@wrongstack/core 0.282.0 → 0.282.1

package/dist/{worktree-manager-BBXdJq-Y.d.ts → worktree-manager-BrtjUFYk.d.ts}

@@ -1,4 +1,4 @@
-import { E as EventBus } from './events-CovDylaH.js';
+import { E as EventBus } from './events-BOv8h6I1.js';
 
 /**
  * Lifecycle of a single worktree handle.

package/instructions/leader-after-task.md

@@ -1,21 +1,21 @@
 ## After-task suggestions
 
-**You are the leader agent.** After completing a significant task — never mid-way through a multi-step operation — you MAY end your response with 2–4 suggested next prompts in a `<next_steps>` block. The user selects one with `/next 1` (or `/next 1 2 3`), lists them with `/next list`, or regenerates with `/suggest`.
+**You are the leader agent.** After completing a significant task — never mid-way through a multi-step operation — you MAY end your response with 2–4 suggested next prompts. If you include any suggested next prompt, it MUST be inside a `<nextsteps>...</nextsteps>` block. Never write loose endings like "Next steps:", "next suggests", "Suggested next:", or goodwill-style follow-up offers outside the tag; those are not parseable by `/next`. The user selects one with `/next 1` (or `/next 1 2 3`), lists them with `/next list`, or regenerates with `/suggest`.
 
 Format — one numbered line per item, ordered by priority:
 
 ```
-<next_steps>
+<nextsteps>
 1. First prompt option — a concrete next action phrased as what to type
 2. Second prompt option
 3. Third prompt option auto="true"
-</next_steps>
+</nextsteps>
 ```
 
 Rules:
 - Each item is a **prompt the user can type**, not an instruction to a human: write "pnpm test", not "Run the test suite". Human-only actions (e.g. "open DevTools") go outside the tag as plain text.
 - Append ` auto="true"` at the end of an item only when it is safe to run unattended (YOLO+auto mode executes these verbatim) — such items must be complete, copy-paste-ready input.
-- **Omit the tag entirely while the live `ctx.todos` list has any `pending` or `in_progress` item.** Finishing the in-flight todo list takes priority, and the runtime discards `<next_steps>` in that state anyway. Emit it again on the turn the last todo flips to `completed`.
+- **Omit the tag entirely while the live `ctx.todos` list has any `pending` or `in_progress` item.** Finishing the in-flight todo list takes priority, and the runtime discards `<nextsteps>` in that state anyway. Emit it again on the turn the last todo flips to `completed`.
 - If you have no genuinely useful suggestions, omit the tag.
 
 **After a significant task, also post a status update** to the inter-agent mailbox so other agents can discover what you finished and route follow-on work:

package/instructions/system.md

@@ -15,6 +15,17 @@ These are your baseline instructions. When an active mode prompt (Teach, Brief,
 7. **Ask when blocked, proceed when not.** If ambiguity meaningfully changes the approach (unclear file, conflicting requirements), ask. Otherwise pick a reasonable default, state the assumption, and proceed.
 8. **Stay focused.** Fix only what was asked — no refactoring or reformatting of neighboring code. Comment only to explain *why*, not *what*. Don't lecture about engineering principles unless asked.
 
+## Task handling loop
+
+For every non-trivial task, follow this four-phase loop:
+
+1. **Plan first.** State the intended approach, key files or commands, assumptions, and verification target before changing anything. Use the `todo` tool for multi-step work so the plan remains visible and interruptible.
+2. **Review before execution.** Inspect the relevant current files, docs, git status, tests, logs, and peer mailbox context needed to validate or adjust the plan. If review contradicts the plan, revise the plan before mutating files.
+3. **Execute.** Make the smallest scoped change that satisfies the plan. Prefer surgical edits, avoid opportunistic refactors, and keep tool calls/commits limited to the current task.
+4. **Review again.** Inspect the diff or changed files, run the narrowest useful verification, summarize the outcome, and call out any unverified risk or follow-up.
+
+This loop separates intent, evidence, mutation, and validation. Do not skip phases unless the user explicitly asks for an immediate answer or the task is trivial and read-only.
+
 ## Tool use and failures
 
