-free.dev\n  npx @agent-native/core@latest skills add ./dist/assets-skill --client codex\n  npx @agent-native/core@latest skills add BuilderIO/skills --client codex --scope project\n  npx @agent-native/core@latest skills add BuilderIO/skills --with-github-action\n\nThe add command installs the SKILL.md instructions, registers the app-backed\nMCP connector, and then authenticates it in one step so you do not hit an OAuth\nwall on the first tool call. Hosted installs can configure Claude Code, Codex,\nClaude Cowork, Cursor, OpenCode, and GitHub Copilot / VS Code; local-files\ninstruction installs target the shared .agents skill path used by Codex, Pi,\nCursor, OpenCode, Copilot, and similar agents, plus Claude Code's native skill\npath when selected. Pass --client to narrow it. Authentication reuses\n\"npx @agent-native/core@latest connect\": OAuth-capable clients (Claude Code,\nCursor, OpenCode, GitHub Copilot / VS Code) get URL-only entries and authenticate\ninside that host, while Codex / Cowork run the browser device-code flow. In a\nnon-interactive shell or CI the auth step is skipped and the exact\n\"npx @agent-native/core@latest connect <url> --client all\" command is printed instead.\n\nRunning \"npx @agent-native/skills@latest add ...\" uses this same shared install\nflow with the broader BuilderIO skills catalog enabled. Pass --no-connect to\nregister MCP where possible without authenticating (leave auth to the host or run\n\"npx @agent-native/core@latest connect\" later). Pass --mcp-url to register that connector against\na custom origin (an ngrok tunnel, a local dev server, or a self-hosted\ndeployment) instead of the built-in hosted default \u2014 a bare origin gets the\nstandard /_agent-native/mcp path appended. Use app-skill pack for marketplace\nbundles and custom adapter output.\n\nWhen installing visual-plan, visual-recap, or visualize-repo interactively, the\nCLI asks where Plans artifacts should live: hosted Plans for shareable\nlinks/comments, local files for \"No sharing, all local.\", or a\nself-hosted/custom Plan app URL.\nPass --mode to choose directly. Local-files mode skips MCP registration and\nauth and installs instructions that default to a no-auth block catalog fetch,\nMDX folders, and the localhost bridge viewer.\n\nWhen installing content with --mode local-files, the CLI installs Content\ninstructions and writes or updates agent-native.json with repo-backed Markdown /\nMDX roots for docs, blog, content, and resources. Use a local Content app, Agent\nNative Desktop, or another trusted local bridge for Content actions to read and\nwrite those files.\n\nWhen installing visual-recap interactively, the CLI offers to add the optional PR\nVisual Recap GitHub Action. Pass --with-github-action to write it directly, then\nrun \"npx @agent-native/core@latest recap setup\" / \"npx @agent-native/core@latest recap doctor\" to configure and\nverify GitHub Actions. Docs: https://www.agent-native.com/docs/pr-visual-recap.\n\nThe status/update commands inspect copied Agent Native skill folders and refresh\ntheir instruction files from the current @agent-native/core package. In generated\napps/workspaces, \"skills update scaffold --project\" refreshes the framework\nskills copied into the scaffold and repairs AGENTS.md / CLAUDE.md and\n.agents/skills / .claude/skills compatibility links.";
+export declare const HELP = "npx @agent-native/core@latest skills\n\nUsage:\n  npx @agent-native/core@latest skills list\n  npx @agent-native/core@latest skills status [assets|content|design-exploration|visual-edit|visual-plan|visual-recap|visualize-repo|context-xray|scaffold] [--client codex|claude-code|pi|all] [--scope user|project] [--json]\n  npx @agent-native/core@latest skills update [assets|content|design-exploration|visual-edit|visual-plan|visual-recap|visualize-repo|context-xray|scaffold] [--client codex|claude-code|pi|all] [--scope user|project] [--dry-run] [--json]\n  npx @agent-native/core@latest skills add assets|content|design-exploration|visual-edit|visual-plan|visual-recap|visualize-repo|context-xray [--client codex|claude-code|cowork|cursor|opencode|github-copilot|all] [--scope user|project] [--mode hosted|local-files|self-hosted] [--mcp-url <url>] [--no-connect] [--with-github-action] [--yes] [--dry-run] [--json]\n  npx @agent-native/core@latest skills add <manifest-or-app-dir|skill-repo> [--skill <name>] [--client ...] [--yes]\n\nExamples:\n  npx @agent-native/core@latest skills add assets\n  npx @agent-native/core@latest skills add content --mode local-files\n  npx @agent-native/core@latest skills add design-exploration\n  npx @agent-native/core@latest skills add visual-edit\n  npx @agent-native/core@latest skills add visual-plan\n  npx @agent-native/core@latest skills add visual-recap\n  npx @agent-native/core@latest skills add visualize-repo\n  npx @agent-native/core@latest skills add visual-recap --with-github-action\n  npx @agent-native/core@latest skills add visual-plan --mode local-files\n  npx @agent-native/core@latest skills add visual-plan --mode self-hosted --mcp-url https://my-plan-app.example.com\n  npx @agent-native/core@latest skills status visual-plan\n  npx @agent-native/core@latest skills update visual-plan\n  npx @agent-native/core@latest skills update scaffold --project\n  npx @agent-native/core@latest skills add visual-plan --no-connect\n  npx @agent-native/core@latest skills add context-xray --client all\n  npx @agent-native/core@latest skills add assets --client claude-code\n  npx @agent-native/core@latest skills add assets --mcp-url https://my-app.ngrok-free.dev\n  npx @agent-native/core@latest skills add ./dist/assets-skill --client codex\n  npx @agent-native/core@latest skills add BuilderIO/skills --client codex --scope project\n  npx @agent-native/core@latest skills add BuilderIO/skills --with-github-action\n\nThe add command installs the SKILL.md instructions, registers the app-backed\nMCP connector, and then authenticates it in one step so you do not hit an OAuth\nwall on the first tool call. Hosted installs can configure Claude Code, Codex,\nClaude Cowork, Cursor, OpenCode, and GitHub Copilot / VS Code; local-files\ninstruction installs target the shared .agents skill path used by Codex, Pi,\nCursor, OpenCode, Copilot, and similar agents, plus Claude Code's native skill\npath when selected. Pass --client to narrow it. Authentication reuses\n\"npx @agent-native/core@latest connect\": OAuth-capable clients (Claude Code,\nCursor, OpenCode, GitHub Copilot / VS Code) get URL-only entries and authenticate\ninside that host, while Codex / Cowork run the browser device-code flow. In a\nnon-interactive shell or CI the auth step is skipped and the exact\n\"npx @agent-native/core@latest connect <url> --client all\" command is printed instead.\n\nRunning \"npx @agent-native/skills@latest add ...\" uses this same shared install\nflow with the broader BuilderIO skills catalog enabled. Pass --no-connect to\nregister MCP where possible without authenticating (leave auth to the host or run\n\"npx @agent-native/core@latest connect\" later). Pass --mcp-url to register that connector against\na custom origin (an ngrok tunnel, a local dev server, or a self-hosted\ndeployment) instead of the built-in hosted default \u2014 a bare origin gets the\nstandard /mcp path appended. Use app-skill pack for marketplace\nbundles and custom adapter output.\n\nWhen installing visual-plan, visual-recap, or visualize-repo interactively, the\nCLI asks where Plans artifacts should live: hosted Plans for shareable\nlinks/comments, local files for \"No sharing, all local.\", or a\nself-hosted/custom Plan app URL.\nPass --mode to choose directly. Local-files mode skips MCP registration and\nauth and installs instructions that default to a no-auth block catalog fetch,\nMDX folders, and the localhost bridge viewer.\n\nWhen installing content with --mode local-files, the CLI installs Content\ninstructions and writes or updates agent-native.json with repo-backed Markdown /\nMDX roots for docs, blog, content, and resources. Use a local Content app, Agent\nNative Desktop, or another trusted local bridge for Content actions to read and\nwrite those files.\n\nWhen installing visual-recap interactively, the CLI offers to add the optional PR\nVisual Recap GitHub Action. Pass --with-github-action to write it directly, then\nrun \"npx @agent-native/core@latest recap setup\" / \"npx @agent-native/core@latest recap doctor\" to configure and\nverify GitHub Actions. Docs: https://www.agent-native.com/docs/pr-visual-recap.\n\nThe status/update commands inspect copied Agent Native skill folders and refresh\ntheir instruction files from the current @agent-native/core package. In generated\napps/workspaces, \"skills update scaffold --project\" refreshes the framework\nskills copied into the scaffold and repairs AGENTS.md / CLAUDE.md and\n.agents/skills / .claude/skills compatibility links.";
 //# sourceMappingURL=help.d.ts.map

package/dist/cli/skills-content/help.d.ts.map CHANGED Viewed

	@@ -1 +1 @@
1	- {"version":3,"file":"help.d.ts","sourceRoot":"","sources":["../../../src/cli/skills-content/help.ts"],"names":[],"mappings":"AAAA,eAAO,MAAM,IAAI,~~k8KA4EoC~~,CAAC"}
1	+ {"version":3,"file":"help.d.ts","sourceRoot":"","sources":["../../../src/cli/skills-content/help.ts"],"names":[],"mappings":"AAAA,eAAO,MAAM,IAAI,o7KA4EoC,CAAC"}

package/dist/cli/skills-content/help.js CHANGED Viewed

@@ -48,7 +48,7 @@ register MCP where possible without authenticating (leave auth to the host or ru
 "npx @agent-native/core@latest connect" later). Pass --mcp-url to register that connector against
 a custom origin (an ngrok tunnel, a local dev server, or a self-hosted
 deployment) instead of the built-in hosted default — a bare origin gets the
-standard /_agent-native/mcp path appended. Use app-skill pack for marketplace
+standard /mcp path appended. Use app-skill pack for marketplace
 bundles and custom adapter output.
 When installing visual-plan, visual-recap, or visualize-repo interactively, the

package/dist/cli/skills-content/help.js.map CHANGED Viewed

	@@ -1 +1 @@
1	- {"version":3,"file":"help.js","sourceRoot":"","sources":["../../../src/cli/skills-content/help.ts"],"names":[],"mappings":"AAAA,MAAM,CAAC,MAAM,IAAI,GAAG;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;qDA4EiC,CAAC","sourcesContent":["export const HELP = `npx @agent-native/core@latest skills\n\nUsage:\n npx @agent-native/core@latest skills list\n npx @agent-native/core@latest skills status [assets\|content\|design-exploration\|visual-edit\|visual-plan\|visual-recap\|visualize-repo\|context-xray\|scaffold] [--client codex\|claude-code\|pi\|all] [--scope user\|project] [--json]\n npx @agent-native/core@latest skills update [assets\|content\|design-exploration\|visual-edit\|visual-plan\|visual-recap\|visualize-repo\|context-xray\|scaffold] [--client codex\|claude-code\|pi\|all] [--scope user\|project] [--dry-run] [--json]\n npx @agent-native/core@latest skills add assets\|content\|design-exploration\|visual-edit\|visual-plan\|visual-recap\|visualize-repo\|context-xray [--client codex\|claude-code\|cowork\|cursor\|opencode\|github-copilot\|all] [--scope user\|project] [--mode hosted\|local-files\|self-hosted] [--mcp-url <url>] [--no-connect] [--with-github-action] [--yes] [--dry-run] [--json]\n npx @agent-native/core@latest skills add <manifest-or-app-dir\|skill-repo> [--skill <name>] [--client ...] [--yes]\n\nExamples:\n npx @agent-native/core@latest skills add assets\n npx @agent-native/core@latest skills add content --mode local-files\n npx @agent-native/core@latest skills add design-exploration\n npx @agent-native/core@latest skills add visual-edit\n npx @agent-native/core@latest skills add visual-plan\n npx @agent-native/core@latest skills add visual-recap\n npx @agent-native/core@latest skills add visualize-repo\n npx @agent-native/core@latest skills add visual-recap --with-github-action\n npx @agent-native/core@latest skills add visual-plan --mode local-files\n npx @agent-native/core@latest skills add visual-plan --mode self-hosted --mcp-url https://my-plan-app.example.com\n npx @agent-native/core@latest skills status visual-plan\n npx @agent-native/core@latest skills update visual-plan\n npx @agent-native/core@latest skills update scaffold --project\n npx @agent-native/core@latest skills add visual-plan --no-connect\n npx @agent-native/core@latest skills add context-xray --client all\n npx @agent-native/core@latest skills add assets --client claude-code\n npx @agent-native/core@latest skills add assets --mcp-url https://my-app.ngrok-free.dev\n npx @agent-native/core@latest skills add ./dist/assets-skill --client codex\n npx @agent-native/core@latest skills add BuilderIO/skills --client codex --scope project\n npx @agent-native/core@latest skills add BuilderIO/skills --with-github-action\n\nThe add command installs the SKILL.md instructions, registers the app-backed\nMCP connector, and then authenticates it in one step so you do not hit an OAuth\nwall on the first tool call. Hosted installs can configure Claude Code, Codex,\nClaude Cowork, Cursor, OpenCode, and GitHub Copilot / VS Code; local-files\ninstruction installs target the shared .agents skill path used by Codex, Pi,\nCursor, OpenCode, Copilot, and similar agents, plus Claude Code's native skill\npath when selected. Pass --client to narrow it. Authentication reuses\n\"npx @agent-native/core@latest connect\": OAuth-capable clients (Claude Code,\nCursor, OpenCode, GitHub Copilot / VS Code) get URL-only entries and authenticate\ninside that host, while Codex / Cowork run the browser device-code flow. In a\nnon-interactive shell or CI the auth step is skipped and the exact\n\"npx @agent-native/core@latest connect <url> --client all\" command is printed instead.\n\nRunning \"npx @agent-native/skills@latest add ...\" uses this same shared install\nflow with the broader BuilderIO skills catalog enabled. Pass --no-connect to\nregister MCP where possible without authenticating (leave auth to the host or run\n\"npx @agent-native/core@latest connect\" later). Pass --mcp-url to register that connector against\na custom origin (an ngrok tunnel, a local dev server, or a self-hosted\ndeployment) instead of the built-in hosted default — a bare origin gets the\nstandard /~~_agent-native/~~mcp path appended. Use app-skill pack for marketplace\nbundles and custom adapter output.\n\nWhen installing visual-plan, visual-recap, or visualize-repo interactively, the\nCLI asks where Plans artifacts should live: hosted Plans for shareable\nlinks/comments, local files for \"No sharing, all local.\", or a\nself-hosted/custom Plan app URL.\nPass --mode to choose directly. Local-files mode skips MCP registration and\nauth and installs instructions that default to a no-auth block catalog fetch,\nMDX folders, and the localhost bridge viewer.\n\nWhen installing content with --mode local-files, the CLI installs Content\ninstructions and writes or updates agent-native.json with repo-backed Markdown /\nMDX roots for docs, blog, content, and resources. Use a local Content app, Agent\nNative Desktop, or another trusted local bridge for Content actions to read and\nwrite those files.\n\nWhen installing visual-recap interactively, the CLI offers to add the optional PR\nVisual Recap GitHub Action. Pass --with-github-action to write it directly, then\nrun \"npx @agent-native/core@latest recap setup\" / \"npx @agent-native/core@latest recap doctor\" to configure and\nverify GitHub Actions. Docs: https://www.agent-native.com/docs/pr-visual-recap.\n\nThe status/update commands inspect copied Agent Native skill folders and refresh\ntheir instruction files from the current @agent-native/core package. In generated\napps/workspaces, \"skills update scaffold --project\" refreshes the framework\nskills copied into the scaffold and repairs AGENTS.md / CLAUDE.md and\n.agents/skills / .claude/skills compatibility links.`;\n"]}
1	+ {"version":3,"file":"help.js","sourceRoot":"","sources":["../../../src/cli/skills-content/help.ts"],"names":[],"mappings":"AAAA,MAAM,CAAC,MAAM,IAAI,GAAG;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;qDA4EiC,CAAC","sourcesContent":["export const HELP = `npx @agent-native/core@latest skills\n\nUsage:\n npx @agent-native/core@latest skills list\n npx @agent-native/core@latest skills status [assets\|content\|design-exploration\|visual-edit\|visual-plan\|visual-recap\|visualize-repo\|context-xray\|scaffold] [--client codex\|claude-code\|pi\|all] [--scope user\|project] [--json]\n npx @agent-native/core@latest skills update [assets\|content\|design-exploration\|visual-edit\|visual-plan\|visual-recap\|visualize-repo\|context-xray\|scaffold] [--client codex\|claude-code\|pi\|all] [--scope user\|project] [--dry-run] [--json]\n npx @agent-native/core@latest skills add assets\|content\|design-exploration\|visual-edit\|visual-plan\|visual-recap\|visualize-repo\|context-xray [--client codex\|claude-code\|cowork\|cursor\|opencode\|github-copilot\|all] [--scope user\|project] [--mode hosted\|local-files\|self-hosted] [--mcp-url <url>] [--no-connect] [--with-github-action] [--yes] [--dry-run] [--json]\n npx @agent-native/core@latest skills add <manifest-or-app-dir\|skill-repo> [--skill <name>] [--client ...] [--yes]\n\nExamples:\n npx @agent-native/core@latest skills add assets\n npx @agent-native/core@latest skills add content --mode local-files\n npx @agent-native/core@latest skills add design-exploration\n npx @agent-native/core@latest skills add visual-edit\n npx @agent-native/core@latest skills add visual-plan\n npx @agent-native/core@latest skills add visual-recap\n npx @agent-native/core@latest skills add visualize-repo\n npx @agent-native/core@latest skills add visual-recap --with-github-action\n npx @agent-native/core@latest skills add visual-plan --mode local-files\n npx @agent-native/core@latest skills add visual-plan --mode self-hosted --mcp-url https://my-plan-app.example.com\n npx @agent-native/core@latest skills status visual-plan\n npx @agent-native/core@latest skills update visual-plan\n npx @agent-native/core@latest skills update scaffold --project\n npx @agent-native/core@latest skills add visual-plan --no-connect\n npx @agent-native/core@latest skills add context-xray --client all\n npx @agent-native/core@latest skills add assets --client claude-code\n npx @agent-native/core@latest skills add assets --mcp-url https://my-app.ngrok-free.dev\n npx @agent-native/core@latest skills add ./dist/assets-skill --client codex\n npx @agent-native/core@latest skills add BuilderIO/skills --client codex --scope project\n npx @agent-native/core@latest skills add BuilderIO/skills --with-github-action\n\nThe add command installs the SKILL.md instructions, registers the app-backed\nMCP connector, and then authenticates it in one step so you do not hit an OAuth\nwall on the first tool call. Hosted installs can configure Claude Code, Codex,\nClaude Cowork, Cursor, OpenCode, and GitHub Copilot / VS Code; local-files\ninstruction installs target the shared .agents skill path used by Codex, Pi,\nCursor, OpenCode, Copilot, and similar agents, plus Claude Code's native skill\npath when selected. Pass --client to narrow it. Authentication reuses\n\"npx @agent-native/core@latest connect\": OAuth-capable clients (Claude Code,\nCursor, OpenCode, GitHub Copilot / VS Code) get URL-only entries and authenticate\ninside that host, while Codex / Cowork run the browser device-code flow. In a\nnon-interactive shell or CI the auth step is skipped and the exact\n\"npx @agent-native/core@latest connect <url> --client all\" command is printed instead.\n\nRunning \"npx @agent-native/skills@latest add ...\" uses this same shared install\nflow with the broader BuilderIO skills catalog enabled. Pass --no-connect to\nregister MCP where possible without authenticating (leave auth to the host or run\n\"npx @agent-native/core@latest connect\" later). Pass --mcp-url to register that connector against\na custom origin (an ngrok tunnel, a local dev server, or a self-hosted\ndeployment) instead of the built-in hosted default — a bare origin gets the\nstandard /mcp path appended. Use app-skill pack for marketplace\nbundles and custom adapter output.\n\nWhen installing visual-plan, visual-recap, or visualize-repo interactively, the\nCLI asks where Plans artifacts should live: hosted Plans for shareable\nlinks/comments, local files for \"No sharing, all local.\", or a\nself-hosted/custom Plan app URL.\nPass --mode to choose directly. Local-files mode skips MCP registration and\nauth and installs instructions that default to a no-auth block catalog fetch,\nMDX folders, and the localhost bridge viewer.\n\nWhen installing content with --mode local-files, the CLI installs Content\ninstructions and writes or updates agent-native.json with repo-backed Markdown /\nMDX roots for docs, blog, content, and resources. Use a local Content app, Agent\nNative Desktop, or another trusted local bridge for Content actions to read and\nwrite those files.\n\nWhen installing visual-recap interactively, the CLI offers to add the optional PR\nVisual Recap GitHub Action. Pass --with-github-action to write it directly, then\nrun \"npx @agent-native/core@latest recap setup\" / \"npx @agent-native/core@latest recap doctor\" to configure and\nverify GitHub Actions. Docs: https://www.agent-native.com/docs/pr-visual-recap.\n\nThe status/update commands inspect copied Agent Native skill folders and refresh\ntheir instruction files from the current @agent-native/core package. In generated\napps/workspaces, \"skills update scaffold --project\" refreshes the framework\nskills copied into the scaffold and repairs AGENTS.md / CLAUDE.md and\n.agents/skills / .claude/skills compatibility links.`;\n"]}

