lazyclaude-ai 0.1.17 → 0.2.0

package/CHANGELOG.md

@@ -1,5 +1,27 @@
 # Changelog
 
+## 0.2.0 - 2026-06-03
+
+- Align the package and Claude plugin manifests to `lazyclaude-ai@0.2.0` for
+  the workflow parity release candidate.
+- Add the `review-work` 5-lane review route and document its goal/constraint
+  verification, hands-on QA execution, code quality, security, and local-first
+  context mining lanes.
+- Add the `ultragoal` CLI/runtime surface for durable criteria, evidence,
+  checkpoints, steering, and review blocker records under `.omo/ultragoal/`.
+- Keep the release boundary explicit: this version is prepared for verification
+  and publication approval, but no npm publish or marketplace publication is claimed
+  here.
+
+## 0.1.18 - 2026-06-02
+
+- Shorten the HUD into compact HUD bars with a three-cell context gauge and
+  two-cell rate-limit gauges for tighter Claude Code status-line space.
+- Replace muted installer choices with vivid HUD color choices and shared
+  mini-HUD previews for all ten brand accent themes.
+- Apply the selected accent as a broader brand accent across separators,
+  labels, brackets, reset text, and git metadata.
+
 ## 0.1.17 - 2026-06-02
 
 - Render a dense bracketed context bar in the HUD, for example
@@ -65,7 +87,7 @@
   checks without requiring install state.
 - Align package, plugin, README, HUD examples, release checklist, and cover image
   generation to `lazyclaude-ai@0.1.11`.
-- Refresh source-origin-free README, reference metadata, and workflow
+- Refresh README, reference metadata, and workflow
   compatibility audit wording.
 - Deepen trigger-specific hook routing for `$ulw-plan`, `$ulw-loop`, and
   `$start-work`, with safer post-edit diagnostic guidance.

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-0.1.17-2ea44f" />
+  <img src="https://img.shields.io/badge/version-0.2.0-2ea44f" />
   <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@0.1.17` for personal install
-convenience. The repo can remain private and quiet; publishing to npm here does
+This checkout is prepared as `lazyclaude-ai@0.2.0` 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 v0.1.17 release materials are source-origin-free and describe LazyClaude in
-its own terms.
+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.
 
 ## Features
 
@@ -35,9 +35,16 @@ its own terms.
 - **ULW prompt hooks** - type `ulw`, `ultrawork`, `$ulw-plan`, or `$ulw-loop`
 - **Deep interview mode** - type `/deep-interview` or `$deep-interview` to
   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
+- **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
   model-facing `get_goal`, `create_goal`, and delayed `update_goal` when those
   surfaces exist, and gives a clear fallback when goal tools are unavailable
+- **Ultragoal CLI/state** - `plugins/lazyclaude/lib/ultragoal/` records durable
+  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
@@ -53,8 +60,9 @@ its own terms.
 - **MCP and LSP helpers** - plugin-local stdio MCP plus TypeScript-family LSP doctor
 - **LazyClaude HUD** - npm install configures a compact Claude Code statusLine
   based on `pretty-claude-hud`, branded as `[💤LAZYCLAUDE vX.Y.Z]`, with
-  install-time color selection, live previews, dense context bars, visible
-  low-usage rate-limit bars, and spaced reset countdowns
+  install-time vivid color selection, live mini-HUD previews, compact context
+  bars, visible low-usage rate-limit bars, broader brand accent coverage, and
+  spaced reset countdowns
 - **Safe uninstall** - removes only LazyClaude-managed state
 
 ## Quick Start
@@ -66,8 +74,8 @@ npx --yes lazyclaude-ai install
 ```
 
 During an interactive `npx` install, LazyClaude shows every HUD brand color as
-a live terminal preview and writes the selected accent into the managed Claude
-`statusLine` command. Animated installs also use colored setup, plugin,
+a vivid live terminal preview and writes the selected accent into the managed
+Claude `statusLine` command. Animated installs also use colored setup, plugin,
 marketplace, registry, and cache labels so progress is easier to scan.
 Noninteractive installs keep deterministic plain `INSTALL_STEP` lines.
 
@@ -80,7 +88,7 @@ install command works:
 