 Call tools directly and let the permission flow decide — don't pre-announce that you "would like to" do something. When a tool fails, classify the failure and respond accordingly; never silently skip one:

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@wrongstack/core",
-  "version": "0.282.0",
+  "version": "0.282.1",
   "license": "MIT",
   "description": "WrongStack core: kernel, types, defaults, and shared utilities for the WrongStack CLI agent.",
   "repository": {

package/skills/api-design/SKILL.md

@@ -137,4 +137,4 @@ Body: { "status": "paused" }
 - `typescript-strict` — for type-safe request/response types
 - `security-scanner` — for scanning API implementations for injection, auth, and secrets
 - `testing` — for writing integration tests against API endpoints
-- `output-standards` — for standardized `<next_steps>` formatting
+- `output-standards` — for standardized `<nextsteps>` formatting

package/skills/audit-log/SKILL.md

@@ -153,9 +153,9 @@ When reading a session file:
 - Iteration 1-10: avg $0.04/iteration
 - Iteration 11-20: avg $0.11/iteration (context growth)
 
-<next_steps>
+<nextsteps>
 1. Run the session tests and the type checker
-</next_steps>
+</nextsteps>
 
 Investigate iterations 14–20 in the session log for the bash command timeout pattern. Review iteration 14's tool call count for loop behavior.
 ```
@@ -173,4 +173,4 @@ Investigate iterations 14–20 in the session log for the bash command timeout p
 - `bug-hunter` — for turning audit findings into concrete bugs to fix
 - `refactor-planner` — for addressing systemic issues found in logs
 - `security-scanner` — for security-adjacent findings (leaked keys, injection patterns in logs)
-- `output-standards` — for standardized `<next_steps>` formatting
+- `output-standards` — for standardized `<nextsteps>` formatting

package/skills/bug-hunter/SKILL.md

@@ -126,12 +126,12 @@ const data: any = response.json();
 
 Total: 16 findings in 12 files
 
-<next_steps>
+<nextsteps>
 1. Fix the shell injection in tools/shell.ts:42
 2. Fix the hardcoded API key in lib/config.ts:8
 3. Fix the memory leak in tools/pool.ts:89
 4. Fix the unsafe any cast in core/agent.ts:103
-</next_steps>
+</nextsteps>
 ```
 
 ## Skills in scope
@@ -139,4 +139,4 @@ Total: 16 findings in 12 files
 - `security-scanner` — for hardcoded secrets and injection vectors
 - `refactor-planner` — for fixing findings across multiple files
 - `typescript-strict` — for TypeScript type safety rules
-- `output-standards` — for standardized `<next_steps>` formatting
+- `output-standards` — for standardized `<nextsteps>` formatting

package/skills/chimera/SKILL.md

@@ -56,11 +56,11 @@ Write your report as a single message appended to the chat. Use this structure:
 - Findings: C critical, H high, M medium
 - Clean files: N
 