package/dist/cli/skills-content/plan-setup-auth.d.ts CHANGED Viewed

@@ -5,5 +5,5 @@
  * `templates/plan/.agents/skills/*`, top-level `skills/*`, and
  * `.agents/skills/*` are guarded byte-identical by `skills.sync.spec.ts`.
  */
-export declare const PLAN_SETUP_AUTH_MD = "## Setup & Authentication\n\nThere are two ways into Plans.\n\n**Coding agent (CLI).** Install once with the Agent-Native CLI. The command\ninstalls the Plans skills, registers the hosted Plans MCP connector, and runs\nauth/setup for the selected local client(s) in the same step (a one-time browser\nsign-in at setup \u2014 this is intended), so the first tool call in that client does\nnot hit an OAuth wall:\n\n```bash\nnpx @agent-native/core@latest skills add visual-plans\n```\n\nAfter that, `/visual-plan`, `/visual-recap`, and `/visualize-repo` are the\ninstalled slash commands. If you only need one command, use\n`skills add visual-plan`, `skills add visual-recap`, or\n`skills add visualize-repo` instead. The other planning modes\n(`create-ui-plan`, `create-prototype-plan`, `create-plan-design`,\n`create-visual-questions`) are MCP tools reachable from `/visual-plan`, not\nseparate slash commands. Pass `--no-connect` to register the connector without\nauthenticating, then run\n`npx @agent-native/core@latest connect https://plan.agent-native.com --client all`\nwhenever you are ready, or choose a narrower `--client`. Auth and MCP tool\nloading are per client config/session.\n\n**Local-only / text installs.** If the user wants no sharing and all local files,\ninstall with `--mode local-files`:\n\n```bash\nnpx @agent-native/core@latest skills add visual-plans --mode local-files\n```\n\nThis mode does not register the Plan MCP connector. Before authoring structured\nMDX, fetch the no-auth, schema-only block catalog with\n`npx @agent-native/core@latest plan blocks --out plan-blocks.md`, read that file,\nwrite the MDX folder locally, run `plan local check`, then run `plan local serve`.\nFor repo-wide visual docs, run\n`npx @agent-native/core@latest visualize-repo --open` to create/update\n`agent-native.json`, seed `.agent-native/visual-docs/repo-overview`, and open\nthe local bridge.\nPlain text skill\ninstalls (Vercel Skills CLI, copied GitHub files, etc.) can follow that same\nlocal flow if `@agent-native/core` is available. Text alone cannot register\nMCP tools; hosted/shareable Plans still need the Agent-Native CLI\ninstall/reconnect step above.\n\n**Browser (people you share with).** Open the Plans editor and create & edit\nwith no sign-up \u2014 you work as a guest. Sign in only when you want to save or\nshare; signing in claims the plans you made as a guest into your account.\n\nSharing and commenting require an account: public/shared plans are viewable by\nanyone with the link, but commenting on them needs an agent-native account.\n\nFor no-account, no-DB plan storage, use local-files mode and the local bridge\ncommand. The optional `plan blocks` lookup reads only public schema metadata.\nIf network access is unavailable, use the bundled references and a local Plan\napp/runtime for validation.\n\nIf a Plans tool returns `needs auth`, `Unauthorized`, or `Session terminated`,\ndo not keep retrying the tool. Stop and give the user the reconnect step for the\nclient they are using: Codex/Codex Desktop should run\n`npx -y @agent-native/core@latest reconnect https://plan.agent-native.com --client codex`\nand start a new Codex session; Claude Code should run `/mcp` and choose\nAuthenticate/Reconnect for the plan connector, or run the reconnect command with\n`--client claude-code` and restart Claude. To refresh every local client config\nthat already has the Plan entry, use `--client all`, then restart/reload each\nclient. Reconnect re-authenticates WITHOUT reinstalling and finds the entry by\nURL regardless of connector name. Never reinstall from scratch just to fix auth.\nContinue once the connector is available.\n\nHosted default: connect `https://plan.agent-native.com/_agent-native/mcp`. Do\nnot put shared secrets in skill files.";
+export declare const PLAN_SETUP_AUTH_MD = "## Setup & Authentication\n\nThere are two ways into Plans.\n\n**Coding agent (CLI).** Install once with the Agent-Native CLI. The command\ninstalls the Plans skills, registers the hosted Plans MCP connector, and runs\nauth/setup for the selected local client(s) in the same step (a one-time browser\nsign-in at setup \u2014 this is intended), so the first tool call in that client does\nnot hit an OAuth wall:\n\n```bash\nnpx @agent-native/core@latest skills add visual-plans\n```\n\nAfter that, `/visual-plan`, `/visual-recap`, and `/visualize-repo` are the\ninstalled slash commands. If you only need one command, use\n`skills add visual-plan`, `skills add visual-recap`, or\n`skills add visualize-repo` instead. The other planning modes\n(`create-ui-plan`, `create-prototype-plan`, `create-plan-design`,\n`create-visual-questions`) are MCP tools reachable from `/visual-plan`, not\nseparate slash commands. Pass `--no-connect` to register the connector without\nauthenticating, then run\n`npx @agent-native/core@latest connect https://plan.agent-native.com --client all`\nwhenever you are ready, or choose a narrower `--client`. Auth and MCP tool\nloading are per client config/session.\n\n**Local-only / text installs.** If the user wants no sharing and all local files,\ninstall with `--mode local-files`:\n\n```bash\nnpx @agent-native/core@latest skills add visual-plans --mode local-files\n```\n\nThis mode does not register the Plan MCP connector. Before authoring structured\nMDX, fetch the no-auth, schema-only block catalog with\n`npx @agent-native/core@latest plan blocks --out plan-blocks.md`, read that file,\nwrite the MDX folder locally, run `plan local check`, then run `plan local serve`.\nFor repo-wide visual docs, run\n`npx @agent-native/core@latest visualize-repo --open` to create/update\n`agent-native.json`, seed `.agent-native/visual-docs/repo-overview`, and open\nthe local bridge.\nPlain text skill\ninstalls (Vercel Skills CLI, copied GitHub files, etc.) can follow that same\nlocal flow if `@agent-native/core` is available. Text alone cannot register\nMCP tools; hosted/shareable Plans still need the Agent-Native CLI\ninstall/reconnect step above.\n\n**Browser (people you share with).** Open the Plans editor and create & edit\nwith no sign-up \u2014 you work as a guest. Sign in only when you want to save or\nshare; signing in claims the plans you made as a guest into your account.\n\nSharing and commenting require an account: public/shared plans are viewable by\nanyone with the link, but commenting on them needs an agent-native account.\n\nFor no-account, no-DB plan storage, use local-files mode and the local bridge\ncommand. The optional `plan blocks` lookup reads only public schema metadata.\nIf network access is unavailable, use the bundled references and a local Plan\napp/runtime for validation.\n\nIf a Plans tool returns `needs auth`, `Unauthorized`, or `Session terminated`,\ndo not keep retrying the tool. Stop and give the user the reconnect step for the\nclient they are using: Codex/Codex Desktop should run\n`npx -y @agent-native/core@latest reconnect https://plan.agent-native.com --client codex`\nand start a new Codex session; Claude Code should run `/mcp` and choose\nAuthenticate/Reconnect for the plan connector, or run the reconnect command with\n`--client claude-code` and restart Claude. To refresh every local client config\nthat already has the Plan entry, use `--client all`, then restart/reload each\nclient. Reconnect re-authenticates WITHOUT reinstalling and finds the entry by\nURL regardless of connector name. Never reinstall from scratch just to fix auth.\nContinue once the connector is available.\n\nHosted default: connect `https://plan.agent-native.com/mcp`. Do\nnot put shared secrets in skill files.";
 //# sourceMappingURL=plan-setup-auth.d.ts.map

package/dist/cli/skills-content/plan-setup-auth.d.ts.map CHANGED Viewed

	@@ -1 +1 @@
1	- {"version":3,"file":"plan-setup-auth.d.ts","sourceRoot":"","sources":["../../../src/cli/skills-content/plan-setup-auth.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AACH,eAAO,MAAM,kBAAkB,~~ytHAwEQ~~,CAAC"}
1	+ {"version":3,"file":"plan-setup-auth.d.ts","sourceRoot":"","sources":["../../../src/cli/skills-content/plan-setup-auth.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AACH,eAAO,MAAM,kBAAkB,2sHAwEQ,CAAC"}

package/dist/cli/skills-content/plan-setup-auth.js CHANGED Viewed

@@ -76,6 +76,6 @@ client. Reconnect re-authenticates WITHOUT reinstalling and finds the entry by
 URL regardless of connector name. Never reinstall from scratch just to fix auth.
 Continue once the connector is available.
-Hosted default: connect \`https://plan.agent-native.com/_agent-native/mcp\`. Do
+Hosted default: connect \`https://plan.agent-native.com/mcp\`. Do
 not put shared secrets in skill files.`;
 //# sourceMappingURL=plan-setup-auth.js.map

package/dist/cli/skills-content/plan-setup-auth.js.map CHANGED Viewed

	@@ -1 +1 @@
1	- {"version":3,"file":"plan-setup-auth.js","sourceRoot":"","sources":["../../../src/cli/skills-content/plan-setup-auth.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AACH,MAAM,CAAC,MAAM,kBAAkB,GAAG;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;uCAwEK,CAAC","sourcesContent":["/*\n Setup/auth block for the `/visual-plan` skill. Interpolated into\n * `VISUAL_PLANS_SKILL_MD` below so the install + one-step authenticate\n * instructions are single-sourced. The materialized SKILL.md copies under\n * `templates/plan/.agents/skills/`, top-level `skills/`, and\n * `.agents/skills/` are guarded byte-identical by `skills.sync.spec.ts`.\n /\nexport const PLAN_SETUP_AUTH_MD = `## Setup & Authentication\n\nThere are two ways into Plans.\n\nCoding agent (CLI). Install once with the Agent-Native CLI. The command\ninstalls the Plans skills, registers the hosted Plans MCP connector, and runs\nauth/setup for the selected local client(s) in the same step (a one-time browser\nsign-in at setup — this is intended), so the first tool call in that client does\nnot hit an OAuth wall:\n\n\\`\\`\\`bash\nnpx @agent-native/core@latest skills add visual-plans\n\\`\\`\\`\n\nAfter that, \\`/visual-plan\\`, \\`/visual-recap\\`, and \\`/visualize-repo\\` are the\ninstalled slash commands. If you only need one command, use\n\\`skills add visual-plan\\`, \\`skills add visual-recap\\`, or\n\\`skills add visualize-repo\\` instead. The other planning modes\n(\\`create-ui-plan\\`, \\`create-prototype-plan\\`, \\`create-plan-design\\`,\n\\`create-visual-questions\\`) are MCP tools reachable from \\`/visual-plan\\`, not\nseparate slash commands. Pass \\`--no-connect\\` to register the connector without\nauthenticating, then run\n\\`npx @agent-native/core@latest connect https://plan.agent-native.com --client all\\`\nwhenever you are ready, or choose a narrower \\`--client\\`. Auth and MCP tool\nloading are per client config/session.\n\nLocal-only / text installs. If the user wants no sharing and all local files,\ninstall with \\`--mode local-files\\`:\n\n\\`\\`\\`bash\nnpx @agent-native/core@latest skills add visual-plans --mode local-files\n\\`\\`\\`\n\nThis mode does not register the Plan MCP connector. Before authoring structured\nMDX, fetch the no-auth, schema-only block catalog with\n\\`npx @agent-native/core@latest plan blocks --out plan-blocks.md\\`, read that file,\nwrite the MDX folder locally, run \\`plan local check\\`, then run \\`plan local serve\\`.\nFor repo-wide visual docs, run\n\\`npx @agent-native/core@latest visualize-repo --open\\` to create/update\n\\`agent-native.json\\`, seed \\`.agent-native/visual-docs/repo-overview\\`, and open\nthe local bridge.\nPlain text skill\ninstalls (Vercel Skills CLI, copied GitHub files, etc.) can follow that same\nlocal flow if \\`@agent-native/core\\` is available. Text alone cannot register\nMCP tools; hosted/shareable Plans still need the Agent-Native CLI\ninstall/reconnect step above.\n\nBrowser (people you share with). Open the Plans editor and create & edit\nwith no sign-up — you work as a guest. Sign in only when you want to save or\nshare; signing in claims the plans you made as a guest into your account.\n\nSharing and commenting require an account: public/shared plans are viewable by\nanyone with the link, but commenting on them needs an agent-native account.\n\nFor no-account, no-DB plan storage, use local-files mode and the local bridge\ncommand. The optional \\`plan blocks\\` lookup reads only public schema metadata.\nIf network access is unavailable, use the bundled references and a local Plan\napp/runtime for validation.\n\nIf a Plans tool returns \\`needs auth\\`, \\`Unauthorized\\`, or \\`Session terminated\\`,\ndo not keep retrying the tool. Stop and give the user the reconnect step for the\nclient they are using: Codex/Codex Desktop should run\n\\`npx -y @agent-native/core@latest reconnect https://plan.agent-native.com --client codex\\`\nand start a new Codex session; Claude Code should run \\`/mcp\\` and choose\nAuthenticate/Reconnect for the plan connector, or run the reconnect command with\n\\`--client claude-code\\` and restart Claude. To refresh every local client config\nthat already has the Plan entry, use \\`--client all\\`, then restart/reload each\nclient. Reconnect re-authenticates WITHOUT reinstalling and finds the entry by\nURL regardless of connector name. Never reinstall from scratch just to fix auth.\nContinue once the connector is available.\n\nHosted default: connect \\`https://plan.agent-native.com/~~_agent-native/~~mcp\\`. Do\nnot put shared secrets in skill files.`;\n"]}
1	+ {"version":3,"file":"plan-setup-auth.js","sourceRoot":"","sources":["../../../src/cli/skills-content/plan-setup-auth.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AACH,MAAM,CAAC,MAAM,kBAAkB,GAAG;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;uCAwEK,CAAC","sourcesContent":["/*\n Setup/auth block for the `/visual-plan` skill. Interpolated into\n * `VISUAL_PLANS_SKILL_MD` below so the install + one-step authenticate\n * instructions are single-sourced. The materialized SKILL.md copies under\n * `templates/plan/.agents/skills/`, top-level `skills/`, and\n * `.agents/skills/` are guarded byte-identical by `skills.sync.spec.ts`.\n /\nexport const PLAN_SETUP_AUTH_MD = `## Setup & Authentication\n\nThere are two ways into Plans.\n\nCoding agent (CLI). Install once with the Agent-Native CLI. The command\ninstalls the Plans skills, registers the hosted Plans MCP connector, and runs\nauth/setup for the selected local client(s) in the same step (a one-time browser\nsign-in at setup — this is intended), so the first tool call in that client does\nnot hit an OAuth wall:\n\n\\`\\`\\`bash\nnpx @agent-native/core@latest skills add visual-plans\n\\`\\`\\`\n\nAfter that, \\`/visual-plan\\`, \\`/visual-recap\\`, and \\`/visualize-repo\\` are the\ninstalled slash commands. If you only need one command, use\n\\`skills add visual-plan\\`, \\`skills add visual-recap\\`, or\n\\`skills add visualize-repo\\` instead. The other planning modes\n(\\`create-ui-plan\\`, \\`create-prototype-plan\\`, \\`create-plan-design\\`,\n\\`create-visual-questions\\`) are MCP tools reachable from \\`/visual-plan\\`, not\nseparate slash commands. Pass \\`--no-connect\\` to register the connector without\nauthenticating, then run\n\\`npx @agent-native/core@latest connect https://plan.agent-native.com --client all\\`\nwhenever you are ready, or choose a narrower \\`--client\\`. Auth and MCP tool\nloading are per client config/session.\n\nLocal-only / text installs. If the user wants no sharing and all local files,\ninstall with \\`--mode local-files\\`:\n\n\\`\\`\\`bash\nnpx @agent-native/core@latest skills add visual-plans --mode local-files\n\\`\\`\\`\n\nThis mode does not register the Plan MCP connector. Before authoring structured\nMDX, fetch the no-auth, schema-only block catalog with\n\\`npx @agent-native/core@latest plan blocks --out plan-blocks.md\\`, read that file,\nwrite the MDX folder locally, run \\`plan local check\\`, then run \\`plan local serve\\`.\nFor repo-wide visual docs, run\n\\`npx @agent-native/core@latest visualize-repo --open\\` to create/update\n\\`agent-native.json\\`, seed \\`.agent-native/visual-docs/repo-overview\\`, and open\nthe local bridge.\nPlain text skill\ninstalls (Vercel Skills CLI, copied GitHub files, etc.) can follow that same\nlocal flow if \\`@agent-native/core\\` is available. Text alone cannot register\nMCP tools; hosted/shareable Plans still need the Agent-Native CLI\ninstall/reconnect step above.\n\nBrowser (people you share with). Open the Plans editor and create & edit\nwith no sign-up — you work as a guest. Sign in only when you want to save or\nshare; signing in claims the plans you made as a guest into your account.\n\nSharing and commenting require an account: public/shared plans are viewable by\nanyone with the link, but commenting on them needs an agent-native account.\n\nFor no-account, no-DB plan storage, use local-files mode and the local bridge\ncommand. The optional \\`plan blocks\\` lookup reads only public schema metadata.\nIf network access is unavailable, use the bundled references and a local Plan\napp/runtime for validation.\n\nIf a Plans tool returns \\`needs auth\\`, \\`Unauthorized\\`, or \\`Session terminated\\`,\ndo not keep retrying the tool. Stop and give the user the reconnect step for the\nclient they are using: Codex/Codex Desktop should run\n\\`npx -y @agent-native/core@latest reconnect https://plan.agent-native.com --client codex\\`\nand start a new Codex session; Claude Code should run \\`/mcp\\` and choose\nAuthenticate/Reconnect for the plan connector, or run the reconnect command with\n\\`--client claude-code\\` and restart Claude. To refresh every local client config\nthat already has the Plan entry, use \\`--client all\\`, then restart/reload each\nclient. Reconnect re-authenticates WITHOUT reinstalling and finds the entry by\nURL regardless of connector name. Never reinstall from scratch just to fix auth.\nContinue once the connector is available.\n\nHosted default: connect \\`https://plan.agent-native.com/mcp\\`. Do\nnot put shared secrets in skill files.`;\n"]}

