lazyclaude-ai 0.2.0 → 0.2.1

package/CHANGELOG.md

@@ -1,5 +1,14 @@
 # Changelog
 
+## 0.2.1 - 2026-06-04
+
+- Add a dedicated `/dynamic-workflow` route for Dynamic workflow bootstrap,
+  native `/goal` fallback guidance, and Claude Code subagent delegation.
+- Add `lazyclaude-ai workflow-check --json` so operators can verify goal,
+  Dynamic workflow, hook route, and subagent delegation readiness before full QA.
+- Fix the right-pane `test/` local-session ignore pattern so ad hoc Claude Code
+  session artifacts stay out of git and package payloads.
+
 ## 0.2.0 - 2026-06-03
 
 - Align the package and Claude plugin manifests to `lazyclaude-ai@0.2.0` for

package/README.md

@@ -9,7 +9,7 @@
 </p>
 <p align="center">
   <img src="https://img.shields.io/badge/npm-lazyclaude--ai-cb3837" />
-  <img src="https://img.shields.io/badge/version-0.2.0-2ea44f" />
+  <img src="https://img.shields.io/badge/version-0.2.1-2ea44f" />
   <img src="https://img.shields.io/badge/Claude%20Code-plugin-blueviolet" />
   <img src="https://img.shields.io/badge/license-MIT-blue" />
 </p>
@@ -22,12 +22,12 @@
 > `lazyclaude@lazyclaude-ai`, so normal `claude` launches can load the
 > LazyClaude skills and hooks without a long `--plugin-dir` command.
 
-This checkout is prepared as `lazyclaude-ai@0.2.0` for personal install
+This checkout is prepared as `lazyclaude-ai@0.2.1` for personal install
 convenience. The repo can remain quiet; preparing npm package metadata here does
 not imply public repo promotion, marketplace publication, or advertisement.
-Future package releases still require explicit user approval. The v0.2.0
-workflow parity materials describe LazyClaude in its own terms and do not claim
-that npm publication has completed.
+Future package releases still require explicit user approval. The v0.2.1
+release materials preserve the v0.2.0 workflow parity work, describe
+LazyClaude in its own terms, and do not claim that npm publication has completed.
 
 ## Features
 
@@ -37,6 +37,9 @@ that npm publication has completed.
   turn broad intent into a spec before planning or implementation
 - **v0.2.0 workflow parity** - adds `review-work` 5-lane review discipline and
   ultragoal runtime docs without claiming a package publication has completed
+- **v0.2.1 dynamic workflow readiness** - adds `/dynamic-workflow` and
+  `workflow-check --json` so goal, Dynamic workflow, and subagent delegation
+  readiness can be checked before full QA
 - **5-lane review** - `/review-work` checks goal/constraint verification,
   hands-on QA execution, code quality, security, and local-first context mining
 - **Native goal guidance** - ULW context points Claude toward `/goal` or
@@ -46,8 +49,8 @@ that npm publication has completed.
   criteria, evidence, checkpoints, steering, and review blockers under
   `.omo/ultragoal/`
 - **Dynamic workflow/worktree guidance** - large or parallel tasks are steered
-  toward Claude Code Dynamic workflow orchestration and Dynamic worktree
-  isolation
+  toward Claude Code Dynamic workflow orchestration, subagent delegation, and
+  Dynamic worktree isolation
 - **Claude skills** - a richer LazyClaude-owned corpus: `programming`,
   `debugging`, `refactor`, `ai-slop-remover`, `remove-ai-slops`, `review-work`,
   `frontend-ui-ux`, `comment-checker`, `rules`, `lsp`, `ultragoal`,
@@ -88,7 +91,7 @@ install command works:
 
 ```bash
 cd /tmp
-npx --yes lazyclaude-ai@0.2.0 install
+npx --yes lazyclaude-ai@0.2.1 install
 ```
 