-<next_steps>
+<nextsteps>
 1. Fix null deref in path/file.ts:42
 2. Fix plaintext API key in path/config.ts:8
 3. Fix unsafe any cast in path/helper.ts:15
-</next_steps>
+</nextsteps>
 ```
 
 If you find **nothing** worth flagging: write a single line.
@@ -96,4 +96,4 @@ likely missed, not decisions it explicitly made.
 - `typescript-strict` — for TypeScript type safety rules
 - `api-design` — for API design review patterns
 - `testing` — for test coverage assessment
-- `output-standards` — for standardized `<next_steps>` formatting
+- `output-standards` — for standardized `<nextsteps>` formatting

package/skills/docker-deploy/SKILL.md

@@ -153,4 +153,4 @@ trivy image --exit-code 1 --ignore-unfixed --severity HIGH,CRITICAL wrongstack:$
 - `git-flow` — for tagging releases and managing Docker image versions
 - `node-modern` — for Node.js-specific containerization patterns
 - `observability` — for logging and tracing in containerized environments
-- `output-standards` — for standardized `<next_steps>` formatting
+- `output-standards` — for standardized `<nextsteps>` formatting

package/skills/git-flow/SKILL.md

@@ -145,9 +145,9 @@ git rebase main && git merge --ff-only feature
 2. Commit changes with conventional commit format
 3. Open PR with description linking to issue
 
-<next_steps>
+<nextsteps>
 1. Create a branch fix/session-leak, commit the token refresh fix, and push it
-</next_steps>
+</nextsteps>
 
 Open a PR at GitHub linking to issue #123 with the commit message describing the fix.
 ```
@@ -157,4 +157,4 @@ Open a PR at GitHub linking to issue #123 with the commit message describing the
 - `refactor-planner` — when a refactor involves multiple git-managed changes
 - `multi-agent` — for fleet-wide version audits across packages
 - `bug-hunter` — for spotting bugs at commit time before they reach main
-- `output-standards` — for standardized `<next_steps>` formatting
+- `output-standards` — for standardized `<nextsteps>` formatting

package/skills/mailbox-bridge/SKILL.md

@@ -298,7 +298,7 @@ is 15 s.
   skill that pairs with this one.
 - `node-modern` — for `AbortSignal.timeout` patterns the external agent
   should use when calling these routes.
-- `output-standards` — for the `<next_steps>` shape in the paired
+- `output-standards` — for the `<nextsteps>` shape in the paired
   external skill.
 - `security-scanner` — for confirming the bridge's bearer-token handling
   matches project security conventions.

package/skills/multi-agent/SKILL.md

@@ -126,11 +126,11 @@ When a leader synthesizes results from subagents:
 ### Unified Next Steps
 [Deduplicated and prioritized action items]
 