package/dist/cli/skills-content/visual-plan-skill.d.ts CHANGED Viewed

@@ -1,2 +1,2 @@
-export declare const VISUAL_PLANS_SKILL_MD = "---\nname: visual-plan\ndescription: >-\n  Turn ordinary text plans into rich interactive visual plans with diagrams,\n  file maps, annotated code, open questions, and UI/prototype review when\n  useful.\nmetadata:\n  visibility: exported\n---\n\n# Agent-Native Plans\n\nAgent-Native Plans is structured visual planning mode for coding agents. Build\nthe plan you would normally write in Markdown, but as a scannable document with\neditable blocks mixed in: inline diagrams, code snippets,\nopen questions, and an optional top visual review area (wireframe canvas, live\nprototype, or both in tabs). Architecture and backend plans stay document-only;\nUI and product plans start with the top canvas/prototype (the Visual Surface\nChoice section owns that rule).\n\n`/visual-plan` is the packaged command and main entry point. Choose the review\nmode from the task: UI-first when the work is primarily product UI and review\nshould start with screens, prototype-first when review should start with a\nfunctional live prototype, design-first when review needs full-fidelity branded\nscreens, or visual-intake when the user explicitly wants a questionnaire before\nplanning. When a Codex, Claude Code, Markdown, or pasted plan already exists,\n`/visual-plan` uses that source plan as the starting point and builds the review\nsurface from it instead of starting over.\n\n## When To Use\n\nCreate or adapt a visual plan whenever the plan would be better as a reviewable\nartifact than a chat paragraph. This includes modest work such as a single UI\nsurface with states, a small workflow, a before/after product change, or a\ncomponent/API/data-shape decision that needs alignment, plus larger multi-file,\nambiguous, long-running, risky, or UI-heavy work. Use it when architecture /\ndata flow / UI direction / options / open questions would benefit from inline\ndiagrams or structured blocks, when the user needs to react to a direction\nbefore you implement, or when an existing text plan needs a richer review\nsurface.\n\n## Plan Discipline\n\n- **Gate thoughtfully.** A visual plan is a richer review surface, not only a\n  tool for giant projects. Use it when the user needs to see, compare, comment\n  on, or approve a direction before code, even for a modest UI/state/workflow\n  change. Skip it for truly trivial, unambiguous work \u2014 typos, one-line fixes, a\n  single well-specified function, anything whose diff you could describe in one\n  sentence \u2014 and just make the change. Never pad a plan with filler and never\n  ship a single-step plan.\n- **Research before you draft.** Read the real files, actions, schema, and\n  patterns first; name actual files, symbols, and data shapes instead of\n  inventing them. Check existing `actions/` before proposing endpoints and prefer\n  named client helpers over raw fetch. Delegate wide exploration to a sub-agent.\n  Lead with reuse: for each step, name what it reuses \u2014 existing actions, schema,\n  components, helpers \u2014 before what it adds, so the plan explains the genuinely new\n  delta instead of redescribing what already exists.\n- **Decide the hard-to-reverse bets first.** For non-trivial backend, data, or API\n  work, sketch where the feature is headed, then call out the decisions that are\n  expensive to undo once data or callers depend on them \u2014 wire format, public ids,\n  data-model shape, auth and ownership boundaries \u2014 and get those right in the plan\n  even if most of the feature ships later. Then scope to the smallest first cut that\n  proves the approach without foreclosing it, stating both what is in and what is\n  explicitly deferred.\n- **Keep examples at the right altitude.** When the user's idea is a broad\n  framework, product, or operating-model change, do not collapse it into the\n  first concrete example, provider, or sync path they mention. Separate the core\n  abstraction from motivating examples and app/provider adapters. Use examples\n  to make the plan legible, but label them as examples unless they are the whole\n  requested scope.\n- **Publish standalone plans.** If the user pasted, referenced, or already has a\n  Codex / Claude Code / Markdown plan, treat it as source material, but rewrite\n  the published plan as a clean standalone proposal. Preserve the source plan's\n  useful intent and codebase facts, label inferred visuals as inferred, and avoid\n  revision language such as \"preserve the prior plan\", \"do not drop the old\n  idea\", \"unlike the previous version\", or \"this revision changes...\". A reader\n  who never saw the chat or earlier drafts should understand the plan.\n- **Make the first read concrete.** If the plan is meant to be shared with\n  someone outside the chat, or if the concept is abstract, lead near the top with\n  one concrete product example before mode tables, architecture, or roadmaps. For\n  UI-capable concepts, that usually means a top-canvas app state that shows the\n  real user workflow in product terms. Do not rely on phrases that only make\n  sense in conversation, and do not frame the plan as \"not the old idea\"; state\n  the positive model directly.\n- **Planning is read-only.** Make no source edits while building or reviewing the\n  plan. Start editing only after the user approves the direction.\n- **Clarify vs. assume.** Do not ask how to build it \u2014 explore and present the\n  approach and options in the plan. Ask a clarifying question only when an\n  ambiguity would change the design and you cannot resolve it from the code; use\n  the host agent's normal ask-user-question flow and batch 2-4 high-leverage\n  questions before finalizing. Do not call `create-visual-questions` for\n  ordinary clarification or preflight; reserve it for the visual-intake mode when\n  the user explicitly asks for a visual intake questionnaire. Otherwise state the\n  assumption explicitly and proceed, and keep anything unresolved in the plan's\n  single bottom `question-form` Open Questions block. For complex plans, do a\n  final open-question pass before handoff: if a decision would affect\n  architecture, scope, UX, data shape, or rollout, either decide it in the plan\n  with rationale or put it in that bottom form with a recommended default.\n- **The plan is the approval gate.** After surfacing it, ask the user to review\n  and approve before you write code, and name which files/areas the work touches.\n  Presenting the plan and requesting sign-off is the approval step \u2014 do not ask a\n  separate \"does this look good?\" question.\n- **The document is the source of truth, not the chat.** When scope shifts,\n  update the plan with `update-visual-plan` rather than only changing course in\n  chat, and make the updated document stand alone. Do not describe the update as\n  a correction to an earlier draft inside the plan itself. Re-read the approved\n  plan before major steps.\n\n## Create A Structured Agent-Native Plan \u2014 Never Inline\n\nThe deliverable is ALWAYS a structured Agent-Native Plan, not a chat-only plan.\nThe hosted Plan MCP connector (`plan` server, or legacy `agent-native-plans`) is\nthe default collaboration and commenting surface; it is not a reason to reject\nthe planning pattern as an external dependency or rented layer. Plans are\nportable source artifacts (`plan.mdx`, optional `canvas.mdx` /\n`prototype.mdx`, JSON, and HTML export), and ownership-sensitive workflows can\nuse local-files mode or a self-hosted/custom Plan app URL without abandoning the\nskill's review discipline. Do not advise the user to skip `/visual-plan` because\nthe default surface is hosted; choose the right Plan mode for the user's\nownership, privacy, sharing, and branding needs.\n\nBy default, create the plan via the Plan MCP connector and NEVER hand it over as\ninline chat content \u2014 no Markdown prose, ASCII sketch, table, or fenced\nwireframe. If the `plan` (or legacy `agent-native-plans`) tools are not visible,\ndiscover them through the host's `tool_search` first; if they are still missing,\nSTOP and give the user the client-specific reconnect step rather than improvising\nan inline plan. Before publishing, or whenever a connector or auth error appears,\nREAD `references/connection.md` in this skill directory \u2014 it is the single source\nof truth for the never-inline rule, connector discovery, and the per-client\nreconnect steps. Local-files privacy mode (after Tool Guidance) is the exception.\n\n## Core Workflow\n\nThis section describes the default hosted Plan MCP workflow. If\n`AGENT_NATIVE_PLANS_MODE=local-files` is set, or the user asks for fully local\nfiles/no hosted Plan writes, use **Local-Files Privacy Mode** instead; carry\nforward only the code-research and plan-composition guidance here.\n\n1. Follow the host agent's normal planning flow: inspect the codebase, delegate\n   wide exploration when useful, gather the info needed, and ask native\n   clarifying questions as needed before generating the plan. If a source plan\n   already exists, gather its exact text from the user's paste, a referenced\n   file, or recent visible agent context; do not invent source text.\n2. Call `get-plan-blocks` for the authoritative block catalog \u2014 do not author\n   from memorized tags. Then call the mode-matched create tool:\n   `create-visual-plan` for document-first plans (architecture, backend, data,\n   refactor, API), `create-ui-plan` for UI-first plans, `create-prototype-plan`\n   for prototype-first plans, `create-plan-design` for design-first plans,\n   `create-visual-questions` only when the user explicitly asks for a visual\n   intake questionnaire. When a source plan already exists,\n   pass it as `planText` and preserve the original plan's useful intent while\n   producing a standalone plan document, not a revision memo.\n3. For UI/product plans, compose the top canvas first with the primary\n   wireframes and annotated states, then write the document with native blocks\n   (see `references/canvas.md` and `references/document-quality.md`). For\n   broad product architecture plans with a user-facing implication, add a\n   concrete \"what this looks like in the app\" visual before the abstract\n   architecture or mode tables. Keep the document close to the standalone\n   Markdown plan the agent would normally output. If an existing plan was\n   provided, carry forward the right facts and decisions without referring to\n   the previous draft or explaining how this version differs. For non-visual\n   plans, skip the top visual surface (Visual Surface Choice below owns the rule)\n   and put `diagram`, `data-model`,\n   `api-endpoint`, `diff`, `file-tree`, `code`, and `annotated-code` blocks\n   directly next to the relevant prose.\n   Wide document layout is renderer-owned and intentionally allowlisted: only\n   literal code-review surfaces (`diff`, `annotated-code`) and `tabs` blocks\n   with vertical orientation or diff-like children break out wider than prose.\n   Keep `api-endpoint`, `openapi-spec`, `data-model`, `json-explorer`,\n   `wireframe`, question, and `custom-html` blocks in normal document flow unless\n   their own renderer says otherwise.\n4. Surface the returned Plans link or inline MCP App and ask the user to review.\n   Always include the actual URL in chat so the next step is a click in CLI or\n   other text-only hosts. When the host exposes an embedded browser/preview panel\n   and a tool can open arbitrary URLs there, open the returned plan URL\n   automatically for convenient review \u2014 a convenience and smoke test, never the\n   only handoff or the access\n   model. Plans should load out of the box for the local agent and local browser\n   session; if a signed-in embedded browser cannot read a local plan that an\n   anonymous/tool check can read, fix the app/action ownership or access path\n   rather than patching one plan by hand. For high-stakes plans (architecture,\n   backend, data, multi-file, or risky), also kick off the self-review pass in\n   **Self-Review Before Handoff** while the user reads, instead of blocking the\n   handoff on it.\n5. For hosted plans, call `get-plan-feedback` before editing, after review,\n   after any long pause,\n   and before the final response. Treat `anchorDetails`, resolver intent, recent\n   review events, and any focused screenshots from browser handoff as the source\n   of truth for exactly what changed and exactly what each comment points at.\n6. For hosted plans, apply changes with `update-visual-plan`, preferring\n   targeted `contentPatches`.\n   Treat the top-level `content` payload as a full replacement, not a merge; do\n   not send a partial `content` object to add a canvas or one block. If a full\n   replacement is unavoidable, first read the complete plan source/content, carry\n   forward every existing block and visual surface, and verify the source/export\n   afterward so the document body was not truncated. When the user wants\n   source-control friendly edits, use `patch-visual-plan-source` against the MDX\n   files instead of regenerating the plan.\n7. For hosted plans, export with `export-visual-plan` only when the user wants a\n   shareable receipt or repo-check-in artifacts.\n\n## Self-Review Before Handoff\n\nFor high-stakes plans \u2014 architecture, backend, data-model, migration, multi-file,\nor otherwise risky work \u2014 run one adversarial self-review pass before treating the\nplan as final. Skip it for small, UI-only, or single-decision plans where the cost\noutweighs the value. Keep the pass cheap and non-blocking:\n\n- **Surface the plan first, review concurrently.** Post the link and let the user\n  start reading, then run the review in parallel \u2014 never make the user wait on it.\n- **Review the written plan; do not re-research.** Critique the plan text and its\n  own blocks. The grounding was already done while drafting, so the review checks\n  the output instead of re-exploring the repo.\n- **Spawn one skeptical reviewer** whose only job is to find what is weak, missing,\n  or wrong \u2014 not to praise. Point it at: hard-to-reverse decisions made implicitly\n  or not at all (wire format, public ids, data-model shape, auth, ownership); steps\n  not anchored in real files or symbols; a menu of options where the plan should\n  commit to one; obvious missing decisions (\"what happens when X?\", \"why not Y?\");\n  and padding or single-step filler.\n- **Fix vs. ask.** Apply clear-cut fixes yourself with `update-visual-plan`\n  `contentPatches` \u2014 vague non-goals, unanchored claims, an obvious missing\n  decision. Route genuine judgment calls back to the user instead: add them to the\n  bottom `question-form` Open Questions block or batch them into the normal\n  ask-user-question flow. Do not silently decide them.\n- **Do not surprise the user mid-read.** On a large plan, apply the patches before\n  the editor loads; otherwise note briefly that a self-review is running so the\n  plan changing under them is expected. When you next respond, summarize what the\n  review changed and what it surfaced for the user to decide.\n\n## Visual Surface Choice\n\nChoose the surface before creating the plan or after reading the source plan. Do\nnot add visual chrome by default:\n\nFor UI/product plans, the top canvas is usually the primary review surface. Put\nthe first meaningful wireframes there, not buried as document-body blocks. Use\nmultiple canvas artboards when states matter, such as the default view, an\noverflow menu or popover, a side panel, loading, or error. Put short annotations\nbeside frames with `targetId` plus `placement`; keep implementation details,\ntradeoffs, file maps, data contracts, risks, and verification in the document\nbody below the canvas.\n\nWhen the user asks for a flow, storyboard, journey, wireframe, canvas, or \"what\nthis looks like\", treat that as a canvas-first request. Make one artboard per\nuser-visible state, connect only adjacent transitions, and use short canvas\nannotations for the product notes. Do not substitute a document-body `diagram`\nblock for the requested storyboard just because HTML diagrams are faster to\nwrite; diagrams belong below the canvas for backend mechanics, architecture, or\ndata-flow explanation.\n\nKeep product wireframes and explanatory/meta diagrams separate. Start with pure\nscreens that look like the app state under discussion, without callout prose or\narchitecture notes embedded inside the UI. Put arrows, labels, contracts, data\nflow, and mode explanations in separate annotations, separate canvas diagrams,\nor the document body.\n\nWhen the plan touches an existing app, inspect the current shell/components\nbefore drawing. The first artboard should look like the real app at the same\ndensity: existing sidebars, toolbar placement, overflow menus, app chrome, and\nframework agent chrome stay in their real places. Model secondary surfaces as\nseparate states, such as a top-right overflow popover, sheet, panel, loading\nstate, or separate AgentSidebar, rather than inventing a permanent inspector or\nfolding framework chrome into the product UI.\n\n- **No visual surface** for architecture-only, backend-only, data migration,\n  copy-only, or otherwise non-visual plans. Do not use the top canvas for\n  architecture diagrams, dependency maps, file plans, API contracts, or\n  data-flow-only reviews. Use a strong document with local inline diagrams\n  only when relationships need a visual explanation, usually one spatial diagram\n  per recommendation or decision. Prefer grouped regions, layers, quadrants,\n  matrices, or before/after panels over a single-axis chain unless the\n  relationship is truly sequential.\n- **Canvas only** for one static screen, a before/after comparison, a component\n  state, a small popover, or a visual direction that does not require clicking.\n  Put those wireframes in `content.canvas` and omit `content.prototype`.\n- **Canvas + prototype** for multi-step UI flows, onboarding, wizards,\n  review/approval flows, navigation changes, or anything where the reviewer\n  needs to operate the behavior. Keep the static wireframes in\n  `content.canvas`, add the aligned functional prototype in\n  `content.prototype`, and rely on the top visual tabs to switch between them.\n- **Prototype-first** when the user asks to operate the UI or when interaction is\n  the main question. Use `create-prototype-plan`, which still preserves static\n  mocks where useful.\n\nFor mixed canvas + prototype plans, reuse the same real labels, app statuses,\nand screen ids across both surfaces. The canvas is the inspectable static reference;\nthe prototype is the interactive version of that same flow, not a separate\ndesign direction.\n\n## Wireframe quality \u2014 read `references/wireframe.md`\n\nUI recap/plan wireframes must meet a strict quality bar \u2014 full-width chrome,\npinned bottom bars, real product content, before/after comparability, the right\n`surface` preset, `--wf-*` tokens instead of hex, and no `<html>`/`<style>`/font\ntags. Before authoring ANY wireframe / `<Screen>` / `WireframeBlock`, READ\n`references/wireframe.md` in this skill directory \u2014 it is the single source of\ntruth for HTML wireframe quality, shared word for word with `/visual-plan`\nand `/visual-recap`. Do not author wireframes from memory.\n\n## Canvas \u2014 read `references/canvas.md`\n\nThe canvas is the single source of truth for static UI mockups: the `surface`\nlocks each artboard's footprint, mixed surfaces lay out\nin lanes, annotations are plain-text designer notes anchored by\n`targetId`/`placement`, and edits are surgical `contentPatches`. Before\nauthoring or editing ANY canvas, artboard, or annotation, READ\n`references/canvas.md` in this skill directory \u2014 it is the single source of truth\nfor canvas/artboard mechanics. Do not author canvas layouts from memory.\nCanvas artboards use the same HTML wireframe path as document-body\n`WireframeBlock` screens: author `<Screen surface=\"...\" html={...} />` with a\nsemantic HTML fragment. Do not author fresh kit-tree children such as\n`<FrameScreen>`, `<Card>`, `<Row>`, or `<Btn>` inside canvas `<Screen>` tags;\nthose are legacy compatibility markup for old plans and produce brittle canvas\nlayouts.\n\n## Document quality \u2014 read `references/document-quality.md`\n\nThe document is a serious technical plan, not marketing: outcome-first,\nprose-first, self-contained, built from the right native blocks, with open\nquestions in a single bottom `question-form` and a pre-handoff visual check.\nBefore authoring the plan document, READ `references/document-quality.md` in this\nskill directory \u2014 it is the single source of truth for the document quality bar.\nDo not write the document from memory.\n\n## Good vs. bad exemplar \u2014 read `references/exemplar.md`\n\nFor a worked example of the bar \u2014 a great UI-first plan and `/visual-plan`, plus\nthe anti-patterns to avoid \u2014 READ `references/exemplar.md` in this skill\ndirectory before authoring a plan.\n\n## Tool Guidance\n\n- `create-visual-plan`: start one structured visual plan per agent task/run, or\n  import an existing text plan by passing `planText`; `content` may include no\n  visual surface, canvas only, or canvas + prototype.\n- `create-ui-plan`: start a UI-first plan when the work is primarily product UI.\n- `create-prototype-plan`: start a prototype-first plan with a functional top\n  review surface.\n- `create-plan-design`: start a full-fidelity branded Design-tab plan with an\n  optional matching Prototype tab.\n- `convert-visual-plan-to-prototype`: convert an existing HTML wireframe canvas\n  into a prototype plan.\n- `create-visual-questions`: use only when the user explicitly asks for a visual\n  intake questionnaire, not as `/visual-plan` preflight.\n- `update-visual-plan`: revise content, status, or comments with targeted\n  `contentPatches` (see Core Workflow step 6).\n- `read-visual-plan-source`: read the normalized plan as `plan.mdx`,\n  optional `canvas.mdx`, optional `.plan-state.json`, and JSON.\n- `patch-visual-plan-source`: apply granular MDX AST patches by stable block,\n  artboard, annotation, component, or wireframe-node id.\n- `import-visual-plan-source`: create or replace a plan from an MDX folder.\n- `get-visual-plan`: read the current structured plan, exported HTML, and\n  annotations; it also returns the MDX folder for source workflows.\n- `get-plan-feedback`: read unconsumed human feedback. Use it frequently; it\n  returns grouped threads, exact anchor details, expected resolver, and recent\n  review-event payloads so agents can act only on the comments meant for them.\n- `get-plan-blocks`: resolve block tags before authoring \u2014 do not memorize tags;\n  call this first to get the authoritative tag names, required fields, and prop\n  shapes from the live block registry.\n- `export-visual-plan`: export HTML, Markdown fallback, structured JSON, and MDX\n  files for repo check-in.\n\nWhen the user critiques a plan's look or structure, fix the renderer or this\nskill \u2014 never hand-edit one stored plan. Turn feedback into better guidance.\n\n## Local-Files Privacy Mode \u2014 read `references/local-files.md`\n\nWhen the user wants no hosted Plan database writes \u2014 no DB writes, no Plan MCP\npublish, fully local/offline/private planning, repo-owned source-controlled\nartifacts, or `AGENT_NATIVE_PLANS_MODE=local-files` \u2014 do not call any hosted Plan\ntool except the schema-only `get-plan-blocks` catalog lookup. Author a local MDX\nfolder and\npreview it with `plan local check` / `plan local serve` / `plan local verify`.\nBefore using local-files mode, READ `references/local-files.md` in this skill\ndirectory \u2014 it is the single source of truth for the full contract (catalog\nlookup, MDX folder layout, the local bridge commands, and the hosted tools you\nmust not call). Carry forward only the code-research and plan-composition\nguidance from Core Workflow; everything hosted is replaced by the local bridge.\n\n## Interpreting comment anchors\n\nThis section applies to hosted plans with `get-plan-feedback` /\n`update-visual-plan`. In local-files mode, do not call hosted feedback or update\ntools; interpret file/chat feedback directly, edit the MDX files, rerun the\nlocal bridge check/serve/verify command, and report the new local URL.\n\n`get-plan-feedback` returns rich anchors \u2014 read them before acting on any comment.\n\n- **Coordinate frames.** `targetX`/`targetY` are percentages *within* the\n  element named by `targetSelector`/`targetKind`. Bare `x`/`y` are percentages\n  of the whole plan document. `canvasX`/`canvasY` are raw board-world pixels on\n  the design canvas (board size given when available).\n- **Wireframe pins.** Anchors on wireframes include `targetNodeId` and\n  `targetNodePath` (e.g. `card > list > listItem \"Acme Inc\"`) identifying the\n  exact kit node. Use `targetNodeId` directly with wireframe node patch ops;\n  use `data-design-id` values from design artboards with\n  `update-design-element-style`. Prefer the node id/path over raw coordinates;\n  fall back to coordinates plus the focused screenshot (red ring marks the exact\n  point) only when no node id is present.\n- **Text quotes.** Resolve `textQuote` against current prose using\n  `contextBefore`/`contextAfter` for disambiguation. If `ambiguous: true`, ask\n  the user \u2014 do not guess which occurrence is meant.\n- **Detached comments.** `get-plan-feedback` flags threads whose quoted text no\n  longer exists as `detached` (in `detachedThreads`). Reconcile these against\n  rewritten content \u2014 never silently drop them.\n- **Routing.** `resolutionTarget` is the only routing signal: act on `agent`,\n  treat `human` as context only. `@mentions` are people to notify, never a\n  routing signal.\n- **Two-axis state.** Mark every ingested comment as consumed\n  (`consumedCommentIds` on `update-visual-plan`). Set `status=resolved` only on\n  agent-targeted comments you actually addressed; leave human-targeted comments\n  open.\n\n## Visibility & Sharing\n\nUse `set-resource-visibility` to change who can see a plan (e.g. public, login,\nor org-scoped). Use `share-resource` to grant specific users or roles access\nby email or role. Gate visibility before sharing any plan that covers\nunreleased or private work \u2014 default to the narrowest scope that meets the\nreview need.\n\n## Setup & Authentication\n\nThere are two ways into Plans.\n\n**Coding agent (CLI).** Install once with the Agent-Native CLI. The command\ninstalls the Plans skills, registers the hosted Plans MCP connector, and runs\nauth/setup for the selected local client(s) in the same step (a one-time browser\nsign-in at setup \u2014 this is intended), so the first tool call in that client does\nnot hit an OAuth wall:\n\n```bash\nnpx @agent-native/core@latest skills add visual-plans\n```\n\nAfter that, `/visual-plan`, `/visual-recap`, and `/visualize-repo` are the\ninstalled slash commands. If you only need one command, use\n`skills add visual-plan`, `skills add visual-recap`, or\n`skills add visualize-repo` instead. The other planning modes\n(`create-ui-plan`, `create-prototype-plan`, `create-plan-design`,\n`create-visual-questions`) are MCP tools reachable from `/visual-plan`, not\nseparate slash commands. Pass `--no-connect` to register the connector without\nauthenticating, then run\n`npx @agent-native/core@latest connect https://plan.agent-native.com --client all`\nwhenever you are ready, or choose a narrower `--client`. Auth and MCP tool\nloading are per client config/session.\n\n**Browser (people you share with).** Open the Plans editor and create & edit\nwith no sign-up \u2014 you work as a guest. Sign in only when you want to save or\nshare; signing in claims the plans you made as a guest into your account.\n\nSharing and commenting require an account: public/shared plans are viewable by\nanyone with the link, but commenting on them needs an agent-native account.\n\nFor fully offline, no-account use, run the Plans app locally and sync plans to\nyour repo as MDX. This local mode is a separate advanced path, not the default\nhosted flow.\n\nFor repo-wide visual docs, run\n`npx @agent-native/core@latest visualize-repo --open` to create/update\n`agent-native.json`, seed `.agent-native/visual-docs/repo-overview`, and open\nthe local bridge.\n\nIf a Plans tool returns `needs auth`, `Unauthorized`, or `Session terminated`, do\nnot keep retrying it \u2014 stop and give the user the per-client reconnect step from\n`references/connection.md`, then continue once the connector is available.\n\nHosted default: connect `https://plan.agent-native.com/_agent-native/mcp`. Do\nnot put shared secrets in skill files.\n";