 ```bash
 cd /tmp
-npx --yes lazyclaude-ai@0.1.17 install
+npx --yes lazyclaude-ai@0.2.0 install
 ```
 
 Validate the installed plugin:
@@ -93,14 +101,16 @@ The installer also sets Claude Code's `statusLine` command to the packaged
 LazyClaude HUD. A typical no-color render starts like:
 
 ```text
-[💤LAZYCLAUDE v0.1.17] | O4.8 │ ctx [▉░░░░░░░░░] 9%/1000k │ 5h [▏░░░] 4% ↻2h15m │ 1w [█▍░░] 35% ↻3d6h │ git main +3 ✓
+[💤LAZYCLAUDE v0.2.0] | 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
 the percentage for readability, and low non-zero percentages still get a
-partial bar glyph instead of looking empty. Claude Code reports reset windows
-as epoch seconds, and LazyClaude also accepts ISO reset timestamps for
-compatibility with test fixtures and older status-line helpers.
+partial bar glyph instead of looking empty. The context bar uses three cells
+and the rate-limit bars use two cells so the HUD stays tight in Claude Code's
+status-line space. Claude Code reports reset windows as epoch seconds, and
+LazyClaude also accepts ISO reset timestamps for compatibility with test
+fixtures and older status-line helpers.
 
 To override the accent without the picker, set `LAZYCLAUDE_HUD_ACCENT` to one
 of `cyan`, `blue`, `teal`, `green`, `lavender`, `rose`, `gold`, `orange`,
@@ -164,6 +174,10 @@ $ulw-loop <what you want executed with evidence>
 /ulw-loop <what you want executed with evidence>
 $deep-interview <what needs clarification>
 /deep-interview <what needs clarification>
+$review-work <scope to review>
+/review-work <scope to review>
+$ultragoal <goal operation>
+/ultragoal <goal operation>
 $start-work plans/lazyclaude-retrofit.md
 /start-work plans/lazyclaude-retrofit.md
 ```
@@ -192,6 +206,30 @@ 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 v0.2.0 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
+`oracle-verifier`, `qa-runner`, `quality-reviewer`, and `librarian-researcher`,
+then aggregate evidence into a PASS, FAIL, or NEEDS-CONTEXT verdict. Manual-QA
+channels must write artifacts, and every tmux session, server, port, browser
+tab, or temp directory needs a cleanup receipt before review completion.
+
+`ultragoal` is the durable local state route for long goals. The runtime lives
+in `plugins/lazyclaude/lib/ultragoal/`, stores state in `.omo/ultragoal/`, and
+keeps current docs/test reads authoritative when stale state disagrees with the
+checkout. Common commands are:
+
+```bash
+lazyclaude ultragoal create-goals --brief "<brief>" --json
+lazyclaude ultragoal record-evidence --criterion <id> --status pass --json '{"artifact":"...","cleanup":"..."}'
+lazyclaude ultragoal checkpoint --status active --note "<progress>" --json
+lazyclaude ultragoal steer --kind scope --note "<what changed and why>" --json
+```
+
+`record-review-blockers` captures unresolved review findings. Malformed JSON,
+unknown criteria, corrupt state, and invalid steering kinds return controlled
+errors instead of silently reporting success.
+
 Plain `ulw` is hook context activation. Claude may still show it as hook
 guidance rather than a separate Skill tool invocation in history. Use visible
 namespaced commands when you want explicit LazyClaude skill activation:
@@ -200,6 +238,8 @@ namespaced commands when you want explicit LazyClaude skill activation:
 /lazyclaude:ulw-loop <what you want executed with evidence>
 /lazyclaude:ulw-plan <what you want planned>
 /lazyclaude:deep-interview <what needs clarification>
+/lazyclaude:review-work <scope to review>
+/lazyclaude:ultragoal <goal operation>
 /lazyclaude:start-work plans/lazyclaude-retrofit.md
 ```
 
@@ -290,7 +330,6 @@ version probe evidence instead of failing mysteriously.
 | MCP | `plugins/lazyclaude/.mcp.json` |
 | LSP | `plugins/lazyclaude/.lsp.json` |
 
-See `README_ko-KR.md` for Korean setup notes, `REFERENCE.md` for the pinned
-private snapshot metadata, `docs/migration.md` for the reference-to-Claude migration table,
-`docs/workflow-compatibility-audit.md` for the current compatibility audit, and `CHANGELOG.md`
-for release notes.
+See `README_ko-KR.md` for Korean setup notes, `docs/migration.md` for the
+workflow migration table, `docs/workflow-compatibility-audit.md` for the current
+compatibility audit, and `CHANGELOG.md` for release notes.