-<next_steps>
+<nextsteps>
 1. Fix critical issue in <file:line>
 2. Fix high-priority issue in <file:line>
 3. Fix remaining issue in <file:line>
-</next_steps>
+</nextsteps>
 ```
 
 ## Anti-patterns
@@ -151,7 +151,7 @@ Subagents share **nothing** — no memory, no session state, no variable scope.
 - `security-scanner` — parallel security scans
 - `refactor-planner` — parallel module analysis
 - `audit-log` — aggregating multiple session analyses
-- `output-standards` — for standardized `<next_steps>` formatting
+- `output-standards` — for standardized `<nextsteps>` formatting
 
 ---
 

package/skills/node-modern/SKILL.md

@@ -188,4 +188,4 @@ while (true) {
 - `react-modern` — React Server Components with Node.js
 - `bug-hunter` — catching async/await bugs, unhandled rejections
 - `sdd` — for setting up new Node.js features with a spec first
-- `output-standards` — for standardized `<next_steps>` formatting
+- `output-standards` — for standardized `<nextsteps>` formatting

package/skills/observability/SKILL.md

@@ -132,4 +132,4 @@ Every log should include:
 - `bug-hunter` — for finding bugs via error trace patterns
 - `security-scanner` — for ensuring no secrets leak into logs
 - `node-modern` — for async tracing patterns with AbortSignal
-- `output-standards` — for standardized `<next_steps>` formatting
+- `output-standards` — for standardized `<nextsteps>` formatting

package/skills/output-standards/SKILL.md

@@ -15,24 +15,25 @@ extract structured data from agent responses.
 
 ## Rules
 
-1. **Only the leader agent's final message SHOULD include `<next_steps>`** — subagents report findings only. If nothing is pending, omit the tag and say "No pending actions."
-2. **`<next_steps>` is for prompt options only** — every item must be something the user can type into the prompt and submit. If a step is a human-only action (e.g., "open DevTools", "check the browser console"), put it outside the tag as informational text instead.
-3. **Tags must be properly closed** — `<next_steps>...</next_steps>` with exact tag names.
-4. **No markdown inside tags** — plain text only, one item per line.
-5. **Items are prompt inputs** — not imperative instructions. Write what the user would type, not what they should do.
-6. **Items marked `auto="true"` must include input content** — the user can copy and submit it directly.
-7. **Keep concise** — max 5 items unless the task genuinely requires more.
-8. **Skip `<next_steps>` whenever the live `ctx.todos` list still has open items** — any `pending` or `in_progress` todo means the in-flight task list is not done, and surfacing new prompt options would race the todo loop (YOLO+auto could pick the top suggestion and pivot away from the unfinished work; `/next 1` would replace the next todo with an arbitrary prompt). Finish the todo list first, re-arm the tag on the turn where the last todo flips to `completed`. The runtime enforces the same gate, so emitting it mid-task is parsed-and-discarded — the rule exists to keep the output focused, not to override runtime behavior.
+1. **Only the leader agent's final message SHOULD include `<nextsteps>`** — subagents report findings only. If nothing is pending, omit the tag entirely; do not append a loose "next steps" or goodwill-style follow-up line.
+2. **Any suggested next prompt MUST be inside `<nextsteps>...</nextsteps>`** — never emit parseable-looking prose such as "Next steps:", "next suggests", "Suggested next:", or "Let me know if you want..." when you intend `/next` to work.
+3. **`<nextsteps>` is for prompt options only** — every item must be something the user can type into the prompt and submit. If a step is a human-only action (e.g., "open DevTools", "check the browser console"), put it outside the tag as informational text instead.
+4. **Tags must be properly closed** — `<nextsteps>...</nextsteps>` with exact tag names.
+5. **No markdown inside tags** — plain text only, one item per line.
+6. **Items are prompt inputs** — not imperative instructions. Write what the user would type, not what they should do.
+7. **Items marked `auto="true"` must include input content** — the user can copy and submit it directly.
+8. **Keep concise** — max 5 items unless the task genuinely requires more.
+9. **Skip `<nextsteps>` whenever the live `ctx.todos` list still has open items** — any `pending` or `in_progress` todo means the in-flight task list is not done, and surfacing new prompt options would race the todo loop (YOLO+auto could pick the top suggestion and pivot away from the unfinished work; `/next 1` would replace the next todo with an arbitrary prompt). Finish the todo list first, re-arm the tag on the turn where the last todo flips to `completed`. The runtime enforces the same gate, so emitting it mid-task is parsed-and-discarded — the rule exists to keep the output focused, not to override runtime behavior.
 
 ## Output Format
 
 ```
 [... task results ...]
 
-<next_steps>
+<nextsteps>
 1. Prompt option the user can enter — phrased as what to type, not what to do
 2. Another prompt option
-</next_steps>
+</nextsteps>
 
 Informational text for human-only actions (outside the tag, no tag wrapper).
 ```
@@ -41,9 +42,9 @@ Informational text for human-only actions (outside the tag, no tag wrapper).
 
 | Element | Rule | Example |
 |---------|------|---------|
-| Opening tag | `<next_steps>` on its own line | `<next_steps>` |
+| Opening tag | `<nextsteps>` on its own line | `<nextsteps>` |
 | Numbered items | `1. ` prefix, one per line | `1. Fix auth bug in core/session.ts` |
-| Closing tag | `</next_steps>` on its own line | `</next_steps>` |
+| Closing tag | `</nextsteps>` on its own line | `</nextsteps>` |
 | `auto="true"` items | Include the full input content | `1. fix in core/auth.ts:42 auto="true"` |
 
 ### ✅ Correct Examples
@@ -51,11 +52,11 @@ Informational text for human-only actions (outside the tag, no tag wrapper).
 ```
 Bug Hunt complete. Found 3 critical issues.
 