+export declare const VISUAL_PLANS_SKILL_MD = "---\nname: visual-plan\ndescription: >-\n  Turn ordinary text plans into rich interactive visual plans with diagrams,\n  file maps, annotated code, open questions, and UI/prototype review when\n  useful.\nmetadata:\n  visibility: exported\n---\n\n# Agent-Native Plans\n\nAgent-Native Plans is structured visual planning mode for coding agents. Build\nthe plan you would normally write in Markdown, but as a scannable document with\neditable blocks mixed in: inline diagrams, code snippets,\nopen questions, and an optional top visual review area (wireframe canvas, live\nprototype, or both in tabs). Architecture and backend plans stay document-only;\nUI and product plans start with the top canvas/prototype (the Visual Surface\nChoice section owns that rule).\n\n`/visual-plan` is the packaged command and main entry point. Choose the review\nmode from the task: UI-first when the work is primarily product UI and review\nshould start with screens, prototype-first when review should start with a\nfunctional live prototype, design-first when review needs full-fidelity branded\nscreens, or visual-intake when the user explicitly wants a questionnaire before\nplanning. When a Codex, Claude Code, Markdown, or pasted plan already exists,\n`/visual-plan` uses that source plan as the starting point and builds the review\nsurface from it instead of starting over.\n\n## When To Use\n\nCreate or adapt a visual plan whenever the plan would be better as a reviewable\nartifact than a chat paragraph. This includes modest work such as a single UI\nsurface with states, a small workflow, a before/after product change, or a\ncomponent/API/data-shape decision that needs alignment, plus larger multi-file,\nambiguous, long-running, risky, or UI-heavy work. Use it when architecture /\ndata flow / UI direction / options / open questions would benefit from inline\ndiagrams or structured blocks, when the user needs to react to a direction\nbefore you implement, or when an existing text plan needs a richer review\nsurface.\n\n## Plan Discipline\n\n- **Gate thoughtfully.** A visual plan is a richer review surface, not only a\n  tool for giant projects. Use it when the user needs to see, compare, comment\n  on, or approve a direction before code, even for a modest UI/state/workflow\n  change. Skip it for truly trivial, unambiguous work \u2014 typos, one-line fixes, a\n  single well-specified function, anything whose diff you could describe in one\n  sentence \u2014 and just make the change. Never pad a plan with filler and never\n  ship a single-step plan.\n- **Research before you draft.** Read the real files, actions, schema, and\n  patterns first; name actual files, symbols, and data shapes instead of\n  inventing them. Check existing `actions/` before proposing endpoints and prefer\n  named client helpers over raw fetch. Delegate wide exploration to a sub-agent.\n  Lead with reuse: for each step, name what it reuses \u2014 existing actions, schema,\n  components, helpers \u2014 before what it adds, so the plan explains the genuinely new\n  delta instead of redescribing what already exists.\n- **Decide the hard-to-reverse bets first.** For non-trivial backend, data, or API\n  work, sketch where the feature is headed, then call out the decisions that are\n  expensive to undo once data or callers depend on them \u2014 wire format, public ids,\n  data-model shape, auth and ownership boundaries \u2014 and get those right in the plan\n  even if most of the feature ships later. Then scope to the smallest first cut that\n  proves the approach without foreclosing it, stating both what is in and what is\n  explicitly deferred.\n- **Keep examples at the right altitude.** When the user's idea is a broad\n  framework, product, or operating-model change, do not collapse it into the\n  first concrete example, provider, or sync path they mention. Separate the core\n  abstraction from motivating examples and app/provider adapters. Use examples\n  to make the plan legible, but label them as examples unless they are the whole\n  requested scope.\n- **Publish standalone plans.** If the user pasted, referenced, or already has a\n  Codex / Claude Code / Markdown plan, treat it as source material, but rewrite\n  the published plan as a clean standalone proposal. Preserve the source plan's\n  useful intent and codebase facts, label inferred visuals as inferred, and avoid\n  revision language such as \"preserve the prior plan\", \"do not drop the old\n  idea\", \"unlike the previous version\", or \"this revision changes...\". A reader\n  who never saw the chat or earlier drafts should understand the plan.\n- **Make the first read concrete.** If the plan is meant to be shared with\n  someone outside the chat, or if the concept is abstract, lead near the top with\n  one concrete product example before mode tables, architecture, or roadmaps. For\n  UI-capable concepts, that usually means a top-canvas app state that shows the\n  real user workflow in product terms. Do not rely on phrases that only make\n  sense in conversation, and do not frame the plan as \"not the old idea\"; state\n  the positive model directly.\n- **Planning is read-only.** Make no source edits while building or reviewing the\n  plan. Start editing only after the user approves the direction.\n- **Clarify vs. assume.** Do not ask how to build it \u2014 explore and present the\n  approach and options in the plan. Ask a clarifying question only when an\n  ambiguity would change the design and you cannot resolve it from the code; use\n  the host agent's normal ask-user-question flow and batch 2-4 high-leverage\n  questions before finalizing. Do not call `create-visual-questions` for\n  ordinary clarification or preflight; reserve it for the visual-intake mode when\n  the user explicitly asks for a visual intake questionnaire. Otherwise state the\n  assumption explicitly and proceed, and keep anything unresolved in the plan's\n  single bottom `question-form` Open Questions block. For complex plans, do a\n  final open-question pass before handoff: if a decision would affect\n  architecture, scope, UX, data shape, or rollout, either decide it in the plan\n  with rationale or put it in that bottom form with a recommended default.\n- **The plan is the approval gate.** After surfacing it, ask the user to review\n  and approve before you write code, and name which files/areas the work touches.\n  Presenting the plan and requesting sign-off is the approval step \u2014 do not ask a\n  separate \"does this look good?\" question.\n- **The document is the source of truth, not the chat.** When scope shifts,\n  update the plan with `update-visual-plan` rather than only changing course in\n  chat, and make the updated document stand alone. Do not describe the update as\n  a correction to an earlier draft inside the plan itself. Re-read the approved\n  plan before major steps.\n\n## Create A Structured Agent-Native Plan \u2014 Never Inline\n\nThe deliverable is ALWAYS a structured Agent-Native Plan, not a chat-only plan.\nThe hosted Plan MCP connector (`plan` server, or legacy `agent-native-plans`) is\nthe default collaboration and commenting surface; it is not a reason to reject\nthe planning pattern as an external dependency or rented layer. Plans are\nportable source artifacts (`plan.mdx`, optional `canvas.mdx` /\n`prototype.mdx`, JSON, and HTML export), and ownership-sensitive workflows can\nuse local-files mode or a self-hosted/custom Plan app URL without abandoning the\nskill's review discipline. Do not advise the user to skip `/visual-plan` because\nthe default surface is hosted; choose the right Plan mode for the user's\nownership, privacy, sharing, and branding needs.\n\nBy default, create the plan via the Plan MCP connector and NEVER hand it over as\ninline chat content \u2014 no Markdown prose, ASCII sketch, table, or fenced\nwireframe. If the `plan` (or legacy `agent-native-plans`) tools are not visible,\ndiscover them through the host's `tool_search` first; if they are still missing,\nSTOP and give the user the client-specific reconnect step rather than improvising\nan inline plan. Before publishing, or whenever a connector or auth error appears,\nREAD `references/connection.md` in this skill directory \u2014 it is the single source\nof truth for the never-inline rule, connector discovery, and the per-client\nreconnect steps. Local-files privacy mode (after Tool Guidance) is the exception.\n\n## Core Workflow\n\nThis section describes the default hosted Plan MCP workflow. If\n`AGENT_NATIVE_PLANS_MODE=local-files` is set, or the user asks for fully local\nfiles/no hosted Plan writes, use **Local-Files Privacy Mode** instead; carry\nforward only the code-research and plan-composition guidance here.\n\n1. Follow the host agent's normal planning flow: inspect the codebase, delegate\n   wide exploration when useful, gather the info needed, and ask native\n   clarifying questions as needed before generating the plan. If a source plan\n   already exists, gather its exact text from the user's paste, a referenced\n   file, or recent visible agent context; do not invent source text.\n2. Call `get-plan-blocks` for the authoritative block catalog \u2014 do not author\n   from memorized tags. Then call the mode-matched create tool:\n   `create-visual-plan` for document-first plans (architecture, backend, data,\n   refactor, API), `create-ui-plan` for UI-first plans, `create-prototype-plan`\n   for prototype-first plans, `create-plan-design` for design-first plans,\n   `create-visual-questions` only when the user explicitly asks for a visual\n   intake questionnaire. When a source plan already exists,\n   pass it as `planText` and preserve the original plan's useful intent while\n   producing a standalone plan document, not a revision memo.\n3. For UI/product plans, compose the top canvas first with the primary\n   wireframes and annotated states, then write the document with native blocks\n   (see `references/canvas.md` and `references/document-quality.md`). For\n   broad product architecture plans with a user-facing implication, add a\n   concrete \"what this looks like in the app\" visual before the abstract\n   architecture or mode tables. Keep the document close to the standalone\n   Markdown plan the agent would normally output. If an existing plan was\n   provided, carry forward the right facts and decisions without referring to\n   the previous draft or explaining how this version differs. For non-visual\n   plans, skip the top visual surface (Visual Surface Choice below owns the rule)\n   and put `diagram`, `data-model`,\n   `api-endpoint`, `diff`, `file-tree`, `code`, and `annotated-code` blocks\n   directly next to the relevant prose.\n   Wide document layout is renderer-owned and intentionally allowlisted: only\n   literal code-review surfaces (`diff`, `annotated-code`) and `tabs` blocks\n   with vertical orientation or diff-like children break out wider than prose.\n   Keep `api-endpoint`, `openapi-spec`, `data-model`, `json-explorer`,\n   `wireframe`, question, and `custom-html` blocks in normal document flow unless\n   their own renderer says otherwise.\n4. Surface the returned Plans link or inline MCP App and ask the user to review.\n   Always include the actual URL in chat so the next step is a click in CLI or\n   other text-only hosts. When the host exposes an embedded browser/preview panel\n   and a tool can open arbitrary URLs there, open the returned plan URL\n   automatically for convenient review \u2014 a convenience and smoke test, never the\n   only handoff or the access\n   model. Plans should load out of the box for the local agent and local browser\n   session; if a signed-in embedded browser cannot read a local plan that an\n   anonymous/tool check can read, fix the app/action ownership or access path\n   rather than patching one plan by hand. For high-stakes plans (architecture,\n   backend, data, multi-file, or risky), also kick off the self-review pass in\n   **Self-Review Before Handoff** while the user reads, instead of blocking the\n   handoff on it.\n5. For hosted plans, call `get-plan-feedback` before editing, after review,\n   after any long pause,\n   and before the final response. Treat `anchorDetails`, resolver intent, recent\n   review events, and any focused screenshots from browser handoff as the source\n   of truth for exactly what changed and exactly what each comment points at.\n6. For hosted plans, apply changes with `update-visual-plan`, preferring\n   targeted `contentPatches`.\n   Treat the top-level `content` payload as a full replacement, not a merge; do\n   not send a partial `content` object to add a canvas or one block. If a full\n   replacement is unavoidable, first read the complete plan source/content, carry\n   forward every existing block and visual surface, and verify the source/export\n   afterward so the document body was not truncated. When the user wants\n   source-control friendly edits, use `patch-visual-plan-source` against the MDX\n   files instead of regenerating the plan.\n7. For hosted plans, export with `export-visual-plan` only when the user wants a\n   shareable receipt or repo-check-in artifacts.\n\n## Self-Review Before Handoff\n\nFor high-stakes plans \u2014 architecture, backend, data-model, migration, multi-file,\nor otherwise risky work \u2014 run one adversarial self-review pass before treating the\nplan as final. Skip it for small, UI-only, or single-decision plans where the cost\noutweighs the value. Keep the pass cheap and non-blocking:\n\n- **Surface the plan first, review concurrently.** Post the link and let the user\n  start reading, then run the review in parallel \u2014 never make the user wait on it.\n- **Review the written plan; do not re-research.** Critique the plan text and its\n  own blocks. The grounding was already done while drafting, so the review checks\n  the output instead of re-exploring the repo.\n- **Spawn one skeptical reviewer** whose only job is to find what is weak, missing,\n  or wrong \u2014 not to praise. Point it at: hard-to-reverse decisions made implicitly\n  or not at all (wire format, public ids, data-model shape, auth, ownership); steps\n  not anchored in real files or symbols; a menu of options where the plan should\n  commit to one; obvious missing decisions (\"what happens when X?\", \"why not Y?\");\n  and padding or single-step filler.\n- **Fix vs. ask.** Apply clear-cut fixes yourself with `update-visual-plan`\n  `contentPatches` \u2014 vague non-goals, unanchored claims, an obvious missing\n  decision. Route genuine judgment calls back to the user instead: add them to the\n  bottom `question-form` Open Questions block or batch them into the normal\n  ask-user-question flow. Do not silently decide them.\n- **Do not surprise the user mid-read.** On a large plan, apply the patches before\n  the editor loads; otherwise note briefly that a self-review is running so the\n  plan changing under them is expected. When you next respond, summarize what the\n  review changed and what it surfaced for the user to decide.\n\n## Visual Surface Choice\n\nChoose the surface before creating the plan or after reading the source plan. Do\nnot add visual chrome by default:\n\nFor UI/product plans, the top canvas is usually the primary review surface. Put\nthe first meaningful wireframes there, not buried as document-body blocks. Use\nmultiple canvas artboards when states matter, such as the default view, an\noverflow menu or popover, a side panel, loading, or error. Put short annotations\nbeside frames with `targetId` plus `placement`; keep implementation details,\ntradeoffs, file maps, data contracts, risks, and verification in the document\nbody below the canvas.\n\nWhen the user asks for a flow, storyboard, journey, wireframe, canvas, or \"what\nthis looks like\", treat that as a canvas-first request. Make one artboard per\nuser-visible state, connect only adjacent transitions, and use short canvas\nannotations for the product notes. Do not substitute a document-body `diagram`\nblock for the requested storyboard just because HTML diagrams are faster to\nwrite; diagrams belong below the canvas for backend mechanics, architecture, or\ndata-flow explanation.\n\nKeep product wireframes and explanatory/meta diagrams separate. Start with pure\nscreens that look like the app state under discussion, without callout prose or\narchitecture notes embedded inside the UI. Put arrows, labels, contracts, data\nflow, and mode explanations in separate annotations, separate canvas diagrams,\nor the document body.\n\nWhen the plan touches an existing app, inspect the current shell/components\nbefore drawing. The first artboard should look like the real app at the same\ndensity: existing sidebars, toolbar placement, overflow menus, app chrome, and\nframework agent chrome stay in their real places. Model secondary surfaces as\nseparate states, such as a top-right overflow popover, sheet, panel, loading\nstate, or separate AgentSidebar, rather than inventing a permanent inspector or\nfolding framework chrome into the product UI.\n\n- **No visual surface** for architecture-only, backend-only, data migration,\n  copy-only, or otherwise non-visual plans. Do not use the top canvas for\n  architecture diagrams, dependency maps, file plans, API contracts, or\n  data-flow-only reviews. Use a strong document with local inline diagrams\n  only when relationships need a visual explanation, usually one spatial diagram\n  per recommendation or decision. Prefer grouped regions, layers, quadrants,\n  matrices, or before/after panels over a single-axis chain unless the\n  relationship is truly sequential.\n- **Canvas only** for one static screen, a before/after comparison, a component\n  state, a small popover, or a visual direction that does not require clicking.\n  Put those wireframes in `content.canvas` and omit `content.prototype`.\n- **Canvas + prototype** for multi-step UI flows, onboarding, wizards,\n  review/approval flows, navigation changes, or anything where the reviewer\n  needs to operate the behavior. Keep the static wireframes in\n  `content.canvas`, add the aligned functional prototype in\n  `content.prototype`, and rely on the top visual tabs to switch between them.\n- **Prototype-first** when the user asks to operate the UI or when interaction is\n  the main question. Use `create-prototype-plan`, which still preserves static\n  mocks where useful.\n\nFor mixed canvas + prototype plans, reuse the same real labels, app statuses,\nand screen ids across both surfaces. The canvas is the inspectable static reference;\nthe prototype is the interactive version of that same flow, not a separate\ndesign direction.\n\n## Wireframe quality \u2014 read `references/wireframe.md`\n\nUI recap/plan wireframes must meet a strict quality bar \u2014 full-width chrome,\npinned bottom bars, real product content, before/after comparability, the right\n`surface` preset, `--wf-*` tokens instead of hex, and no `<html>`/`<style>`/font\ntags. Before authoring ANY wireframe / `<Screen>` / `WireframeBlock`, READ\n`references/wireframe.md` in this skill directory \u2014 it is the single source of\ntruth for HTML wireframe quality, shared word for word with `/visual-plan`\nand `/visual-recap`. Do not author wireframes from memory.\n\n## Canvas \u2014 read `references/canvas.md`\n\nThe canvas is the single source of truth for static UI mockups: the `surface`\nlocks each artboard's footprint, mixed surfaces lay out\nin lanes, annotations are plain-text designer notes anchored by\n`targetId`/`placement`, and edits are surgical `contentPatches`. Before\nauthoring or editing ANY canvas, artboard, or annotation, READ\n`references/canvas.md` in this skill directory \u2014 it is the single source of truth\nfor canvas/artboard mechanics. Do not author canvas layouts from memory.\nCanvas artboards use the same HTML wireframe path as document-body\n`WireframeBlock` screens: author `<Screen surface=\"...\" html={...} />` with a\nsemantic HTML fragment. Do not author fresh kit-tree children such as\n`<FrameScreen>`, `<Card>`, `<Row>`, or `<Btn>` inside canvas `<Screen>` tags;\nthose are legacy compatibility markup for old plans and produce brittle canvas\nlayouts.\n\n## Document quality \u2014 read `references/document-quality.md`\n\nThe document is a serious technical plan, not marketing: outcome-first,\nprose-first, self-contained, built from the right native blocks, with open\nquestions in a single bottom `question-form` and a pre-handoff visual check.\nBefore authoring the plan document, READ `references/document-quality.md` in this\nskill directory \u2014 it is the single source of truth for the document quality bar.\nDo not write the document from memory.\n\n## Good vs. bad exemplar \u2014 read `references/exemplar.md`\n\nFor a worked example of the bar \u2014 a great UI-first plan and `/visual-plan`, plus\nthe anti-patterns to avoid \u2014 READ `references/exemplar.md` in this skill\ndirectory before authoring a plan.\n\n## Tool Guidance\n\n- `create-visual-plan`: start one structured visual plan per agent task/run, or\n  import an existing text plan by passing `planText`; `content` may include no\n  visual surface, canvas only, or canvas + prototype.\n- `create-ui-plan`: start a UI-first plan when the work is primarily product UI.\n- `create-prototype-plan`: start a prototype-first plan with a functional top\n  review surface.\n- `create-plan-design`: start a full-fidelity branded Design-tab plan with an\n  optional matching Prototype tab.\n- `convert-visual-plan-to-prototype`: convert an existing HTML wireframe canvas\n  into a prototype plan.\n- `create-visual-questions`: use only when the user explicitly asks for a visual\n  intake questionnaire, not as `/visual-plan` preflight.\n- `update-visual-plan`: revise content, status, or comments with targeted\n  `contentPatches` (see Core Workflow step 6).\n- `read-visual-plan-source`: read the normalized plan as `plan.mdx`,\n  optional `canvas.mdx`, optional `.plan-state.json`, and JSON.\n- `patch-visual-plan-source`: apply granular MDX AST patches by stable block,\n  artboard, annotation, component, or wireframe-node id.\n- `import-visual-plan-source`: create or replace a plan from an MDX folder.\n- `get-visual-plan`: read the current structured plan, exported HTML, and\n  annotations; it also returns the MDX folder for source workflows.\n- `get-plan-feedback`: read unconsumed human feedback. Use it frequently; it\n  returns grouped threads, exact anchor details, expected resolver, and recent\n  review-event payloads so agents can act only on the comments meant for them.\n- `get-plan-blocks`: resolve block tags before authoring \u2014 do not memorize tags;\n  call this first to get the authoritative tag names, required fields, and prop\n  shapes from the live block registry.\n- `export-visual-plan`: export HTML, Markdown fallback, structured JSON, and MDX\n  files for repo check-in.\n\nWhen the user critiques a plan's look or structure, fix the renderer or this\nskill \u2014 never hand-edit one stored plan. Turn feedback into better guidance.\n\n## Local-Files Privacy Mode \u2014 read `references/local-files.md`\n\nWhen the user wants no hosted Plan database writes \u2014 no DB writes, no Plan MCP\npublish, fully local/offline/private planning, repo-owned source-controlled\nartifacts, or `AGENT_NATIVE_PLANS_MODE=local-files` \u2014 do not call any hosted Plan\ntool except the schema-only `get-plan-blocks` catalog lookup. Author a local MDX\nfolder and\npreview it with `plan local check` / `plan local serve` / `plan local verify`.\nBefore using local-files mode, READ `references/local-files.md` in this skill\ndirectory \u2014 it is the single source of truth for the full contract (catalog\nlookup, MDX folder layout, the local bridge commands, and the hosted tools you\nmust not call). Carry forward only the code-research and plan-composition\nguidance from Core Workflow; everything hosted is replaced by the local bridge.\n\n## Interpreting comment anchors\n\nThis section applies to hosted plans with `get-plan-feedback` /\n`update-visual-plan`. In local-files mode, do not call hosted feedback or update\ntools; interpret file/chat feedback directly, edit the MDX files, rerun the\nlocal bridge check/serve/verify command, and report the new local URL.\n\n`get-plan-feedback` returns rich anchors \u2014 read them before acting on any comment.\n\n- **Coordinate frames.** `targetX`/`targetY` are percentages *within* the\n  element named by `targetSelector`/`targetKind`. Bare `x`/`y` are percentages\n  of the whole plan document. `canvasX`/`canvasY` are raw board-world pixels on\n  the design canvas (board size given when available).\n- **Wireframe pins.** Anchors on wireframes include `targetNodeId` and\n  `targetNodePath` (e.g. `card > list > listItem \"Acme Inc\"`) identifying the\n  exact kit node. Use `targetNodeId` directly with wireframe node patch ops;\n  use `data-design-id` values from design artboards with\n  `update-design-element-style`. Prefer the node id/path over raw coordinates;\n  fall back to coordinates plus the focused screenshot (red ring marks the exact\n  point) only when no node id is present.\n- **Text quotes.** Resolve `textQuote` against current prose using\n  `contextBefore`/`contextAfter` for disambiguation. If `ambiguous: true`, ask\n  the user \u2014 do not guess which occurrence is meant.\n- **Detached comments.** `get-plan-feedback` flags threads whose quoted text no\n  longer exists as `detached` (in `detachedThreads`). Reconcile these against\n  rewritten content \u2014 never silently drop them.\n- **Routing.** `resolutionTarget` is the only routing signal: act on `agent`,\n  treat `human` as context only. `@mentions` are people to notify, never a\n  routing signal.\n- **Two-axis state.** Mark every ingested comment as consumed\n  (`consumedCommentIds` on `update-visual-plan`). Set `status=resolved` only on\n  agent-targeted comments you actually addressed; leave human-targeted comments\n  open.\n\n## Visibility & Sharing\n\nUse `set-resource-visibility` to change who can see a plan (e.g. public, login,\nor org-scoped). Use `share-resource` to grant specific users or roles access\nby email or role. Gate visibility before sharing any plan that covers\nunreleased or private work \u2014 default to the narrowest scope that meets the\nreview need.\n\n## Setup & Authentication\n\nThere are two ways into Plans.\n\n**Coding agent (CLI).** Install once with the Agent-Native CLI. The command\ninstalls the Plans skills, registers the hosted Plans MCP connector, and runs\nauth/setup for the selected local client(s) in the same step (a one-time browser\nsign-in at setup \u2014 this is intended), so the first tool call in that client does\nnot hit an OAuth wall:\n\n```bash\nnpx @agent-native/core@latest skills add visual-plans\n```\n\nAfter that, `/visual-plan`, `/visual-recap`, and `/visualize-repo` are the\ninstalled slash commands. If you only need one command, use\n`skills add visual-plan`, `skills add visual-recap`, or\n`skills add visualize-repo` instead. The other planning modes\n(`create-ui-plan`, `create-prototype-plan`, `create-plan-design`,\n`create-visual-questions`) are MCP tools reachable from `/visual-plan`, not\nseparate slash commands. Pass `--no-connect` to register the connector without\nauthenticating, then run\n`npx @agent-native/core@latest connect https://plan.agent-native.com --client all`\nwhenever you are ready, or choose a narrower `--client`. Auth and MCP tool\nloading are per client config/session.\n\n**Browser (people you share with).** Open the Plans editor and create & edit\nwith no sign-up \u2014 you work as a guest. Sign in only when you want to save or\nshare; signing in claims the plans you made as a guest into your account.\n\nSharing and commenting require an account: public/shared plans are viewable by\nanyone with the link, but commenting on them needs an agent-native account.\n\nFor fully offline, no-account use, run the Plans app locally and sync plans to\nyour repo as MDX. This local mode is a separate advanced path, not the default\nhosted flow.\n\nFor repo-wide visual docs, run\n`npx @agent-native/core@latest visualize-repo --open` to create/update\n`agent-native.json`, seed `.agent-native/visual-docs/repo-overview`, and open\nthe local bridge.\n\nIf a Plans tool returns `needs auth`, `Unauthorized`, or `Session terminated`, do\nnot keep retrying it \u2014 stop and give the user the per-client reconnect step from\n`references/connection.md`, then continue once the connector is available.\n\nHosted default: connect `https://plan.agent-native.com/mcp`. Do\nnot put shared secrets in skill files.\n";
 //# sourceMappingURL=visual-plan-skill.d.ts.map