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-0.1.17-2ea44f" />
+  <img src="https://img.shields.io/badge/version-0.2.0-2ea44f" />
   <img src="https://img.shields.io/badge/Claude%20Code-plugin-blueviolet" />
   <img src="https://img.shields.io/badge/license-MIT-blue" />
 </p>
@@ -26,13 +26,12 @@
 > 설치되므로, 매번 긴 `--plugin-dir` 없이 일반 `claude` 실행에서
 > LazyClaude skill과 hook을 불러올 수 있습니다.
 
-현재 checkout은 `lazyclaude-ai@0.1.17` 배포용으로 준비되어 있습니다. 목적은 다른 PC에서도
-빠르게 설치하기 위한 개인용 배포물입니다. 저장소는 비공개 저장소로
-유지할 수 있고, npm 배포가 곧 홍보, 공개 저장소 운영, Claude marketplace
-등록을 의미하지는 않습니다. 새 버전 배포는 항상 별도의 명시적 승인 후에
-진행합니다.
-v0.1.17 release material은 source-origin-free 상태이며 LazyClaude 자체의
-표현으로 정리되어 있습니다.
+현재 checkout은 `lazyclaude-ai@0.2.0` 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.
 
 ## 기능
 
@@ -40,9 +39,17 @@ v0.1.17 release material은 source-origin-free 상태이며 LazyClaude 자체의
 - **ULW prompt hook** - `ulw`, `ultrawork`, `$ulw-plan`, `$ulw-loop` 트리거
 - **Deep interview mode** - `/deep-interview` 또는 `$deep-interview`로 넓고
   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
+- **5-lane review** - `/review-work`가 goal/constraint verification,
+  hands-on QA execution, code quality, security, local-first context mining을
+  한 번에 점검
 - **Native goal guidance** - Claude Code가 `/goal` 또는 `get_goal`,
   `create_goal`, `update_goal` 같은 goal surface를 제공하면 이를 우선
   사용하도록 유도하고, goal tools are unavailable 상황의 fallback도 명시
+- **Ultragoal CLI/state** - `plugins/lazyclaude/lib/ultragoal/`가 durable
+  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
 - **Claude skills** - LazyClaude 스타일을 더 풍부하게 옮긴 corpus:
@@ -57,8 +64,9 @@ v0.1.17 release material은 source-origin-free 상태이며 LazyClaude 자체의
 - **MCP와 LSP helper** - plugin-local stdio MCP와 TypeScript 계열 LSP doctor
 - **LazyClaude HUD** - npm install 시 `pretty-claude-hud` 기반의 compact
   Claude Code statusLine을 `[💤LAZYCLAUDE vX.Y.Z]` 브랜드로 자동 설정하고,
-  설치 중 색상 선택, 즉시 미리보기, 촘촘한 context bar, 낮은 사용량도
-  비어 보이지 않는 rate-limit bar, 간격이 있는 reset countdown을 제공
+  설치 중 눈에 잘 띄는 색상 선택, 즉시 mini-HUD 미리보기, compact context
+  bar, 낮은 사용량도 비어 보이지 않는 rate-limit bar, 더 넓은 brand accent
+  적용 범위, 간격이 있는 reset countdown을 제공
 - **안전한 uninstall** - LazyClaude가 관리한 상태만 제거
 