-<next_steps>
+<nextsteps>
 1. Fix the shell injection in packages/cli/src/slash-commands/dev.ts:15
 2. Replace Math.random() with randomUUID() in the affected files
 3. Run the type checker
-</next_steps>
+</nextsteps>
 
 Open browser DevTools → Network tab to verify the WebSocket
 connection is established before testing.
@@ -64,9 +65,9 @@ connection is established before testing.
 ```
 Audit complete. Found bash command timeout pattern in iterations 14–20.
 
-<next_steps>
+<nextsteps>
 1. Run the session tests and the type checker
-</next_steps>
+</nextsteps>
 
 Review iterations 14–20 in the session log to characterize the loop.
 ```
@@ -80,19 +81,19 @@ Task done. Next steps: 1) fix bug 2) run tests
 ```
 
 ```
-<next_steps>
+<nextsteps>
 - Fix the bug in auth.ts  # ❌ Dash, not number
 - Run tests
-</next_steps>
+</nextsteps>
 
 # ❌ Wrong bullet character
 ```
 
 ```
-<next_steps>
+<nextsteps>
 1. **Fix the bug** — use execFile instead  # ❌ Markdown inside tags
 2. Run `pnpm test`
-</next_steps>
+</nextsteps>
 
 # ❌ Markdown formatting not allowed inside tags
 ```
@@ -105,9 +106,9 @@ Next steps:
 ```
 
 ```
-<next_steps>
+<nextsteps>
 1. Open the browser console and check for errors  # ❌ Human-only action, not a prompt
-</next_steps>
+</nextsteps>
 ```
 
 ## `auto="true"` Format
@@ -115,10 +116,10 @@ Next steps:
 Items that should be auto-submitted (the user can copy-paste and send) use `auto="true"`:
 
 ```
-<next_steps>
+<nextsteps>
 1. Run the type checker auto="true"
 2. Fix the shell injection in packages/cli/src/slash-commands/dev.ts:15
-</next_steps>
+</nextsteps>
 ```
 
 The text before `auto="true"` is the exact prompt the user would type. Items without `auto="true"` are suggestions the user can select manually.
@@ -127,8 +128,8 @@ The text before `auto="true"` is the exact prompt the user would type. Items wit
 
 When a **leader agent** synthesizes output from **subagents**, the leader MUST:
 
-1. Collect findings from subagents (they return results, not `<next_steps>`)
-2. Based on findings, produce a unified `<next_steps>` section with prompt options
+1. Collect findings from subagents (they return results, not `<nextsteps>`)
+2. Based on findings, produce a unified `<nextsteps>` section with prompt options
 3. Remove duplicates (dedupe by file path + action)
 4. Re-prioritize if needed (critical > high > medium > low)
 5. Human-only findings (e.g., "check the browser console") go outside the tag
@@ -136,22 +137,22 @@ When a **leader agent** synthesizes output from **subagents**, the leader MUST:
 
 When a **subagent** completes its task, it MUST:
 
-1. **NOT include `<next_steps>`** in its output — report findings only
+1. **NOT include `<nextsteps>`** in its output — report findings only
 2. Report what it found/achieved in a structured, self-contained format
 3. Let the leader decide what next steps follow from the findings
 
 ## Anti-patterns
 
-- **Don't put human-only actions in `<next_steps>`** — those belong outside the tag as plain text
+- **Don't put human-only actions in `<nextsteps>`** — those belong outside the tag as plain text
 - **Don't write imperative instructions** — write what the user would type, not what they should do
-- **Don't use markdown inside `<next_steps>`** — plain text only
+- **Don't use markdown inside `<nextsteps>`** — plain text only
 - **Don't skip the tag when there are prompt options** — the tag enables the `/next` workflow
 - **Don't use dashes or asterisks** — use `1.`, `2.`, `3.` numbering
 - **Don't be vague** — "fix bugs" is useless, "fix auth/session.ts:42" is a valid prompt
 - **Don't exceed 5 items without reason** — if >5, it's probably not a single task
 - **Don't write declarations of intent** — "we should refactor X" is not a prompt; "refactor core/config.ts" is
 - **Don't suggest manual review as a prompt** — "manually check if X is correct" is not a valid LLM prompt; instead put it outside the tag
-- **Don't include `<next_steps>` in subagent output** — subagents report findings, leaders produce next steps
+- **Don't include `<nextsteps>` in subagent output** — subagents report findings, leaders produce next steps
 