 Validate the installed plugin:
@@ -101,7 +104,7 @@ The installer also sets Claude Code's `statusLine` command to the packaged
 LazyClaude HUD. A typical no-color render starts like:
 
 ```text
-[💤LAZYCLAUDE v0.2.0] | O4.8 │ ctx [▎░░] 9%/1000k │ 5h [▏░] 4% ↻2h15m │ 1w [▊░] 35% ↻3d6h │ git main +3 ✓
+[💤LAZYCLAUDE v0.2.1] | O4.8 │ ctx [▎░░] 9%/1000k │ 5h [▏░] 4% ↻2h15m │ 1w [▊░] 35% ↻3d6h │ git main +3 ✓
 ```
 
 The `↻` suffix is a compact rate-limit reset countdown. It is separated from
@@ -174,6 +177,8 @@ $ulw-loop <what you want executed with evidence>
 /ulw-loop <what you want executed with evidence>
 $deep-interview <what needs clarification>
 /deep-interview <what needs clarification>
+$dynamic-workflow <parallel or delegated objective>
+/dynamic-workflow <parallel or delegated objective>
 $review-work <scope to review>
 /review-work <scope to review>
 $ultragoal <goal operation>
@@ -206,6 +211,18 @@ Code's available orchestration surfaces: when `Workflow` is exposed, call the
 `EnterWorktree`. If only the CLI surface is available for a fresh isolated lane,
 use `claude --worktree <short-name> --tmux`.
 
+For v0.2.1 dynamic workflow readiness, `/dynamic-workflow` is the consolidated
+bootstrap route for broad delegated work. It keeps `/goal` user-controlled,
+checks model-facing goal tools when exposed, asks for an exact fallback
+`/goal <completion condition>` when needed, and maps subagent delegation to
+`prometheus-planner`, `boulder-executor`, `oracle-verifier`, `qa-runner`,
+`quality-reviewer`, and `librarian-researcher`. Run the package diagnostic from
+the checkout or an installed package before full QA:
+
+```bash
+lazyclaude-ai workflow-check --json
+```
+
 For v0.2.0 workflow parity, `review-work` is the dedicated review route. It is a
 5-lane review: goal/constraint verification, hands-on QA execution, code
 quality, security, and local-first context mining. The lanes bind to
@@ -236,6 +253,7 @@ namespaced commands when you want explicit LazyClaude skill activation:
 
 ```text
 /lazyclaude:ulw-loop <what you want executed with evidence>
+/lazyclaude:dynamic-workflow <parallel or delegated objective>
 /lazyclaude:ulw-plan <what you want planned>
 /lazyclaude:deep-interview <what needs clarification>
 /lazyclaude:review-work <scope to review>

package/README_ko-KR.md

@@ -9,7 +9,7 @@
 </p>
 <p align="center">
   <img src="https://img.shields.io/badge/npm-lazyclaude--ai-cb3837" />
-  <img src="https://img.shields.io/badge/version-0.2.0-2ea44f" />
+  <img src="https://img.shields.io/badge/version-0.2.1-2ea44f" />
   <img src="https://img.shields.io/badge/Claude%20Code-plugin-blueviolet" />
   <img src="https://img.shields.io/badge/license-MIT-blue" />
 </p>
@@ -26,12 +26,13 @@
 > 설치되므로, 매번 긴 `--plugin-dir` 없이 일반 `claude` 실행에서
 > LazyClaude skill과 hook을 불러올 수 있습니다.
 
-현재 checkout은 `lazyclaude-ai@0.2.0` 배포 준비용으로 정리되어 있습니다. 목적은
+현재 checkout은 `lazyclaude-ai@0.2.1` 배포 준비용으로 정리되어 있습니다. 목적은
 다른 PC에서도 빠르게 설치하기 위한 개인용 package metadata를 갖추는 것입니다.
 npm package metadata를 준비했다고 해서 홍보, 공개 저장소 운영, Claude
 marketplace 등록을 의미하지는 않습니다. 새 버전 배포는 항상 별도의 명시적
-승인 후에 진행합니다. v0.2.0 workflow parity material은 LazyClaude 자체의
-표현으로 정리되어 있으며, npm publish가 완료됐다고 주장하지 않습니다.
+승인 후에 진행합니다. v0.2.1 release material은 v0.2.0 workflow parity work를
+보존하면서 LazyClaude 자체의 표현으로 정리되어 있으며, npm publish가 완료됐다고
+주장하지 않습니다.
 
 ## 기능
 
@@ -41,6 +42,9 @@ marketplace 등록을 의미하지는 않습니다. 새 버전 배포는 항상
   모호한 의도를 먼저 spec으로 정리한 뒤 계획/구현으로 넘김
 - **v0.2.0 workflow parity** - package publish가 끝났다고 말하지 않으면서
   `review-work` 5-lane review discipline과 ultragoal runtime 문서를 추가
+- **v0.2.1 dynamic workflow readiness** - `/dynamic-workflow`와
+  `workflow-check --json`으로 goal, Dynamic workflow, subagent delegation
+  readiness를 full QA 전에 확인
 - **5-lane review** - `/review-work`가 goal/constraint verification,
   hands-on QA execution, code quality, security, local-first context mining을
   한 번에 점검
@@ -51,7 +55,7 @@ marketplace 등록을 의미하지는 않습니다. 새 버전 배포는 항상
   criteria, evidence, checkpoint, steering, review blocker를 `.omo/ultragoal/`
   아래에 기록
 - **Dynamic workflow/worktree guidance** - 크거나 병렬적인 작업은 Claude
-  Code Dynamic workflow와 Dynamic worktree 격리 쪽으로 유도
+  Code Dynamic workflow, subagent delegation, Dynamic worktree 격리 쪽으로 유도
 - **Claude skills** - LazyClaude 스타일을 더 풍부하게 옮긴 corpus:
   `programming`, `debugging`, `refactor`, `ai-slop-remover`, `remove-ai-slops`,
   `review-work`, `frontend-ui-ux`, `comment-checker`, `rules`, `lsp`,
@@ -93,7 +97,7 @@ checkout을 먼저 해석해서 `sh: lazyclaude-ai: command not found`로 실패
 