 ## 빠른 시작
@@ -69,8 +77,8 @@ v0.1.17 release material은 source-origin-free 상태이며 LazyClaude 자체의
 npx --yes lazyclaude-ai install
 ```
 
-interactive `npx` 설치에서는 LazyClaude가 HUD brand color 후보를 실제
-터미널 색상으로 바로 보여주고, 선택한 accent를 Claude의 managed
+interactive `npx` 설치에서는 LazyClaude가 HUD brand color 후보를 더 선명한
+실제 터미널 색상으로 바로 보여주고, 선택한 accent를 Claude의 managed
 `statusLine` command에 저장합니다. animated install에서는 setup, plugin,
 marketplace, registry, cache label도 색상으로 구분해서 진행 상황을 더 쉽게
 스캔할 수 있습니다. noninteractive install은 deterministic한 plain
@@ -85,7 +93,7 @@ checkout을 먼저 해석해서 `sh: lazyclaude-ai: command not found`로 실패
 
 ```bash
 cd /tmp
-npx --yes lazyclaude-ai@0.1.17 install
+npx --yes lazyclaude-ai@0.2.0 install
 ```
 
 설치 상태를 확인합니다.
@@ -98,13 +106,15 @@ installer는 Claude Code의 `statusLine` command도 packaged LazyClaude HUD로
 설정합니다. 색상을 제거한 예시는 다음처럼 시작합니다.
 
 ```text
-[💤LAZYCLAUDE v0.1.17] | O4.8 │ ctx [▉░░░░░░░░░] 9%/1000k │ 5h [▏░░░] 4% ↻2h15m │ 1w [█▍░░] 35% ↻3d6h │ git main +3 ✓
+[💤LAZYCLAUDE v0.2.0] | O4.8 │ ctx [▎░░] 9%/1000k │ 5h [▏░] 4% ↻2h15m │ 1w [▊░] 35% ↻3d6h │ git main +3 ✓
 ```
 
 `↻` 표시는 rate-limit reset까지 남은 시간을 짧게 보여주는 countdown입니다.
 percentage와는 한 칸 띄워서 읽기 쉽게 만들었고, 낮은 non-zero 사용량도
-partial bar glyph로 표시되어 비어 보이지 않습니다. Claude Code가 제공하는
-epoch seconds 형태와 ISO timestamp 형태를 모두 해석합니다.
+partial bar glyph로 표시되어 비어 보이지 않습니다. context bar는 3칸,
+rate-limit bar는 2칸으로 줄여 Claude Code status-line 공간을 덜 차지합니다.
+Claude Code가 제공하는 epoch seconds 형태와 ISO timestamp 형태를 모두
+해석합니다.
 
 picker 없이 색상을 지정하려면 설치 전에 `LAZYCLAUDE_HUD_ACCENT`를
 `cyan`, `blue`, `teal`, `green`, `lavender`, `rose`, `gold`, `orange`,
@@ -168,6 +178,10 @@ $ulw-loop <증거 기반으로 실행할 작업>
 /ulw-loop <증거 기반으로 실행할 작업>
 $deep-interview <명확화가 필요한 작업>
 /deep-interview <명확화가 필요한 작업>
+$review-work <검토할 범위>
+/review-work <검토할 범위>
+$ultragoal <goal operation>
+/ultragoal <goal operation>
 $start-work plans/lazyclaude-retrofit.md
 /start-work plans/lazyclaude-retrofit.md
 ```
@@ -195,6 +209,30 @@ 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.
 