package/dist/cli/skills-content/visual-plan-skill.d.ts.map CHANGED Viewed

	@@ -1 +1 @@
1	- {"version":3,"file":"visual-plan-skill.d.ts","sourceRoot":"","sources":["../../../src/cli/skills-content/visual-plan-skill.ts"],"names":[],"mappings":"AAAA,eAAO,MAAM,qBAAqB,~~6o4BAqdjC,~~CAAC"}
1	+ {"version":3,"file":"visual-plan-skill.d.ts","sourceRoot":"","sources":["../../../src/cli/skills-content/visual-plan-skill.ts"],"names":[],"mappings":"AAAA,eAAO,MAAM,qBAAqB,+n4BAqdjC,CAAC"}

package/dist/cli/skills-content/visual-plan-skill.js CHANGED Viewed

@@ -465,7 +465,7 @@ If a Plans tool returns \`needs auth\`, \`Unauthorized\`, or \`Session terminate
 not keep retrying it — stop and give the user the per-client reconnect step from
 \`references/connection.md\`, then continue once the connector is available.
-Hosted default: connect \`https://plan.agent-native.com/_agent-native/mcp\`. Do
+Hosted default: connect \`https://plan.agent-native.com/mcp\`. Do
 not put shared secrets in skill files.
 `;
 //# sourceMappingURL=visual-plan-skill.js.map