 ```bash
 cd /tmp
-npx --yes lazyclaude-ai@0.2.0 install
+npx --yes lazyclaude-ai@0.2.1 install
 ```
 
 설치 상태를 확인합니다.
@@ -106,7 +110,7 @@ installer는 Claude Code의 `statusLine` command도 packaged LazyClaude HUD로
 설정합니다. 색상을 제거한 예시는 다음처럼 시작합니다.
 
 ```text
-[💤LAZYCLAUDE v0.2.0] | O4.8 │ ctx [▎░░] 9%/1000k │ 5h [▏░] 4% ↻2h15m │ 1w [▊░] 35% ↻3d6h │ git main +3 ✓
+[💤LAZYCLAUDE v0.2.1] | O4.8 │ ctx [▎░░] 9%/1000k │ 5h [▏░] 4% ↻2h15m │ 1w [▊░] 35% ↻3d6h │ git main +3 ✓
 ```
 
 `↻` 표시는 rate-limit reset까지 남은 시간을 짧게 보여주는 countdown입니다.
@@ -178,6 +182,8 @@ $ulw-loop <증거 기반으로 실행할 작업>
 /ulw-loop <증거 기반으로 실행할 작업>
 $deep-interview <명확화가 필요한 작업>
 /deep-interview <명확화가 필요한 작업>
+$dynamic-workflow <병렬 또는 위임할 목표>
+/dynamic-workflow <병렬 또는 위임할 목표>
 $review-work <검토할 범위>
 /review-work <검토할 범위>
 $ultragoal <goal operation>
@@ -209,6 +215,18 @@ goal이 없을 때만 `create_goal`을 호출하며, `update_goal`은 검증 완
 model-facing worktree를 필요로 하면 `EnterWorktree`를 사용합니다. CLI surface만
 가능한 새 격리 lane에서는 `claude --worktree <short-name> --tmux`를 사용합니다.
 
+v0.2.1 dynamic workflow readiness에서 `/dynamic-workflow`는 넓은 위임 작업을
+위한 통합 bootstrap route입니다. `/goal`은 user-controlled 상태로 두고,
+model-facing goal tools가 노출되면 확인하며, 필요하면 정확한 fallback
+`/goal <completion condition>`만 제안합니다. subagent delegation은
+`prometheus-planner`, `boulder-executor`, `oracle-verifier`, `qa-runner`,
+`quality-reviewer`, `librarian-researcher`에 매핑됩니다. Full QA 전에는 다음
+package diagnostic을 실행합니다.
+
+```bash
+lazyclaude-ai workflow-check --json
+```
+
 v0.2.0 workflow parity에서 `review-work`는 전용 review route입니다. 5-lane
 review는 goal/constraint verification, hands-on QA execution, code quality,
 security, local-first context mining을 포함합니다. 각 lane은
@@ -240,6 +258,7 @@ command를 사용합니다.
 