+v0.2.0 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
+`oracle-verifier`, `qa-runner`, `quality-reviewer`, `librarian-researcher`에
+연결되고, 증거를 모아 PASS, FAIL, NEEDS-CONTEXT verdict로 정리합니다.
+Manual-QA channels는 artifact를 남겨야 하며 tmux session, server, port,
+browser tab, temp directory는 completion 전에 cleanup receipt를 남겨야 합니다.
+
+`ultragoal`은 긴 목표를 위한 durable local state route입니다. runtime은
+`plugins/lazyclaude/lib/ultragoal/`에 있고 state는 `.omo/ultragoal/` 아래에
+남깁니다. stale state가 checkout과 어긋나면 current docs/test reads를
+기준으로 판단합니다. 자주 쓰는 명령은 다음과 같습니다.
+
+```bash
+lazyclaude ultragoal create-goals --brief "<brief>" --json
+lazyclaude ultragoal record-evidence --criterion <id> --status pass --json '{"artifact":"...","cleanup":"..."}'
+lazyclaude ultragoal checkpoint --status active --note "<progress>" --json
+lazyclaude ultragoal steer --kind scope --note "<what changed and why>" --json
+```
+
+`record-review-blockers`는 해결되지 않은 review finding을 기록합니다.
+malformed JSON, unknown criterion, corrupt state, invalid steering kind는
+성공처럼 보이지 않고 controlled error로 실패해야 합니다.
+
 단순히 `ulw`라고 입력하는 것은 hook context activation입니다. Claude Code
 history에는 별도 Skill tool invocation이 아니라 hook guidance로 보일 수
 있습니다. 명시적인 LazyClaude skill activation을 보고 싶다면 namespaced
@@ -204,6 +242,8 @@ command를 사용합니다.
 /lazyclaude:ulw-loop <증거 기반으로 실행할 작업>
 /lazyclaude:ulw-plan <계획이 필요한 작업>
 /lazyclaude:deep-interview <명확화가 필요한 작업>
+/lazyclaude:review-work <검토할 범위>
+/lazyclaude:ultragoal <goal operation>
 /lazyclaude:start-work plans/lazyclaude-retrofit.md
 ```
 
@@ -296,6 +336,6 @@ probe evidence를 남깁니다.
 | MCP | `plugins/lazyclaude/.mcp.json` |
 | LSP | `plugins/lazyclaude/.lsp.json` |
 
-영문 설명은 `README.md`, private snapshot metadata는 `REFERENCE.md`,
-reference-to-Claude 변환 표는 `docs/migration.md`, 현재 compatibility audit은
-`docs/workflow-compatibility-audit.md`, release notes는 `CHANGELOG.md`를 참고하세요.
+영문 설명은 `README.md`, workflow migration 표는 `docs/migration.md`, 현재
+compatibility audit은 `docs/workflow-compatibility-audit.md`, release notes는
+`CHANGELOG.md`를 참고하세요.

package/RELEASE_CHECKLIST.md

@@ -1,12 +1,14 @@
 # LazyClaude Release Checklist
 
-Status: `lazyclaude-ai@0.1.17` is the current release candidate for HUD polish
-and installer color improvements. The HUD now uses a dense bracketed context
-bar, shows low non-zero 5-hour and 7-day usage with partial fill glyphs, and
-spaces the `↻` reset countdown away from the percentage. Animated `npx`
-installs now show more color-coded progress labels. Versions `0.1.11`,
-`0.1.12`, `0.1.13`, `0.1.14`, `0.1.15`, and `0.1.16` already exist or were
-prepared in this release series, so this patch version is the next publishable target
+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`.
+
+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.
 
 DO NOT publish a new version of LazyClaude, run `npm publish`, push release
@@ -24,17 +26,34 @@ public repo promotion, or a public launch campaign.
 - `npm run qa:portable`
 - `npm run pack:dry-run`
 
-## Local / Private Checkout Use
+## Local Checkout Use
 
 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. Start Claude Code with `claude --plugin-dir ./plugins/lazyclaude`.
+4. Run `node bin/lazyclaude-ai.js ultragoal --help`.
+5. Start Claude Code with `claude --plugin-dir ./plugins/lazyclaude`.
 
 No npm publication is required for this track.
 
+## v0.2.0 Workflow Parity 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`.
+- `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.
+- `node bin/lazyclaude-ai.js ultragoal --help` prints durable state commands.
+- `npm pack --dry-run --json` includes runtime payloads and excludes local
+  `.omo/`, `.omc/`, and `evidence/` state.
+- `.omo/ulw-loop/evidence/v020-red-contracts.txt` or equivalent RED evidence
+  exists for the workflow parity contracts before GREEN evidence.
+
 ## Fresh Machine NPM Install Use
 
 Use this track after an approved npm package version exists:
@@ -66,7 +85,8 @@ Use this track only when the user explicitly approves making a new package
 version installable through `npm`, `npx`, and `bunx`.
 