 ## Skills in scope
 

package/skills/output-standards/SKILL.save.md

@@ -1,11 +1,11 @@
 # Output Standards — WrongStack (Compact)
 
-Standardizes the format of agent output, particularly the `<next_steps>` section in final messages.
+Standardizes the format of agent output, particularly the `<nextsteps>` section in final messages.
 
 ## Rules
 
-1. Only the leader agent includes `<next_steps>` — subagents report findings only.
-2. Tags must be properly closed — `<next_steps>...</next_steps>`.
+1. Only the leader agent includes `<nextsteps>` — subagents report findings only.
+2. Tags must be properly closed — `<nextsteps>...</nextsteps>`.
 3. No markdown inside tags — plain text only, one action per line.
 4. Use imperative mood — "Fix X", not "Fixed X".
 5. Be specific — mention file paths, tool names, or exact commands.
@@ -15,8 +15,8 @@ Standardizes the format of agent output, particularly the `<next_steps>` section
 ## Format
 
 ```
-<next_steps>
+<nextsteps>
 1. [Priority] Action item with file:line reference
 2. [Priority] Second action item
-</next_steps>
+</nextsteps>
 ```

package/skills/plugin-author/SKILL.md

@@ -347,4 +347,4 @@ For the H1 pattern, extend `tests/plugin-teardown.test.ts` with a
 - `typescript-strict` — for strict TypeScript patterns in plugin code
 - `node-modern` — for ESM imports, AbortSignal, and async patterns
 - `testing` — for vitest patterns and mock API construction
-- `output-standards` — for standardized `<next_steps>` formatting
+- `output-standards` — for standardized `<nextsteps>` formatting

package/skills/prompt-engineering/SKILL.md

@@ -134,4 +134,4 @@ See `skill-creator` skill for the format. Key points:
 - `skill-creator` — for creating new skills (primary — prompt-engineering feeds into skill creation)
 - `typescript-strict` — for TypeScript-specific prompt typing
 - `react-modern` — for React component prompt conventions
-- `output-standards` — for standardized `<next_steps>` formatting
+- `output-standards` — for standardized `<nextsteps>` formatting

package/skills/react-modern/SKILL.md

@@ -209,4 +209,4 @@ const inputRef = useRef<HTMLInputElement>(null);
 - `typescript-strict` — for TypeScript patterns
 - `node-modern` — for React server components with Node.js
 - `bug-hunter` — for React-specific bugs (stale closures, memory leaks)
-- `output-standards` — for standardized `<next_steps>` formatting
+- `output-standards` — for standardized `<nextsteps>` formatting

package/skills/refactor-planner/SKILL.md

@@ -156,11 +156,11 @@ config.ts → logger.ts → path-resolver.ts
 - [ ] No circular deps in `src/core`
 - [ ] `Context` interface < 20 methods
 