 ```text
 /lazyclaude:ulw-loop <증거 기반으로 실행할 작업>
+/lazyclaude:dynamic-workflow <병렬 또는 위임할 목표>
 /lazyclaude:ulw-plan <계획이 필요한 작업>
 /lazyclaude:deep-interview <명확화가 필요한 작업>
 /lazyclaude:review-work <검토할 범위>

package/RELEASE_CHECKLIST.md

@@ -1,15 +1,14 @@
 # LazyClaude Release Checklist
 
-Status: `lazyclaude-ai@0.2.0` is the current release candidate for deep workflow parity.
-`package.json` is aligned to `0.2.0`, and
-`plugins/lazyclaude/.claude-plugin/plugin.json` is aligned to `0.2.0`.
+Status: `lazyclaude-ai@0.2.1` is the current release candidate for dynamic workflow readiness.
+`package.json` is aligned to `0.2.1`, and
+`plugins/lazyclaude/.claude-plugin/plugin.json` is aligned to `0.2.1`.
 
-This release carries the v0.2.0 workflow parity surfaces: `review-work` 5-lane
-review, ultragoal runtime state, local-first context mining, Manual-QA channels,
-cleanup receipts, and explicit publish boundary guidance. The package retains
-the recent install, hook, and HUD work from `0.1.12`, `0.1.13`, `0.1.14`,
-`0.1.15`, `0.1.16`, `0.1.17`, and `0.1.18`, while `0.2.0` is the next publishable target
-when explicitly approved.
+This release carries the v0.2.1 dynamic workflow readiness surfaces:
+`/dynamic-workflow`, `workflow-check --json`, native `/goal` fallback guidance,
+subagent delegation mapping, and the v0.2.0 `review-work` / `ultragoal`
+workflow parity surfaces, including the ultragoal runtime. It is the
+next publishable target when explicitly approved.
 
 DO NOT publish a new version of LazyClaude, run `npm publish`, push release
 tags, or add a remote Claude Code marketplace entry without explicit user
@@ -18,6 +17,13 @@ approval.
 This release path is for personal install convenience, not advertisement,
 public repo promotion, or a public launch campaign.
 
+Historical baseline anchors still covered by this checklist: `0.1.12` was the
+publish-recovery baseline, `0.1.13` added ULW command trigger guardrails,
+`0.1.14` added command-name HUD display, `0.1.15` introduced HUD brand color
+selection, `0.1.16` added rate-limit reset countdown and deep-interview install
+guidance, and `0.1.18` covered compact HUD bars and broader brand accent
+behavior.
+
 ## Verified Locally
 
 - `npm test`
@@ -33,18 +39,21 @@ Use this track when testing from the current checkout:
 1. Run `npm test`.
 2. Run `npm run validate:plugin`.
 3. Run `npm run qa:tmux`.
-4. Run `node bin/lazyclaude-ai.js ultragoal --help`.
-5. Start Claude Code with `claude --plugin-dir ./plugins/lazyclaude`.
+4. Run `node bin/lazyclaude-ai.js workflow-check --json`.
+5. Run `node bin/lazyclaude-ai.js ultragoal --help`.
+6. Start Claude Code with `claude --plugin-dir ./plugins/lazyclaude`.
 
 No npm publication is required for this track.
 