 1. Confirm the target package name and version with the user.
-2. Review `REFERENCE.md` and `docs/migration.md` for sanitized private-reference metadata.
+2. Review `README.md`, `README_ko-KR.md`, `docs/migration.md`, and
+   `docs/workflow-compatibility-audit.md` for neutral release wording.
 3. Run `npm whoami` and confirm the intended npm account.
 4. Re-run the full local verification set from a clean checkout:
    - `npm test`

package/bin/lazyclaude-ai.js

@@ -14,12 +14,14 @@ import { homedir } from "node:os";
 import { dirname, join, resolve } from "node:path";
 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";
 
 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> [...args]
+const usage = `Usage: lazyclaude-ai [--dry-run] <install|doctor|path|run|update|uninstall|ultragoal> [...args]
        lazyclaude-ai --version
 
 Commands:
@@ -27,6 +29,7 @@ Commands:
   doctor        Validate the installed LazyClaude plugin path.
   path          Print the installed Claude plugin path.
   run -- ...    Run Claude Code after the global plugin install.
+  ultragoal     Manage ultragoal runtime state and evidence.
   update        Reinstall this package version and refresh the Claude plugin registry.
   uninstall     Remove LazyClaude-managed install state.
 `;
@@ -63,19 +66,7 @@ const knownExternalLspPlugins = {
   "gopls-lsp@claude-plugins-official": ["gopls"],
 };
 const spinnerFrames = ["⠋", "⠙", "⠹", "⠸", "⠼", "⠴", "⠦", "⠧", "⠇", "⠏"];
-const hudAccentThemes = [
-  { name: "cyan", code: 81, mood: "LazyClaude default" },
-  { name: "blue", code: 74, mood: "calm terminal" },
-  { name: "teal", code: 66, mood: "muted productivity" },
-  { name: "green", code: 71, mood: "classic shell" },
-  { name: "lavender", code: 139, mood: "quiet purple" },
-  { name: "rose", code: 132, mood: "soft contrast" },
-  { name: "gold", code: 136, mood: "warm focus" },
-  { name: "orange", code: 173, mood: "high energy" },
-  { name: "slate", code: 60, mood: "low saturation" },
-  { name: "gray", code: 245, mood: "monochrome" },
-];
-const hudAccentNames = new Set(hudAccentThemes.map((theme) => theme.name));
+const hudAccentThemes = HUD_ACCENT_THEMES;
 
 const printUsage = () => {
   process.stderr.write(usage);
@@ -161,12 +152,8 @@ const writeClaudeSettings = (settings, home = claudeHome()) => {
   writeFileSync(settingsPath, `${JSON.stringify(settings, null, 2)}\n`);
 };
 
-const normalizeHudAccent = (value) => {
-  const normalized = String(value || "").trim().toLowerCase();
-  return hudAccentNames.has(normalized) ? normalized : "cyan";
-};
-
-const hudAccentPreview = (theme) => `\x1b[38;5;${theme.code}m[💤LAZYCLAUDE v${version}]\x1b[0m`;
+const hudAccentPreview = (theme) =>
+  `\x1b[38;5;${theme.code}m[💤LAZYCLAUDE v${version}] | O4.8 │ ctx [▌░░] 18%/1000k │ 5h [▏░] 4%\x1b[0m`;
 
 const shouldPromptHudAccent = () => {
   if (process.env.LAZYCLAUDE_HUD_ACCENT_PROMPT === "1") return true;
@@ -195,7 +182,7 @@ const chooseHudAccent = async () => {
     if (trimmed && selected === "cyan" && trimmed !== "cyan" && byIndex === undefined) {
       process.stdout.write("HUD_COLOR_WARNING: unknown color; using cyan\n");
     }
-    process.stdout.write(`HUD_COLOR_SELECTED: ${selected} ${hudAccentPreview(hudAccentThemes.find((theme) => theme.name === selected))}\n`);
+    process.stdout.write(`HUD_COLOR_SELECTED: ${selected} ${hudAccentPreview(themeForAccent(selected))}\n`);
     return selected;
   } finally {
     rl.close();
@@ -631,6 +618,9 @@ const main = async () => {
     case "run":
       runClaude(parsed);
       break;
+    case "ultragoal":
+      process.exit(runUltragoalCli(parsed.rest));
+      break;
     case "uninstall":
       uninstall(parsed);
       break;

package/docs/agents.md

@@ -16,6 +16,22 @@ The planner is deliberately constrained because the safest Claude Code retrofit
 keeps planning separate from mutation. Executor and QA agents can act only
 inside the plan and evidence contract.
 
+## Review Work Routing
+
+The v0.2.0 workflow parity review route uses five evidence lanes:
+
+| Review lane | Agent routing | Required evidence |