package/dist/cli/skills-content/visual-plan-skill.js.map CHANGED Viewed

	@@ -1 +1 @@
1	- {"version":3,"file":"visual-plan-skill.js","sourceRoot":"","sources":["../../../src/cli/skills-content/visual-plan-skill.ts"],"names":[],"mappings":"AAAA,MAAM,CAAC,MAAM,qBAAqB,GAAG;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CAqdpC,CAAC","sourcesContent":["export const VISUAL_PLANS_SKILL_MD = `---\nname: visual-plan\ndescription: >-\n Turn ordinary text plans into rich interactive visual plans with diagrams,\n file maps, annotated code, open questions, and UI/prototype review when\n useful.\nmetadata:\n visibility: exported\n---\n\n# Agent-Native Plans\n\nAgent-Native Plans is structured visual planning mode for coding agents. Build\nthe plan you would normally write in Markdown, but as a scannable document with\neditable blocks mixed in: inline diagrams, code snippets,\nopen questions, and an optional top visual review area (wireframe canvas, live\nprototype, or both in tabs). Architecture and backend plans stay document-only;\nUI and product plans start with the top canvas/prototype (the Visual Surface\nChoice section owns that rule).\n\n\\`/visual-plan\\` is the packaged command and main entry point. Choose the review\nmode from the task: UI-first when the work is primarily product UI and review\nshould start with screens, prototype-first when review should start with a\nfunctional live prototype, design-first when review needs full-fidelity branded\nscreens, or visual-intake when the user explicitly wants a questionnaire before\nplanning. When a Codex, Claude Code, Markdown, or pasted plan already exists,\n\\`/visual-plan\\` uses that source plan as the starting point and builds the review\nsurface from it instead of starting over.\n\n## When To Use\n\nCreate or adapt a visual plan whenever the plan would be better as a reviewable\nartifact than a chat paragraph. This includes modest work such as a single UI\nsurface with states, a small workflow, a before/after product change, or a\ncomponent/API/data-shape decision that needs alignment, plus larger multi-file,\nambiguous, long-running, risky, or UI-heavy work. Use it when architecture /\ndata flow / UI direction / options / open questions would benefit from inline\ndiagrams or structured blocks, when the user needs to react to a direction\nbefore you implement, or when an existing text plan needs a richer review\nsurface.\n\n## Plan Discipline\n\n- Gate thoughtfully. A visual plan is a richer review surface, not only a\n tool for giant projects. Use it when the user needs to see, compare, comment\n on, or approve a direction before code, even for a modest UI/state/workflow\n change. Skip it for truly trivial, unambiguous work — typos, one-line fixes, a\n single well-specified function, anything whose diff you could describe in one\n sentence — and just make the change. Never pad a plan with filler and never\n ship a single-step plan.\n- Research before you draft. Read the real files, actions, schema, and\n patterns first; name actual files, symbols, and data shapes instead of\n inventing them. Check existing \\`actions/\\` before proposing endpoints and prefer\n named client helpers over raw fetch. Delegate wide exploration to a sub-agent.\n Lead with reuse: for each step, name what it reuses — existing actions, schema,\n components, helpers — before what it adds, so the plan explains the genuinely new\n delta instead of redescribing what already exists.\n- Decide the hard-to-reverse bets first. For non-trivial backend, data, or API\n work, sketch where the feature is headed, then call out the decisions that are\n expensive to undo once data or callers depend on them — wire format, public ids,\n data-model shape, auth and ownership boundaries — and get those right in the plan\n even if most of the feature ships later. Then scope to the smallest first cut that\n proves the approach without foreclosing it, stating both what is in and what is\n explicitly deferred.\n- Keep examples at the right altitude. When the user's idea is a broad\n framework, product, or operating-model change, do not collapse it into the\n first concrete example, provider, or sync path they mention. Separate the core\n abstraction from motivating examples and app/provider adapters. Use examples\n to make the plan legible, but label them as examples unless they are the whole\n requested scope.\n- Publish standalone plans. If the user pasted, referenced, or already has a\n Codex / Claude Code / Markdown plan, treat it as source material, but rewrite\n the published plan as a clean standalone proposal. Preserve the source plan's\n useful intent and codebase facts, label inferred visuals as inferred, and avoid\n revision language such as \"preserve the prior plan\", \"do not drop the old\n idea\", \"unlike the previous version\", or \"this revision changes...\". A reader\n who never saw the chat or earlier drafts should understand the plan.\n- Make the first read concrete. If the plan is meant to be shared with\n someone outside the chat, or if the concept is abstract, lead near the top with\n one concrete product example before mode tables, architecture, or roadmaps. For\n UI-capable concepts, that usually means a top-canvas app state that shows the\n real user workflow in product terms. Do not rely on phrases that only make\n sense in conversation, and do not frame the plan as \"not the old idea\"; state\n the positive model directly.\n- Planning is read-only. Make no source edits while building or reviewing the\n plan. Start editing only after the user approves the direction.\n- Clarify vs. assume. Do not ask how to build it — explore and present the\n approach and options in the plan. Ask a clarifying question only when an\n ambiguity would change the design and you cannot resolve it from the code; use\n the host agent's normal ask-user-question flow and batch 2-4 high-leverage\n questions before finalizing. Do not call \\`create-visual-questions\\` for\n ordinary clarification or preflight; reserve it for the visual-intake mode when\n the user explicitly asks for a visual intake questionnaire. Otherwise state the\n assumption explicitly and proceed, and keep anything unresolved in the plan's\n single bottom \\`question-form\\` Open Questions block. For complex plans, do a\n final open-question pass before handoff: if a decision would affect\n architecture, scope, UX, data shape, or rollout, either decide it in the plan\n with rationale or put it in that bottom form with a recommended default.\n- The plan is the approval gate. After surfacing it, ask the user to review\n and approve before you write code, and name which files/areas the work touches.\n Presenting the plan and requesting sign-off is the approval step — do not ask a\n separate \"does this look good?\" question.\n- The document is the source of truth, not the chat. When scope shifts,\n update the plan with \\`update-visual-plan\\` rather than only changing course in\n chat, and make the updated document stand alone. Do not describe the update as\n a correction to an earlier draft inside the plan itself. Re-read the approved\n plan before major steps.\n\n## Create A Structured Agent-Native Plan — Never Inline\n\nThe deliverable is ALWAYS a structured Agent-Native Plan, not a chat-only plan.\nThe hosted Plan MCP connector (\\`plan\\` server, or legacy \\`agent-native-plans\\`) is\nthe default collaboration and commenting surface; it is not a reason to reject\nthe planning pattern as an external dependency or rented layer. Plans are\nportable source artifacts (\\`plan.mdx\\`, optional \\`canvas.mdx\\` /\n\\`prototype.mdx\\`, JSON, and HTML export), and ownership-sensitive workflows can\nuse local-files mode or a self-hosted/custom Plan app URL without abandoning the\nskill's review discipline. Do not advise the user to skip \\`/visual-plan\\` because\nthe default surface is hosted; choose the right Plan mode for the user's\nownership, privacy, sharing, and branding needs.\n\nBy default, create the plan via the Plan MCP connector and NEVER hand it over as\ninline chat content — no Markdown prose, ASCII sketch, table, or fenced\nwireframe. If the \\`plan\\` (or legacy \\`agent-native-plans\\`) tools are not visible,\ndiscover them through the host's \\`tool_search\\` first; if they are still missing,\nSTOP and give the user the client-specific reconnect step rather than improvising\nan inline plan. Before publishing, or whenever a connector or auth error appears,\nREAD \\`references/connection.md\\` in this skill directory — it is the single source\nof truth for the never-inline rule, connector discovery, and the per-client\nreconnect steps. Local-files privacy mode (after Tool Guidance) is the exception.\n\n## Core Workflow\n\nThis section describes the default hosted Plan MCP workflow. If\n\\`AGENT_NATIVE_PLANS_MODE=local-files\\` is set, or the user asks for fully local\nfiles/no hosted Plan writes, use Local-Files Privacy Mode instead; carry\nforward only the code-research and plan-composition guidance here.\n\n1. Follow the host agent's normal planning flow: inspect the codebase, delegate\n wide exploration when useful, gather the info needed, and ask native\n clarifying questions as needed before generating the plan. If a source plan\n already exists, gather its exact text from the user's paste, a referenced\n file, or recent visible agent context; do not invent source text.\n2. Call \\`get-plan-blocks\\` for the authoritative block catalog — do not author\n from memorized tags. Then call the mode-matched create tool:\n \\`create-visual-plan\\` for document-first plans (architecture, backend, data,\n refactor, API), \\`create-ui-plan\\` for UI-first plans, \\`create-prototype-plan\\`\n for prototype-first plans, \\`create-plan-design\\` for design-first plans,\n \\`create-visual-questions\\` only when the user explicitly asks for a visual\n intake questionnaire. When a source plan already exists,\n pass it as \\`planText\\` and preserve the original plan's useful intent while\n producing a standalone plan document, not a revision memo.\n3. For UI/product plans, compose the top canvas first with the primary\n wireframes and annotated states, then write the document with native blocks\n (see \\`references/canvas.md\\` and \\`references/document-quality.md\\`). For\n broad product architecture plans with a user-facing implication, add a\n concrete \"what this looks like in the app\" visual before the abstract\n architecture or mode tables. Keep the document close to the standalone\n Markdown plan the agent would normally output. If an existing plan was\n provided, carry forward the right facts and decisions without referring to\n the previous draft or explaining how this version differs. For non-visual\n plans, skip the top visual surface (Visual Surface Choice below owns the rule)\n and put \\`diagram\\`, \\`data-model\\`,\n \\`api-endpoint\\`, \\`diff\\`, \\`file-tree\\`, \\`code\\`, and \\`annotated-code\\` blocks\n directly next to the relevant prose.\n Wide document layout is renderer-owned and intentionally allowlisted: only\n literal code-review surfaces (\\`diff\\`, \\`annotated-code\\`) and \\`tabs\\` blocks\n with vertical orientation or diff-like children break out wider than prose.\n Keep \\`api-endpoint\\`, \\`openapi-spec\\`, \\`data-model\\`, \\`json-explorer\\`,\n \\`wireframe\\`, question, and \\`custom-html\\` blocks in normal document flow unless\n their own renderer says otherwise.\n4. Surface the returned Plans link or inline MCP App and ask the user to review.\n Always include the actual URL in chat so the next step is a click in CLI or\n other text-only hosts. When the host exposes an embedded browser/preview panel\n and a tool can open arbitrary URLs there, open the returned plan URL\n automatically for convenient review — a convenience and smoke test, never the\n only handoff or the access\n model. Plans should load out of the box for the local agent and local browser\n session; if a signed-in embedded browser cannot read a local plan that an\n anonymous/tool check can read, fix the app/action ownership or access path\n rather than patching one plan by hand. For high-stakes plans (architecture,\n backend, data, multi-file, or risky), also kick off the self-review pass in\n Self-Review Before Handoff while the user reads, instead of blocking the\n handoff on it.\n5. For hosted plans, call \\`get-plan-feedback\\` before editing, after review,\n after any long pause,\n and before the final response. Treat \\`anchorDetails\\`, resolver intent, recent\n review events, and any focused screenshots from browser handoff as the source\n of truth for exactly what changed and exactly what each comment points at.\n6. For hosted plans, apply changes with \\`update-visual-plan\\`, preferring\n targeted \\`contentPatches\\`.\n Treat the top-level \\`content\\` payload as a full replacement, not a merge; do\n not send a partial \\`content\\` object to add a canvas or one block. If a full\n replacement is unavoidable, first read the complete plan source/content, carry\n forward every existing block and visual surface, and verify the source/export\n afterward so the document body was not truncated. When the user wants\n source-control friendly edits, use \\`patch-visual-plan-source\\` against the MDX\n files instead of regenerating the plan.\n7. For hosted plans, export with \\`export-visual-plan\\` only when the user wants a\n shareable receipt or repo-check-in artifacts.\n\n## Self-Review Before Handoff\n\nFor high-stakes plans — architecture, backend, data-model, migration, multi-file,\nor otherwise risky work — run one adversarial self-review pass before treating the\nplan as final. Skip it for small, UI-only, or single-decision plans where the cost\noutweighs the value. Keep the pass cheap and non-blocking:\n\n- Surface the plan first, review concurrently. Post the link and let the user\n start reading, then run the review in parallel — never make the user wait on it.\n- Review the written plan; do not re-research. Critique the plan text and its\n own blocks. The grounding was already done while drafting, so the review checks\n the output instead of re-exploring the repo.\n- Spawn one skeptical reviewer whose only job is to find what is weak, missing,\n or wrong — not to praise. Point it at: hard-to-reverse decisions made implicitly\n or not at all (wire format, public ids, data-model shape, auth, ownership); steps\n not anchored in real files or symbols; a menu of options where the plan should\n commit to one; obvious missing decisions (\"what happens when X?\", \"why not Y?\");\n and padding or single-step filler.\n- Fix vs. ask. Apply clear-cut fixes yourself with \\`update-visual-plan\\`\n \\`contentPatches\\` — vague non-goals, unanchored claims, an obvious missing\n decision. Route genuine judgment calls back to the user instead: add them to the\n bottom \\`question-form\\` Open Questions block or batch them into the normal\n ask-user-question flow. Do not silently decide them.\n- Do not surprise the user mid-read. On a large plan, apply the patches before\n the editor loads; otherwise note briefly that a self-review is running so the\n plan changing under them is expected. When you next respond, summarize what the\n review changed and what it surfaced for the user to decide.\n\n## Visual Surface Choice\n\nChoose the surface before creating the plan or after reading the source plan. Do\nnot add visual chrome by default:\n\nFor UI/product plans, the top canvas is usually the primary review surface. Put\nthe first meaningful wireframes there, not buried as document-body blocks. Use\nmultiple canvas artboards when states matter, such as the default view, an\noverflow menu or popover, a side panel, loading, or error. Put short annotations\nbeside frames with \\`targetId\\` plus \\`placement\\`; keep implementation details,\ntradeoffs, file maps, data contracts, risks, and verification in the document\nbody below the canvas.\n\nWhen the user asks for a flow, storyboard, journey, wireframe, canvas, or \"what\nthis looks like\", treat that as a canvas-first request. Make one artboard per\nuser-visible state, connect only adjacent transitions, and use short canvas\nannotations for the product notes. Do not substitute a document-body \\`diagram\\`\nblock for the requested storyboard just because HTML diagrams are faster to\nwrite; diagrams belong below the canvas for backend mechanics, architecture, or\ndata-flow explanation.\n\nKeep product wireframes and explanatory/meta diagrams separate. Start with pure\nscreens that look like the app state under discussion, without callout prose or\narchitecture notes embedded inside the UI. Put arrows, labels, contracts, data\nflow, and mode explanations in separate annotations, separate canvas diagrams,\nor the document body.\n\nWhen the plan touches an existing app, inspect the current shell/components\nbefore drawing. The first artboard should look like the real app at the same\ndensity: existing sidebars, toolbar placement, overflow menus, app chrome, and\nframework agent chrome stay in their real places. Model secondary surfaces as\nseparate states, such as a top-right overflow popover, sheet, panel, loading\nstate, or separate AgentSidebar, rather than inventing a permanent inspector or\nfolding framework chrome into the product UI.\n\n- No visual surface for architecture-only, backend-only, data migration,\n copy-only, or otherwise non-visual plans. Do not use the top canvas for\n architecture diagrams, dependency maps, file plans, API contracts, or\n data-flow-only reviews. Use a strong document with local inline diagrams\n only when relationships need a visual explanation, usually one spatial diagram\n per recommendation or decision. Prefer grouped regions, layers, quadrants,\n matrices, or before/after panels over a single-axis chain unless the\n relationship is truly sequential.\n- Canvas only for one static screen, a before/after comparison, a component\n state, a small popover, or a visual direction that does not require clicking.\n Put those wireframes in \\`content.canvas\\` and omit \\`content.prototype\\`.\n- Canvas + prototype for multi-step UI flows, onboarding, wizards,\n review/approval flows, navigation changes, or anything where the reviewer\n needs to operate the behavior. Keep the static wireframes in\n \\`content.canvas\\`, add the aligned functional prototype in\n \\`content.prototype\\`, and rely on the top visual tabs to switch between them.\n- Prototype-first when the user asks to operate the UI or when interaction is\n the main question. Use \\`create-prototype-plan\\`, which still preserves static\n mocks where useful.\n\nFor mixed canvas + prototype plans, reuse the same real labels, app statuses,\nand screen ids across both surfaces. The canvas is the inspectable static reference;\nthe prototype is the interactive version of that same flow, not a separate\ndesign direction.\n\n## Wireframe quality — read \\`references/wireframe.md\\`\n\nUI recap/plan wireframes must meet a strict quality bar — full-width chrome,\npinned bottom bars, real product content, before/after comparability, the right\n\\`surface\\` preset, \\`--wf-\\` tokens instead of hex, and no \\`<html>\\`/\\`<style>\\`/font\ntags. Before authoring ANY wireframe / \\`<Screen>\\` / \\`WireframeBlock\\`, READ\n\\`references/wireframe.md\\` in this skill directory — it is the single source of\ntruth for HTML wireframe quality, shared word for word with \\`/visual-plan\\`\nand \\`/visual-recap\\`. Do not author wireframes from memory.