-## v0.2.0 Workflow Parity Gates
+## v0.2.1 Dynamic Workflow Gates
 
 Before requesting publication approval, confirm these artifacts from the current
 checkout:
 
-- `package.json` version is `0.2.0`.
-- `plugins/lazyclaude/.claude-plugin/plugin.json` version is `0.2.0`.
+- `package.json` version is `0.2.1`.
+- `plugins/lazyclaude/.claude-plugin/plugin.json` version is `0.2.1`.
+- `plugins/lazyclaude/commands/dynamic-workflow.md` documents subagent delegation.
+- `node bin/lazyclaude-ai.js workflow-check --json` reports `status: pass`.
 - `plugins/lazyclaude/commands/review-work.md` documents the 5-lane review.
 - `plugins/lazyclaude/commands/ultragoal.md` documents durable goal state.
 - `plugins/lazyclaude/lib/ultragoal/` ships the runtime CLI/state modules.

package/bin/lazyclaude-ai.js

@@ -16,12 +16,13 @@ import { createInterface } from "node:readline/promises";
 import { fileURLToPath } from "node:url";
 import { HUD_ACCENT_THEMES, normalizeHudAccent, themeForAccent } from "../plugins/lazyclaude/lib/hud-accent-palette.mjs";
 import { runUltragoalCli } from "../plugins/lazyclaude/lib/ultragoal/cli.mjs";
+import { runWorkflowCheckCli } from "../plugins/lazyclaude/lib/workflow-check.mjs";
 
 const root = resolve(dirname(fileURLToPath(import.meta.url)), "..");
 const packageJson = JSON.parse(readFileSync(join(root, "package.json"), "utf8"));
 const version = packageJson.version;
 
-const usage = `Usage: lazyclaude-ai [--dry-run] <install|doctor|path|run|update|uninstall|ultragoal> [...args]
+const usage = `Usage: lazyclaude-ai [--dry-run] <install|doctor|path|run|update|uninstall|ultragoal|workflow-check> [...args]
        lazyclaude-ai --version
 
 Commands:
@@ -30,6 +31,7 @@ Commands:
   path          Print the installed Claude plugin path.
   run -- ...    Run Claude Code after the global plugin install.
   ultragoal     Manage ultragoal runtime state and evidence.
+  workflow-check Verify Dynamic workflow, /goal, and subagent delegation readiness.
   update        Reinstall this package version and refresh the Claude plugin registry.
   uninstall     Remove LazyClaude-managed install state.
 `;
@@ -621,6 +623,9 @@ const main = async () => {
     case "ultragoal":
       process.exit(runUltragoalCli(parsed.rest));
       break;
+    case "workflow-check":
+      process.exit(runWorkflowCheckCli(root, version, parsed.rest));
+      break;
     case "uninstall":
       uninstall(parsed);
       break;

package/docs/agents.md

@@ -32,6 +32,23 @@ The aggregate verdict is PASS, FAIL, or NEEDS-CONTEXT. Broad review work may
 use Dynamic workflow when Claude Code exposes it; isolated edits can use
 `claude --worktree <short-name> --tmux` when a separate checkout is required.
 
+## Dynamic Workflow Delegation
+
+The v0.2.1 `/dynamic-workflow` route makes the delegation map explicit for
+Claude Code Dynamic workflow lanes and subagent spawning:
+
+| Delegation lane | Agent | Evidence boundary |
+| --- | --- | --- |
+| plan and dependency order | `prometheus-planner` | Read-only plan with files, tests, Manual-QA channel, and cleanup. |
+| implementation | `boulder-executor` | Smallest checked code change with RED -> GREEN evidence. |
+| acceptance verification | `oracle-verifier` | Goal, criteria, and artifact checks before completion. |
+| manual QA | `qa-runner` | tmux/browser/HTTP/computer-use artifact plus cleanup receipt. |
+| code/security review | `quality-reviewer` | Findings-first review with concrete file references. |
+| local-first context mining | `librarian-researcher` | Repo/docs/history search before external sources. |
+
+`lazyclaude-ai workflow-check --json` verifies that this route, goal guidance,
+Dynamic workflow guidance, and subagent delegation surface are present.
+
 ## Local Use
 