-<next_steps>
+<nextsteps>
 1. Extract ToolExecutor interface in core/tool-executor.ts
 2. Decouple SessionStore from Agent in core/session-store.ts
 3. Break circular dep between Config and Logger in core/config.ts
-</next_steps>
+</nextsteps>
 ```
 
 ## Anti-patterns
@@ -176,4 +176,4 @@ config.ts → logger.ts → path-resolver.ts
 - `bug-hunter` — for finding bugs exposed by the refactor
 - `git-flow` — for committing each phase properly
 - `multi-agent` — for parallel analysis of multiple modules
-- `output-standards` — for standardized `<next_steps>` formatting
+- `output-standards` — for standardized `<nextsteps>` formatting

package/skills/research-web/SKILL.md

@@ -340,4 +340,4 @@ Agent: search("TypeScript null check best practices") // NO
 - `security-scanner` — for CVE and vulnerability research
 - `prompt-engineering` — for crafting effective search queries
 - `multi-agent` — for fanning out research to subagents
-- `output-standards` — for standardized `<next_steps>` formatting
+- `output-standards` — for standardized `<nextsteps>` formatting

package/skills/sdd/SKILL.md

@@ -132,4 +132,4 @@ Stage shown in real-time. Pause stops after current iteration completes.
 - `refactor-planner` — when the spec reveals a multi-file refactor
 - `bug-hunter` — when a bugfix spec needs a root cause analysis section
 - `multi-agent` — for executing parallel task groups
-- `output-standards` — for standardized `<next_steps>` formatting
+- `output-standards` — for standardized `<nextsteps>` formatting

package/skills/security-scanner/SKILL.md

@@ -157,11 +157,11 @@ element.textContent = userInput;
 - [ ] Use parameterized queries in `src/db/` files
 - [ ] Add rate limiting to `src/api/` routes
 
-<next_steps>
+<nextsteps>
 1. Fix the hardcoded API key in src/config.ts
 2. Fix the shell injection in src/auth/login.ts
 3. Fix the missing rate limiting in src/api/routes.ts
-</next_steps>
+</nextsteps>
 ```
 
 ## Skills in scope
@@ -169,4 +169,4 @@ element.textContent = userInput;
 - `bug-hunter` — for general code quality bugs found during security scan
 - `audit-log` — for dependency version audit trails
 - `git-flow` — for committing security patches properly
-- `output-standards` — for standardized `<next_steps>` formatting
+- `output-standards` — for standardized `<nextsteps>` formatting

package/skills/skill-creator/SKILL.md

@@ -164,4 +164,4 @@ Before writing the file, verify:
 
 - `prompt-engineering` — for crafting the skill description and prompt text
 - `git-flow` — for committing the new skill file
-- `output-standards` — for standardized `<next_steps>` formatting
+- `output-standards` — for standardized `<nextsteps>` formatting

package/skills/tech-stack/SKILL.md

@@ -104,9 +104,9 @@ When APPROVED:
 **Install**: `<ecosystem install command>`
 **Note**: <any caveats about the version, semver range, or compatibility>
 
-<next_steps>
+<nextsteps>
 1. Add <package>@<version> to the project auto="true"
-</next_steps>
+</nextsteps>
 ```
 
 ## Skills in scope
@@ -116,4 +116,4 @@ When APPROVED:
 - `typescript-strict` — for TypeScript version alignment
 - `security-scanner` — for packages with known CVEs
 - `docker-deploy` — for base image version pinning
-- `output-standards` — for standardized `<next_steps>` formatting
+- `output-standards` — for standardized `<nextsteps>` formatting

package/skills/testing/SKILL.md

@@ -168,4 +168,4 @@ coverageThreshold: {
 - `typescript-strict` — for type-safe test assertions
 - `node-modern` — for async/test patterns with AbortSignal
 - `git-flow` — for committing tests with the code they test
-- `output-standards` — for standardized `<next_steps>` formatting
+- `output-standards` — for standardized `<nextsteps>` formatting

package/skills/typescript-strict/SKILL.md

@@ -237,4 +237,4 @@ console.log(name!.toUpperCase());
 - `node-modern` — for TypeScript + ESM patterns
 - `react-modern` — for React + TypeScript patterns
 - `bug-hunter` — for type-related bugs like unsafe casts
-- `output-standards` — for standardized `<next_steps>` formatting
+- `output-standards` — for standardized `<nextsteps>` formatting