\n\n## Canvas — read \\`references/canvas.md\\`\n\nThe canvas is the single source of truth for static UI mockups: the \\`surface\\`\nlocks each artboard's footprint, mixed surfaces lay out\nin lanes, annotations are plain-text designer notes anchored by\n\\`targetId\\`/\\`placement\\`, and edits are surgical \\`contentPatches\\`. Before\nauthoring or editing ANY canvas, artboard, or annotation, READ\n\\`references/canvas.md\\` in this skill directory — it is the single source of truth\nfor canvas/artboard mechanics. Do not author canvas layouts from memory.\nCanvas artboards use the same HTML wireframe path as document-body\n\\`WireframeBlock\\` screens: author \\`<Screen surface=\"...\" html={...} />\\` with a\nsemantic HTML fragment. Do not author fresh kit-tree children such as\n\\`<FrameScreen>\\`, \\`<Card>\\`, \\`<Row>\\`, or \\`<Btn>\\` inside canvas \\`<Screen>\\` tags;\nthose are legacy compatibility markup for old plans and produce brittle canvas\nlayouts.\n\n## Document quality — read \\`references/document-quality.md\\`\n\nThe document is a serious technical plan, not marketing: outcome-first,\nprose-first, self-contained, built from the right native blocks, with open\nquestions in a single bottom \\`question-form\\` and a pre-handoff visual check.\nBefore authoring the plan document, READ \\`references/document-quality.md\\` in this\nskill directory — it is the single source of truth for the document quality bar.\nDo not write the document from memory.\n\n## Good vs. bad exemplar — read \\`references/exemplar.md\\`\n\nFor a worked example of the bar — a great UI-first plan and \\`/visual-plan\\`, plus\nthe anti-patterns to avoid — READ \\`references/exemplar.md\\` in this skill\ndirectory before authoring a plan.\n\n## Tool Guidance\n\n- \\`create-visual-plan\\`: start one structured visual plan per agent task/run, or\n import an existing text plan by passing \\`planText\\`; \\`content\\` may include no\n visual surface, canvas only, or canvas + prototype.\n- \\`create-ui-plan\\`: start a UI-first plan when the work is primarily product UI.\n- \\`create-prototype-plan\\`: start a prototype-first plan with a functional top\n review surface.\n- \\`create-plan-design\\`: start a full-fidelity branded Design-tab plan with an\n optional matching Prototype tab.\n- \\`convert-visual-plan-to-prototype\\`: convert an existing HTML wireframe canvas\n into a prototype plan.\n- \\`create-visual-questions\\`: use only when the user explicitly asks for a visual\n intake questionnaire, not as \\`/visual-plan\\` preflight.\n- \\`update-visual-plan\\`: revise content, status, or comments with targeted\n \\`contentPatches\\` (see Core Workflow step 6).\n- \\`read-visual-plan-source\\`: read the normalized plan as \\`plan.mdx\\`,\n optional \\`canvas.mdx\\`, optional \\`.plan-state.json\\`, and JSON.\n- \\`patch-visual-plan-source\\`: apply granular MDX AST patches by stable block,\n artboard, annotation, component, or wireframe-node id.\n- \\`import-visual-plan-source\\`: create or replace a plan from an MDX folder.\n- \\`get-visual-plan\\`: read the current structured plan, exported HTML, and\n annotations; it also returns the MDX folder for source workflows.\n- \\`get-plan-feedback\\`: read unconsumed human feedback. Use it frequently; it\n returns grouped threads, exact anchor details, expected resolver, and recent\n review-event payloads so agents can act only on the comments meant for them.\n- \\`get-plan-blocks\\`: resolve block tags before authoring — do not memorize tags;\n call this first to get the authoritative tag names, required fields, and prop\n shapes from the live block registry.\n- \\`export-visual-plan\\`: export HTML, Markdown fallback, structured JSON, and MDX\n files for repo check-in.\n\nWhen the user critiques a plan's look or structure, fix the renderer or this\nskill — never hand-edit one stored plan. Turn feedback into better guidance.\n\n## Local-Files Privacy Mode — read \\`references/local-files.md\\`\n\nWhen the user wants no hosted Plan database writes — no DB writes, no Plan MCP\npublish, fully local/offline/private planning, repo-owned source-controlled\nartifacts, or \\`AGENT_NATIVE_PLANS_MODE=local-files\\` — do not call any hosted Plan\ntool except the schema-only \\`get-plan-blocks\\` catalog lookup. Author a local MDX\nfolder and\npreview it with \\`plan local check\\` / \\`plan local serve\\` / \\`plan local verify\\`.\nBefore using local-files mode, READ \\`references/local-files.md\\` in this skill\ndirectory — it is the single source of truth for the full contract (catalog\nlookup, MDX folder layout, the local bridge commands, and the hosted tools you\nmust not call). Carry forward only the code-research and plan-composition\nguidance from Core Workflow; everything hosted is replaced by the local bridge.\n\n## Interpreting comment anchors\n\nThis section applies to hosted plans with \\`get-plan-feedback\\` /\n\\`update-visual-plan\\`. In local-files mode, do not call hosted feedback or update\ntools; interpret file/chat feedback directly, edit the MDX files, rerun the\nlocal bridge check/serve/verify command, and report the new local URL.\n\n\\`get-plan-feedback\\` returns rich anchors — read them before acting on any comment.\n\n- Coordinate frames.* \\`targetX\\`/\\`targetY\\` are percentages within the\n element named by \\`targetSelector\\`/\\`targetKind\\`. Bare \\`x\\`/\\`y\\` are percentages\n of the whole plan document. \\`canvasX\\`/\\`canvasY\\` are raw board-world pixels on\n the design canvas (board size given when available).\n- Wireframe pins. Anchors on wireframes include \\`targetNodeId\\` and\n \\`targetNodePath\\` (e.g. \\`card > list > listItem \"Acme Inc\"\\`) identifying the\n exact kit node. Use \\`targetNodeId\\` directly with wireframe node patch ops;\n use \\`data-design-id\\` values from design artboards with\n \\`update-design-element-style\\`. Prefer the node id/path over raw coordinates;\n fall back to coordinates plus the focused screenshot (red ring marks the exact\n point) only when no node id is present.\n- Text quotes. Resolve \\`textQuote\\` against current prose using\n \\`contextBefore\\`/\\`contextAfter\\` for disambiguation. If \\`ambiguous: true\\`, ask\n the user — do not guess which occurrence is meant.\n- Detached comments. \\`get-plan-feedback\\` flags threads whose quoted text no\n longer exists as \\`detached\\` (in \\`detachedThreads\\`). Reconcile these against\n rewritten content — never silently drop them.\n- Routing. \\`resolutionTarget\\` is the only routing signal: act on \\`agent\\`,\n treat \\`human\\` as context only. \\`@mentions\\` are people to notify, never a\n routing signal.\n- Two-axis state. Mark every ingested comment as consumed\n (\\`consumedCommentIds\\` on \\`update-visual-plan\\`). Set \\`status=resolved\\` only on\n agent-targeted comments you actually addressed; leave human-targeted comments\n open.\n\n## Visibility & Sharing\n\nUse \\`set-resource-visibility\\` to change who can see a plan (e.g. public, login,\nor org-scoped). Use \\`share-resource\\` to grant specific users or roles access\nby email or role. Gate visibility before sharing any plan that covers\nunreleased or private work — default to the narrowest scope that meets the\nreview need.\n\n## Setup & Authentication\n\nThere are two ways into Plans.\n\nCoding agent (CLI). Install once with the Agent-Native CLI. The command\ninstalls the Plans skills, registers the hosted Plans MCP connector, and runs\nauth/setup for the selected local client(s) in the same step (a one-time browser\nsign-in at setup — this is intended), so the first tool call in that client does\nnot hit an OAuth wall:\n\n\\`\\`\\`bash\nnpx @agent-native/core@latest skills add visual-plans\n\\`\\`\\`\n\nAfter that, \\`/visual-plan\\`, \\`/visual-recap\\`, and \\`/visualize-repo\\` are the\ninstalled slash commands. If you only need one command, use\n\\`skills add visual-plan\\`, \\`skills add visual-recap\\`, or\n\\`skills add visualize-repo\\` instead. The other planning modes\n(\\`create-ui-plan\\`, \\`create-prototype-plan\\`, \\`create-plan-design\\`,\n\\`create-visual-questions\\`) are MCP tools reachable from \\`/visual-plan\\`, not\nseparate slash commands. Pass \\`--no-connect\\` to register the connector without\nauthenticating, then run\n\\`npx @agent-native/core@latest connect https://plan.agent-native.com --client all\\`\nwhenever you are ready, or choose a narrower \\`--client\\`. Auth and MCP tool\nloading are per client config/session.\n\nBrowser (people you share with). Open the Plans editor and create & edit\nwith no sign-up — you work as a guest. Sign in only when you want to save or\nshare; signing in claims the plans you made as a guest into your account.\n\nSharing and commenting require an account: public/shared plans are viewable by\nanyone with the link, but commenting on them needs an agent-native account.\n\nFor fully offline, no-account use, run the Plans app locally and sync plans to\nyour repo as MDX. This local mode is a separate advanced path, not the default\nhosted flow.\n\nFor repo-wide visual docs, run\n\\`npx @agent-native/core@latest visualize-repo --open\\` to create/update\n\\`agent-native.json\\`, seed \\`.agent-native/visual-docs/repo-overview\\`, and open\nthe local bridge.\n\nIf a Plans tool returns \\`needs auth\\`, \\`Unauthorized\\`, or \\`Session terminated\\`, do\nnot keep retrying it — stop and give the user the per-client reconnect step from\n\\`references/connection.md\\`, then continue once the connector is available.\n\nHosted default: connect \\`https://plan.agent-native.com/_agent-native/mcp\\`. Do\nnot put shared secrets in skill files.\n`;\n"]}
1	+ {"version":3,"file":"visual-plan-skill.js","sourceRoot":"","sources":["../../../src/cli/skills-content/visual-plan-skill.ts"],"names":[],"mappings":"AAAA,MAAM,CAAC,MAAM,qBAAqB,GAAG;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CAqdpC,CAAC","sourcesContent":["export const VISUAL_PLANS_SKILL_MD = `---\nname: visual-plan\ndescription: >-\n Turn ordinary text plans into rich interactive visual plans with diagrams,\n file maps, annotated code, open questions, and UI/prototype review when\n useful.\nmetadata:\n visibility: exported\n---\n\n# Agent-Native Plans\n\nAgent-Native Plans is structured visual planning mode for coding agents. Build\nthe plan you would normally write in Markdown, but as a scannable document with\neditable blocks mixed in: inline diagrams, code snippets,\nopen questions, and an optional top visual review area (wireframe canvas, live\nprototype, or both in tabs). Architecture and backend plans stay document-only;\nUI and product plans start with the top canvas/prototype (the Visual Surface\nChoice section owns that rule).\n\n\\`/visual-plan\\` is the packaged command and main entry point. Choose the review\nmode from the task: UI-first when the work is primarily product UI and review\nshould start with screens, prototype-first when review should start with a\nfunctional live prototype, design-first when review needs full-fidelity branded\nscreens, or visual-intake when the user explicitly wants a questionnaire before\nplanning. When a Codex, Claude Code, Markdown, or pasted plan already exists,\n\\`/visual-plan\\` uses that source plan as the starting point and builds the review\nsurface from it instead of starting over.\n\n## When To Use\n\nCreate or adapt a visual plan whenever the plan would be better as a reviewable\nartifact than a chat paragraph. This includes modest work such as a single UI\nsurface with states, a small workflow, a before/after product change, or a\ncomponent/API/data-shape decision that needs alignment, plus larger multi-file,\nambiguous, long-running, risky, or UI-heavy work. Use it when architecture /\ndata flow / UI direction / options / open questions would benefit from inline\ndiagrams or structured blocks, when the user needs to react to a direction\nbefore you implement, or when an existing text plan needs a richer review\nsurface.\n\n## Plan Discipline\n\n- Gate thoughtfully. A visual plan is a richer review surface, not only a\n tool for giant projects. Use it when the user needs to see, compare, comment\n on, or approve a direction before code, even for a modest UI/state/workflow\n change. Skip it for truly trivial, unambiguous work — typos, one-line fixes, a\n single well-specified function, anything whose diff you could describe in one\n sentence — and just make the change. Never pad a plan with filler and never\n ship a single-step plan.\n- Research before you draft. Read the real files, actions, schema, and\n patterns first; name actual files, symbols, and data shapes instead of\n inventing them. Check existing \\`actions/\\` before proposing endpoints and prefer\n named client helpers over raw fetch. Delegate wide exploration to a sub-agent.\n Lead with reuse: for each step, name what it reuses — existing actions, schema,\n components, helpers — before what it adds, so the plan explains the genuinely new\n delta instead of redescribing what already exists.\n- Decide the hard-to-reverse bets first. For non-trivial backend, data, or API\n work, sketch where the feature is headed, then call out the decisions that are\n expensive to undo once data or callers depend on them — wire format, public ids,\n data-model shape, auth and ownership boundaries — and get those right in the plan\n even if most of the feature ships later. Then scope to the smallest first cut that\n proves the approach without foreclosing it, stating both what is in and what is\n explicitly deferred.\n- Keep examples at the right altitude. When the user's idea is a broad\n framework, product, or operating-model change, do not collapse it into the\n first concrete example, provider, or sync path they mention. Separate the core\n abstraction from motivating examples and app/provider adapters. Use examples\n to make the plan legible, but label them as examples unless they are the whole\n requested scope.\n- Publish standalone plans. If the user pasted, referenced, or already has a\n Codex / Claude Code / Markdown plan, treat it as source material, but rewrite\n the published plan as a clean standalone proposal. Preserve the source plan's\n useful intent and codebase facts, label inferred visuals as inferred, and avoid\n revision language such as \"preserve the prior plan\", \"do not drop the old\n idea\", \"unlike the previous version\", or \"this revision changes...\". A reader\n who never saw the chat or earlier drafts should understand the plan.\n- Make the first read concrete. If the plan is meant to be shared with\n someone outside the chat, or if the concept is abstract, lead near the top with\n one concrete product example before mode tables, architecture, or roadmaps. For\n UI-capable concepts, that usually means a top-canvas app state that shows the\n real user workflow in product terms. Do not rely on phrases that only make\n sense in conversation, and do not frame the plan as \"not the old idea\"; state\n the positive model directly.\n- Planning is read-only. Make no source edits while building or reviewing the\n plan. Start editing only after the user approves the direction.\n- Clarify vs. assume. Do not ask how to build it — explore and present the\n approach and options in the plan. Ask a clarifying question only when an\n ambiguity would change the design and you cannot resolve it from the code; use\n the host agent's normal ask-user-question flow and batch 2-4 high-leverage\n questions before finalizing. Do not call \\`create-visual-questions\\` for\n ordinary clarification or preflight; reserve it for the visual-intake mode when\n the user explicitly asks for a visual intake questionnaire. Otherwise state the\n assumption explicitly and proceed, and keep anything unresolved in the plan's\n single bottom \\`question-form\\` Open Questions block. For complex plans, do a\n final open-question pass before handoff: if a decision would affect\n architecture, scope, UX, data shape, or rollout, either decide it in the plan\n with rationale or put it in that bottom form with a recommended default.\n- The plan is the approval gate. After surfacing it, ask the user to review\n and approve before you write code, and name which files/areas the work touches.\n Presenting the plan and requesting sign-off is the approval step — do not ask a\n separate \"does this look good?\" question.\n- The document is the source of truth, not the chat. When scope shifts,\n update the plan with \\`update-visual-plan\\` rather than only changing course in\n chat, and make the updated document stand alone. Do not describe the update as\n a correction to an earlier draft inside the plan itself. Re-read the approved\n plan before major steps.\n\n## Create A Structured Agent-Native Plan — Never Inline\n\nThe deliverable is ALWAYS a structured Agent-Native Plan, not a chat-only plan.\nThe hosted Plan MCP connector (\\`plan\\` server, or legacy \\`agent-native-plans\\`) is\nthe default collaboration and commenting surface; it is not a reason to reject\nthe planning pattern as an external dependency or rented layer. Plans are\nportable source artifacts (\\`plan.mdx\\`, optional \\`canvas.mdx\\` /\n\\`prototype.mdx\\`, JSON, and HTML export), and ownership-sensitive workflows can\nuse local-files mode or a self-hosted/custom Plan app URL without abandoning the\nskill's review discipline. Do not advise the user to skip \\`/visual-plan\\` because\nthe default surface is hosted; choose the right Plan mode for the user's\nownership, privacy, sharing, and branding needs.\n\nBy default, create the plan via the Plan MCP connector and NEVER hand it over as\ninline chat content — no Markdown prose, ASCII sketch, table, or fenced\nwireframe. If the \\`plan\\` (or legacy \\`agent-native-plans\\`) tools are not visible,\ndiscover them through the host's \\`tool_search\\` first; if they are still missing,\nSTOP and give the user the client-specific reconnect step rather than improvising\nan inline plan. Before publishing, or whenever a connector or auth error appears,\nREAD \\`references/connection.md\\` in this skill directory — it is the single source\nof truth for the never-inline rule, connector discovery, and the per-client\nreconnect steps. Local-files privacy mode (after Tool Guidance) is the exception.\n\n## Core Workflow\n\nThis section describes the default hosted Plan MCP workflow. If\n\\`AGENT_NATIVE_PLANS_MODE=local-files\\` is set, or the user asks for fully local\nfiles/no hosted Plan writes, use Local-Files Privacy Mode instead; carry\nforward only the code-research and plan-composition guidance here.\n\n1. Follow the host agent's normal planning flow: inspect the codebase, delegate\n wide exploration when useful, gather the info needed, and ask native\n clarifying questions as needed before generating the plan. If a source plan\n already exists, gather its exact text from the user's paste, a referenced\n file, or recent visible agent context; do not invent source text.\n2. Call \\`get-plan-blocks\\` for the authoritative block catalog — do not author\n from memorized tags. Then call the mode-matched create tool:\n \\`create-visual-plan\\` for document-first plans (architecture, backend, data,\n refactor, API), \\`create-ui-plan\\` for UI-first plans, \\`create-prototype-plan\\`\n for prototype-first plans, \\`create-plan-design\\` for design-first plans,\n \\`create-visual-questions\\` only when the user explicitly asks for a visual\n intake questionnaire. When a source plan already exists,\n pass it as \\`planText\\` and preserve the original plan's useful intent while\n producing a standalone plan document, not a revision memo.