 Load the plugin from this checkout:

package/docs/hooks.md

@@ -28,6 +28,9 @@ $ulw-loop
 $deep-interview
 /deep-interview
 /lazyclaude:deep-interview
+$dynamic-workflow
+/dynamic-workflow
+/lazyclaude:dynamic-workflow
 $review-work
 /review-work
 /lazyclaude:review-work
@@ -66,6 +69,13 @@ cleanup. If isolated edits need a model-facing worktree lane, use
 `EnterWorktree`; when only the CLI surface is available, the actionable launch
 form is `claude --worktree <short-name> --tmux`.
 
+`/dynamic-workflow` and `$dynamic-workflow` are the v0.2.1 consolidated route
+for that behavior. They load `/lazyclaude:dynamic-workflow` / `Skill(ulw-loop)`,
+then map subagent delegation to `prometheus-planner`, `boulder-executor`,
+`oracle-verifier`, `qa-runner`, `quality-reviewer`, and `librarian-researcher`.
+Run `lazyclaude-ai workflow-check --json` to verify the hook route, goal
+guidance, Dynamic workflow guidance, and subagent delegation text before full QA.
+
 Plain `ulw` therefore activates hook context, not a visible Skill tool call.
 For a visible LazyClaude command/skill invocation, use the namespaced Claude
 Code commands. The shorter slash aliases above are also recognized by the prompt
@@ -74,6 +84,7 @@ hook so they route to the same discipline instead of falling through to plain
 
 ```text
 /lazyclaude:ulw-loop <goal>
+/lazyclaude:dynamic-workflow <parallel or delegated objective>
 /lazyclaude:ulw-plan <planning brief>
 /lazyclaude:start-work plans/lazyclaude-retrofit.md
 ```

package/docs/migration.md

@@ -15,6 +15,7 @@ conservative local fallback where it does not.
 | Durable goal runtime | Package CLI plus local state | `ultragoal` writes criteria, evidence, checkpoints, steering, and blockers under `.omo/ultragoal/` |
 | Goal-tool guidance | Claude Code native goal surface | `/goal` when user-selected, or model-facing `get_goal`, `create_goal`, and verified-final `update_goal` guidance when exposed |
 | Parallel orchestration | Claude Code Dynamic workflow and Dynamic worktree surfaces | Call `Workflow` for broad independent work when exposed; use `EnterWorktree` or the CLI worktree path for risky or parallel edits |
+| Dynamic workflow readiness | Claude Code command plus package diagnostic | `/dynamic-workflow` and `workflow-check --json` verify goal, Dynamic workflow, and subagent delegation surfaces |
 | Hooks | Claude Code hooks | `plugins/lazyclaude/hooks/hooks.json` |
 | MCP helpers | Claude Code plugin MCP config | `plugins/lazyclaude/.mcp.json` |
 | LSP integration | Claude Code plugin LSP config | `plugins/lazyclaude/.lsp.json` |
@@ -72,6 +73,17 @@ execution, bind each lane to criteria and evidence, and use `EnterWorktree` for
 isolated model-facing worktree lanes. When only the CLI surface is available,
 the concrete isolated-lane launch form is `claude --worktree <short-name> --tmux`.
 
+For v0.2.1, `/dynamic-workflow`, `$dynamic-workflow`, and
+`/lazyclaude:dynamic-workflow` consolidate that behavior into one route. The
+route keeps `/goal` user-controlled, calls model-facing goal tools only when
+exposed, and maps subagent delegation to `prometheus-planner`,
+`boulder-executor`, `oracle-verifier`, `qa-runner`, `quality-reviewer`, and
+`librarian-researcher`. Operators can verify availability with:
+
+```bash
+lazyclaude-ai workflow-check --json
+```
+
 ## v0.2.0 Review And Ultragoal Parity
 
 The v0.2.0 workflow parity surface is local-first and evidence-bound. It does

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "lazyclaude-ai",
-  "version": "0.2.0",
+  "version": "0.2.1",
   "description": "Claude Code-native workflow distribution.",
   "type": "module",
   "bin": {

package/plugins/lazyclaude/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "lazyclaude",
   "description": "Claude Code-native workflow plugin.",
-  "version": "0.2.0",
+  "version": "0.2.1",
   "author": {
     "name": "LazyClaude contributors"
   },

package/plugins/lazyclaude/bin/lazyclaude-hook.js

@@ -39,6 +39,7 @@ const writeContext = (additionalContext, systemMessage) => {
 
 const workflowTriggers = [
   { pattern: /(?:^|\s)(?:\$|\/(?:lazyclaude:)?)deep-interview(?=$|[^\w-])/u, command: "/lazyclaude:deep-interview", skill: "Skill(deep-interview)", discipline: "deep-interview" },
+  { pattern: /(?:^|\s)(?:\$|\/(?:lazyclaude:)?)dynamic-workflow(?=$|[^\w-])/u, command: "/lazyclaude:dynamic-workflow", skill: "Skill(ulw-loop)", discipline: "dynamic-workflow" },
   { pattern: /(?:^|\s)(?:\$|\/(?:lazyclaude:)?)ulw-plan(?=$|[^\w-])/u, command: "/lazyclaude:ulw-plan", skill: "Skill(ulw-plan)", discipline: "ulw-plan" },
   { pattern: /(?:^|\s)(?:\$|\/(?:lazyclaude:)?)ulw-loop(?=$|[^\w-])/u, command: "/lazyclaude:ulw-loop", skill: "Skill(ulw-loop)", discipline: "ulw-loop" },
   { pattern: /(?:^|\s)(?:\$|\/(?:lazyclaude:)?)start-work(?=$|[^\w-])/u, command: "/lazyclaude:start-work", skill: "Skill(start-work)", discipline: "start-work" },
@@ -63,6 +64,7 @@ const ultraworkContext = ({ command, skill, discipline }) => [
   "Do not auto-type or inject the user's slash commands; treat /goal as Claude Code's native goal surface, not as prompt text for this hook to send.",
   "Dynamic workflow integration: when Claude Code exposes the Workflow tool and the task is broad, risky, parallel, or long-running, call the Workflow tool before serial execution and bind each lane to explicit criteria, artifacts, and cleanup receipts.",
   "Dynamic worktree integration: when Claude Code exposes EnterWorktree and isolated edits are needed, use EnterWorktree for the selected lane; otherwise use or recommend claude --worktree <short-name> --tmux. Never mutate unrelated user state.",
+  "Subagent delegation: route planning to prometheus-planner, implementation to boulder-executor, verification to oracle-verifier, hands-on QA to qa-runner, code/security review to quality-reviewer, and local-first research to librarian-researcher when Claude Code subagents or Dynamic workflow lanes are available.",
 ].join(" ");
 
 const input = readInput();

package/plugins/lazyclaude/commands/dynamic-workflow.md

@@ -0,0 +1,32 @@
+---
+description: Verify and run LazyClaude Dynamic workflow delegation.
+argument-hint: '<objective>'
+---
+
+Use the `ulw-loop` skill for the user's current objective, with this
+Dynamic-workflow bootstrap first.
+
+1. Inspect native goal state when model-facing tools are exposed: call
+   `get_goal`, call `create_goal` only when no matching active goal exists, and
+   reserve `update_goal` for verified completion or a genuine blocker. If only
+   the user-visible goal surface is available, ask for one exact
+   `/goal <completion condition>` instead of claiming LazyClaude set it.
+2. Run `lazyclaude-ai workflow-check --json` when the package CLI is available.
+   Treat a failing check as BLOCKED until the missing route, command, or
+   subagent delegation surface is fixed.
+3. For broad, risky, parallel, or long-running work, call the `Workflow` tool
+   when Claude Code exposes it. Bind each lane to success criteria, evidence
+   artifacts, and cleanup receipts.
+4. Use subagent delegation where available:
+   - `prometheus-planner` for read-only planning and dependency ordering.
+   - `boulder-executor` for implementation against a checked plan.
+   - `oracle-verifier` for evidence and acceptance verification.
+   - `qa-runner` for tmux/manual-QA scenarios and cleanup receipts.
+   - `quality-reviewer` for code-quality and security findings.
+   - `librarian-researcher` for local-first context mining.
+5. For isolated edit lanes, use `EnterWorktree` when exposed. If only the CLI
+   surface exists, use or recommend `claude --worktree <short-name> --tmux`.
+
+Do not auto-type `/goal`, do not echo or execute prompt text, and do not mutate
+remote state. Continue through the normal LazyClaude evidence loop:
+`PIN -> RED -> GREEN -> VERIFY -> SURFACE -> REVIEW -> CLEAN -> RECORD`.