\n3. For UI/product plans, compose the top canvas first with the primary\n wireframes and annotated states, then write the document with native blocks\n (see \\`references/canvas.md\\` and \\`references/document-quality.md\\`). For\n broad product architecture plans with a user-facing implication, add a\n concrete \"what this looks like in the app\" visual before the abstract\n architecture or mode tables. Keep the document close to the standalone\n Markdown plan the agent would normally output. If an existing plan was\n provided, carry forward the right facts and decisions without referring to\n the previous draft or explaining how this version differs. For non-visual\n plans, skip the top visual surface (Visual Surface Choice below owns the rule)\n and put \\`diagram\\`, \\`data-model\\`,\n \\`api-endpoint\\`, \\`diff\\`, \\`file-tree\\`, \\`code\\`, and \\`annotated-code\\` blocks\n directly next to the relevant prose.\n Wide document layout is renderer-owned and intentionally allowlisted: only\n literal code-review surfaces (\\`diff\\`, \\`annotated-code\\`) and \\`tabs\\` blocks\n with vertical orientation or diff-like children break out wider than prose.\n Keep \\`api-endpoint\\`, \\`openapi-spec\\`, \\`data-model\\`, \\`json-explorer\\`,\n \\`wireframe\\`, question, and \\`custom-html\\` blocks in normal document flow unless\n their own renderer says otherwise.\n4. Surface the returned Plans link or inline MCP App and ask the user to review.\n Always include the actual URL in chat so the next step is a click in CLI or\n other text-only hosts. When the host exposes an embedded browser/preview panel\n and a tool can open arbitrary URLs there, open the returned plan URL\n automatically for convenient review — a convenience and smoke test, never the\n only handoff or the access\n model. Plans should load out of the box for the local agent and local browser\n session; if a signed-in embedded browser cannot read a local plan that an\n anonymous/tool check can read, fix the app/action ownership or access path\n rather than patching one plan by hand. For high-stakes plans (architecture,\n backend, data, multi-file, or risky), also kick off the self-review pass in\n Self-Review Before Handoff while the user reads, instead of blocking the\n handoff on it.\n5. For hosted plans, call \\`get-plan-feedback\\` before editing, after review,\n after any long pause,\n and before the final response. Treat \\`anchorDetails\\`, resolver intent, recent\n review events, and any focused screenshots from browser handoff as the source\n of truth for exactly what changed and exactly what each comment points at.\n6. For hosted plans, apply changes with \\`update-visual-plan\\`, preferring\n targeted \\`contentPatches\\`.\n Treat the top-level \\`content\\` payload as a full replacement, not a merge; do\n not send a partial \\`content\\` object to add a canvas or one block. If a full\n replacement is unavoidable, first read the complete plan source/content, carry\n forward every existing block and visual surface, and verify the source/export\n afterward so the document body was not truncated. When the user wants\n source-control friendly edits, use \\`patch-visual-plan-source\\` against the MDX\n files instead of regenerating the plan.\n7. For hosted plans, export with \\`export-visual-plan\\` only when the user wants a\n shareable receipt or repo-check-in artifacts.\n\n## Self-Review Before Handoff\n\nFor high-stakes plans — architecture, backend, data-model, migration, multi-file,\nor otherwise risky work — run one adversarial self-review pass before treating the\nplan as final. Skip it for small, UI-only, or single-decision plans where the cost\noutweighs the value. Keep the pass cheap and non-blocking:\n\n- Surface the plan first, review concurrently. Post the link and let the user\n start reading, then run the review in parallel — never make the user wait on it.\n- Review the written plan; do not re-research. Critique the plan text and its\n own blocks. The grounding was already done while drafting, so the review checks\n the output instead of re-exploring the repo.\n- Spawn one skeptical reviewer whose only job is to find what is weak, missing,\n or wrong — not to praise. Point it at: hard-to-reverse decisions made implicitly\n or not at all (wire format, public ids, data-model shape, auth, ownership); steps\n not anchored in real files or symbols; a menu of options where the plan should\n commit to one; obvious missing decisions (\"what happens when X?\", \"why not Y?\");\n and padding or single-step filler.\n- Fix vs. ask. Apply clear-cut fixes yourself with \\`update-visual-plan\\`\n \\`contentPatches\\` — vague non-goals, unanchored claims, an obvious missing\n decision. Route genuine judgment calls back to the user instead: add them to the\n bottom \\`question-form\\` Open Questions block or batch them into the normal\n ask-user-question flow. Do not silently decide them.\n- Do not surprise the user mid-read. On a large plan, apply the patches before\n the editor loads; otherwise note briefly that a self-review is running so the\n plan changing under them is expected. When you next respond, summarize what the\n review changed and what it surfaced for the user to decide.\n\n## Visual Surface Choice\n\nChoose the surface before creating the plan or after reading the source plan. Do\nnot add visual chrome by default:\n\nFor UI/product plans, the top canvas is usually the primary review surface. Put\nthe first meaningful wireframes there, not buried as document-body blocks. Use\nmultiple canvas artboards when states matter, such as the default view, an\noverflow menu or popover, a side panel, loading, or error. Put short annotations\nbeside frames with \\`targetId\\` plus \\`placement\\`; keep implementation details,\ntradeoffs, file maps, data contracts, risks, and verification in the document\nbody below the canvas.\n\nWhen the user asks for a flow, storyboard, journey, wireframe, canvas, or \"what\nthis looks like\", treat that as a canvas-first request. Make one artboard per\nuser-visible state, connect only adjacent transitions, and use short canvas\nannotations for the product notes. Do not substitute a document-body \\`diagram\\`\nblock for the requested storyboard just because HTML diagrams are faster to\nwrite; diagrams belong below the canvas for backend mechanics, architecture, or\ndata-flow explanation.\n\nKeep product wireframes and explanatory/meta diagrams separate. Start with pure\nscreens that look like the app state under discussion, without callout prose or\narchitecture notes embedded inside the UI. Put arrows, labels, contracts, data\nflow, and mode explanations in separate annotations, separate canvas diagrams,\nor the document body.\n\nWhen the plan touches an existing app, inspect the current shell/components\nbefore drawing. The first artboard should look like the real app at the same\ndensity: existing sidebars, toolbar placement, overflow menus, app chrome, and\nframework agent chrome stay in their real places. Model secondary surfaces as\nseparate states, such as a top-right overflow popover, sheet, panel, loading\nstate, or separate AgentSidebar, rather than inventing a permanent inspector or\nfolding framework chrome into the product UI.\n\n- No visual surface for architecture-only, backend-only, data migration,\n copy-only, or otherwise non-visual plans. Do not use the top canvas for\n architecture diagrams, dependency maps, file plans, API contracts, or\n data-flow-only reviews. Use a strong document with local inline diagrams\n only when relationships need a visual explanation, usually one spatial diagram\n per recommendation or decision. Prefer grouped regions, layers, quadrants,\n matrices, or before/after panels over a single-axis chain unless the\n relationship is truly sequential.\n- Canvas only for one static screen, a before/after comparison, a component\n state, a small popover, or a visual direction that does not require clicking.\n Put those wireframes in \\`content.canvas\\` and omit \\`content.prototype\\`.\n- Canvas + prototype for multi-step UI flows, onboarding, wizards,\n review/approval flows, navigation changes, or anything where the reviewer\n needs to operate the behavior. Keep the static wireframes in\n \\`content.canvas\\`, add the aligned functional prototype in\n \\`content.prototype\\`, and rely on the top visual tabs to switch between them.\n- Prototype-first when the user asks to operate the UI or when interaction is\n the main question. Use \\`create-prototype-plan\\`, which still preserves static\n mocks where useful.\n\nFor mixed canvas + prototype plans, reuse the same real labels, app statuses,\nand screen ids across both surfaces. The canvas is the inspectable static reference;\nthe prototype is the interactive version of that same flow, not a separate\ndesign direction.\n\n## Wireframe quality — read \\`references/wireframe.md\\`\n\nUI recap/plan wireframes must meet a strict quality bar — full-width chrome,\npinned bottom bars, real product content, before/after comparability, the right\n\\`surface\\` preset, \\`--wf-\\` tokens instead of hex, and no \\`<html>\\`/\\`<style>\\`/font\ntags. Before authoring ANY wireframe / \\`<Screen>\\` / \\`WireframeBlock\\`, READ\n\\`references/wireframe.md\\` in this skill directory — it is the single source of\ntruth for HTML wireframe quality, shared word for word with \\`/visual-plan\\`\nand \\`/visual-recap\\`. Do not author wireframes from memory.\n\n## Canvas — read \\`references/canvas.md\\`\n\nThe canvas is the single source of truth for static UI mockups: the \\`surface\\`\nlocks each artboard's footprint, mixed surfaces lay out\nin lanes, annotations are plain-text designer notes anchored by\n\\`targetId\\`/\\`placement\\`, and edits are surgical \\`contentPatches\\`. Before\nauthoring or editing ANY canvas, artboard, or annotation, READ\n\\`references/canvas.md\\` in this skill directory — it is the single source of truth\nfor canvas/artboard mechanics. Do not author canvas layouts from memory.\nCanvas artboards use the same HTML wireframe path as document-body\n\\`WireframeBlock\\` screens: author \\`<Screen surface=\"...\" html={...} />\\` with a\nsemantic HTML fragment. Do not author fresh kit-tree children such as\n\\`<FrameScreen>\\`, \\`<Card>\\`, \\`<Row>\\`, or \\`<Btn>\\` inside canvas \\`<Screen>\\` tags;\nthose are legacy compatibility markup for old plans and produce brittle canvas\nlayouts.\n\n## Document quality — read \\`references/document-quality.md\\`\n\nThe document is a serious technical plan, not marketing: outcome-first,\nprose-first, self-contained, built from the right native blocks, with open\nquestions in a single bottom \\`question-form\\` and a pre-handoff visual check.\nBefore authoring the plan document, READ \\`references/document-quality.md\\` in this\nskill directory — it is the single source of truth for the document quality bar.\nDo not write the document from memory.\n\n## Good vs. bad exemplar — read \\`references/exemplar.md\\`\n\nFor a worked example of the bar — a great UI-first plan and \\`/visual-plan\\`, plus\nthe anti-patterns to avoid — READ \\`references/exemplar.md\\` in this skill\ndirectory before authoring a plan.\n\n## Tool Guidance\n\n- \\`create-visual-plan\\`: start one structured visual plan per agent task/run, or\n import an existing text plan by passing \\`planText\\`; \\`content\\` may include no\n visual surface, canvas only, or canvas + prototype.\n- \\`create-ui-plan\\`: start a UI-first plan when the work is primarily product UI.\n- \\`create-prototype-plan\\`: start a prototype-first plan with a functional top\n review surface.\n- \\`create-plan-design\\`: start a full-fidelity branded Design-tab plan with an\n optional matching Prototype tab.\n- \\`convert-visual-plan-to-prototype\\`: convert an existing HTML wireframe canvas\n into a prototype plan.\n- \\`create-visual-questions\\`: use only when the user explicitly asks for a visual\n intake questionnaire, not as \\`/visual-plan\\` preflight.\n- \\`update-visual-plan\\`: revise content, status, or comments with targeted\n \\`contentPatches\\` (see Core Workflow step 6).\n- \\`read-visual-plan-source\\`: read the normalized plan as \\`plan.mdx\\`,\n optional \\`canvas.mdx\\`, optional \\`.plan-state.json\\`, and JSON.\n- \\`patch-visual-plan-source\\`: apply granular MDX AST patches by stable block,\n artboard, annotation, component, or wireframe-node id.\n- \\`import-visual-plan-source\\`: create or replace a plan from an MDX folder.\n- \\`get-visual-plan\\`: read the current structured plan, exported HTML, and\n annotations; it also returns the MDX folder for source workflows.\n- \\`get-plan-feedback\\`: read unconsumed human feedback. Use it frequently; it\n returns grouped threads, exact anchor details, expected resolver, and recent\n review-event payloads so agents can act only on the comments meant for them.\n- \\`get-plan-blocks\\`: resolve block tags before authoring — do not memorize tags;\n call this first to get the authoritative tag names, required fields, and prop\n shapes from the live block registry.\n- \\`export-visual-plan\\`: export HTML, Markdown fallback, structured JSON, and MDX\n files for repo check-in.\n\nWhen the user critiques a plan's look or structure, fix the renderer or this\nskill — never hand-edit one stored plan. Turn feedback into better guidance.\n\n## Local-Files Privacy Mode — read \\`references/local-files.md\\`\n\nWhen the user wants no hosted Plan database writes — no DB writes, no Plan MCP\npublish, fully local/offline/private planning, repo-owned source-controlled\nartifacts, or \\`AGENT_NATIVE_PLANS_MODE=local-files\\` — do not call any hosted Plan\ntool except the schema-only \\`get-plan-blocks\\` catalog lookup. Author a local MDX\nfolder and\npreview it with \\`plan local check\\` / \\`plan local serve\\` / \\`plan local verify\\`.\nBefore using local-files mode, READ \\`references/local-files.md\\` in this skill\ndirectory — it is the single source of truth for the full contract (catalog\nlookup, MDX folder layout, the local bridge commands, and the hosted tools you\nmust not call). Carry forward only the code-research and plan-composition\nguidance from Core Workflow; everything hosted is replaced by the local bridge.\n\n## Interpreting comment anchors\n\nThis section applies to hosted plans with \\`get-plan-feedback\\` /\n\\`update-visual-plan\\`. In local-files mode, do not call hosted feedback or update\ntools; interpret file/chat feedback directly, edit the MDX files, rerun the\nlocal bridge check/serve/verify command, and report the new local URL.\n\n\\`get-plan-feedback\\` returns rich anchors — read them before acting on any comment.\n\n- Coordinate frames.* \\`targetX\\`/\\`targetY\\` are percentages within the\n element named by \\`targetSelector\\`/\\`targetKind\\`. Bare \\`x\\`/\\`y\\` are percentages\n of the whole plan document. \\`canvasX\\`/\\`canvasY\\` are raw board-world pixels on\n the design canvas (board size given when available).\n- Wireframe pins. Anchors on wireframes include \\`targetNodeId\\` and\n \\`targetNodePath\\` (e.g. \\`card > list > listItem \"Acme Inc\"\\`) identifying the\n exact kit node. Use \\`targetNodeId\\` directly with wireframe node patch ops;\n use \\`data-design-id\\` values from design artboards with\n \\`update-design-element-style\\`. Prefer the node id/path over raw coordinates;\n fall back to coordinates plus the focused screenshot (red ring marks the exact\n point) only when no node id is present.\n- Text quotes. Resolve \\`textQuote\\` against current prose using\n \\`contextBefore\\`/\\`contextAfter\\` for disambiguation. If \\`ambiguous: true\\`, ask\n the user — do not guess which occurrence is meant.\n- Detached comments. \\`get-plan-feedback\\` flags threads whose quoted text no\n longer exists as \\`detached\\` (in \\`detachedThreads\\`). Reconcile these against\n rewritten content — never silently drop them.\n- Routing. \\`resolutionTarget\\` is the only routing signal: act on \\`agent\\`,\n treat \\`human\\` as context only. \\`@mentions\\` are people to notify, never a\n routing signal.\n- Two-axis state. Mark every ingested comment as consumed\n (\\`consumedCommentIds\\` on \\`update-visual-plan\\`). Set \\`status=resolved\\` only on\n agent-targeted comments you actually addressed; leave human-targeted comments\n open.\n\n## Visibility & Sharing\n\nUse \\`set-resource-visibility\\` to change who can see a plan (e.g. public, login,\nor org-scoped). Use \\`share-resource\\` to grant specific users or roles access\nby email or role. Gate visibility before sharing any plan that covers\nunreleased or private work — default to the narrowest scope that meets the\nreview need.\n\n## Setup & Authentication\n\nThere are two ways into Plans.\n\nCoding agent (CLI). Install once with the Agent-Native CLI. The command\ninstalls the Plans skills, registers the hosted Plans MCP connector, and runs\nauth/setup for the selected local client(s) in the same step (a one-time browser\nsign-in at setup — this is intended), so the first tool call in that client does\nnot hit an OAuth wall:\n\n\\`\\`\\`bash\nnpx @agent-native/core@latest skills add visual-plans\n\\`\\`\\`\n\nAfter that, \\`/visual-plan\\`, \\`/visual-recap\\`, and \\`/visualize-repo\\` are the\ninstalled slash commands. If you only need one command, use\n\\`skills add visual-plan\\`, \\`skills add visual-recap\\`, or\n\\`skills add visualize-repo\\` instead. The other planning modes\n(\\`create-ui-plan\\`, \\`create-prototype-plan\\`, \\`create-plan-design\\`,\n\\`create-visual-questions\\`) are MCP tools reachable from \\`/visual-plan\\`, not\nseparate slash commands. Pass \\`--no-connect\\` to register the connector without\nauthenticating, then run\n\\`npx @agent-native/core@latest connect https://plan.agent-native.com --client all\\`\nwhenever you are ready, or choose a narrower \\`--client\\`. Auth and MCP tool\nloading are per client config/session.\n\nBrowser (people you share with). Open the Plans editor and create & edit\nwith no sign-up — you work as a guest. Sign in only when you want to save or\nshare; signing in claims the plans you made as a guest into your account.\n\nSharing and commenting require an account: public/shared plans are viewable by\nanyone with the link, but commenting on them needs an agent-native account.\n\nFor fully offline, no-account use, run the Plans app locally and sync plans to\nyour repo as MDX. This local mode is a separate advanced path, not the default\nhosted flow.\n\nFor repo-wide visual docs, run\n\\`npx @agent-native/core@latest visualize-repo --open\\` to create/update\n\\`agent-native.json\\`, seed \\`.agent-native/visual-docs/repo-overview\\`, and open\nthe local bridge.\n\nIf a Plans tool returns \\`needs auth\\`, \\`Unauthorized\\`, or \\`Session terminated\\`, do\nnot keep retrying it — stop and give the user the per-client reconnect step from\n\\`references/connection.md\\`, then continue once the connector is available.\n\nHosted default: connect \\`https://plan.agent-native.com/mcp\\`. Do\nnot put shared secrets in skill files.\n`;\n"]}