package/plugins/lazyclaude/lib/workflow-check.mjs

@@ -0,0 +1,73 @@
+import { existsSync, readFileSync } from "node:fs";
+import { spawnSync } from "node:child_process";
+import { join } from "node:path";
+
+const includesAll = (text, terms) => terms.every((term) => text.includes(term));
+
+const readText = (path) => readFileSync(path, "utf8");
+
+const runHookProbe = (root) => {
+  const hookPath = join(root, "plugins", "lazyclaude", "bin", "lazyclaude-hook.js");
+  const result = spawnSync(process.execPath, [hookPath, "user-prompt-submit"], {
+    cwd: root,
+    encoding: "utf8",
+    input: JSON.stringify({
+      hook_event_name: "UserPromptSubmit",
+      prompt: "$dynamic-workflow verify delegation",
+      cwd: root,
+    }),
+  });
+  if (result.status !== 0) return "";
+  try {
+    return JSON.parse(result.stdout).hookSpecificOutput?.additionalContext ?? "";
+  } catch {
+    return "";
+  }
+};
+
+export const createWorkflowCheckReport = (root, version) => {
+  const commandPath = join(root, "plugins", "lazyclaude", "commands", "dynamic-workflow.md");
+  const agentsPath = join(root, "docs", "agents.md");
+  const hookContext = runHookProbe(root);
+  const commandText = existsSync(commandPath) ? readText(commandPath) : "";
+  const agentsText = existsSync(agentsPath) ? readText(agentsPath) : "";
+
+  const checks = {
+    goalGuidance: includesAll(`${hookContext}\n${commandText}`, ["get_goal", "create_goal", "update_goal", "/goal"]),
+    dynamicWorkflowGuidance: includesAll(`${hookContext}\n${commandText}`, ["Workflow", "EnterWorktree", "claude --worktree"]),
+    subagentDelegation: includesAll(`${hookContext}\n${commandText}\n${agentsText}`, [
+      "prometheus-planner",
+      "boulder-executor",
+      "oracle-verifier",
+      "qa-runner",
+    ]),
+    dynamicWorkflowCommand: existsSync(commandPath),
+    hookRoute: hookContext.includes("/lazyclaude:dynamic-workflow"),
+  };
+
+  const missing = Object.entries(checks)
+    .filter(([, passed]) => !passed)
+    .map(([name]) => name);
+
+  return {
+    status: missing.length === 0 ? "pass" : "fail",
+    version,
+    checks,
+    missing,
+  };
+};
+
+export const runWorkflowCheckCli = (root, version, args, io = { stdout: process.stdout, stderr: process.stderr }) => {
+  const outputJson = args.includes("--json");
+  const report = createWorkflowCheckReport(root, version);
+  if (outputJson) {
+    io.stdout.write(`${JSON.stringify(report, null, 2)}\n`);
+  } else {
+    io.stdout.write(`WORKFLOW_CHECK_${report.status.toUpperCase()}\n`);
+    for (const [name, passed] of Object.entries(report.checks)) {
+      io.stdout.write(`${name}=${passed ? "pass" : "fail"}\n`);
+    }
+    if (report.missing.length) io.stdout.write(`missing=${report.missing.join(",")}\n`);
+  }
+  return report.status === "pass" ? 0 : 1;
+};