+| --- | --- | --- |
+| goal/constraint verification | `oracle-verifier` with `review-work` and `rules` | Goal, non-goals, acceptance criteria, publish boundary, and constraints checked against current docs/test reads. |
+| hands-on QA execution | `qa-runner` with `start-work` and `review-work` | Automated test output, Manual-QA channels, artifacts, and cleanup receipt. |
+| code quality | `quality-reviewer` with `review-work` and `programming` | Findings-first code review focused on regressions and maintainability. |
+| security | `quality-reviewer` with `review-work` and `programming` | Prompt injection, malformed input, local state, and unsafe command handling risks. |
+| local-first context mining | `librarian-researcher` with `rules` | Local checkout, docs, tests, and ledgers checked before external references. |
+
+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.
+
 ## Local Use
 
 Load the plugin from this checkout:

package/docs/hooks.md

@@ -28,6 +28,12 @@ $ulw-loop
 $deep-interview
 /deep-interview
 /lazyclaude:deep-interview
+$review-work
+/review-work
+/lazyclaude:review-work
+$ultragoal
+/ultragoal
+/lazyclaude:ultragoal
 $start-work
 /start-work
 /lazyclaude:start-work
@@ -79,12 +85,20 @@ These are real Claude Code command files in `plugins/lazyclaude/commands/`.
 before `/ulw-plan` when a request lacks non-goals, decision boundaries, or
 acceptance criteria.
 
+`/review-work` and `$review-work` load `/lazyclaude:review-work` /
+`Skill(review-work)`. That route runs the v0.2.0 workflow parity 5-lane review:
+goal/constraint verification, hands-on QA execution, code quality, security,
+and local-first context mining. `/ultragoal` and `$ultragoal` load
+`/lazyclaude:ultragoal` / `Skill(ultragoal)` for durable local goal state and
+the ultragoal CLI.
+
 ## Safety
 
 Hooks parse JSON from stdin and return JSON to Claude Code. The hook does not
-execute prompt text and does not echo prompt text into the returned context. The
-ultrawork detector returns constant workflow guidance, so a prompt cannot become
-a shell command through the hook response.
+execute prompt text and does not echo prompt text into the returned context;
+prompt text is not executed or echoed. The ultrawork detector returns constant
+workflow guidance, so a prompt cannot become a shell command through the hook
+response. Malformed hook input and malformed ultragoal JSON should surface a controlled error instead of a misleading success response.
 
 ## Local Smoke
 

package/docs/migration.md

@@ -1,8 +1,8 @@
 # LazyClaude Migration
 
-LazyClaude maps a pinned private workflow reference into Claude Code-native
-surfaces. The goal is behavior parity where Claude Code exposes the same kind
-of surface, and a conservative local fallback where it does not.
+LazyClaude maps workflow disciplines into Claude Code-native surfaces. The goal
+is behavior parity where Claude Code exposes the same kind of surface, and a
+conservative local fallback where it does not.
 
 | Reference surface | Claude Code surface | LazyClaude implementation |
 | --- | --- | --- |
@@ -11,6 +11,8 @@ of surface, and a conservative local fallback where it does not.
 | Ultrawork plan mode | Claude Code skill plus planner agent | `ulw-plan` and `prometheus-planner` |
 | Clarification interview | Claude Code skill plus command | `deep-interview` asks one Socratic question per round, persists state under `deep-interview/`, and hands a spec to planning or execution |
 | Execution loop | Claude Code skill plus executor agent | `ulw-loop`, `start-work`, and `boulder-executor` |
+| 5-lane review | Claude Code command, skill, and agents | `review-work` runs goal/constraint verification, hands-on QA execution, code quality, security, and local-first context mining |
+| 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 |
 | Hooks | Claude Code hooks | `plugins/lazyclaude/hooks/hooks.json` |
@@ -70,6 +72,33 @@ 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`.
 
+## v0.2.0 Review And Ultragoal Parity
+
+The v0.2.0 workflow parity surface is local-first and evidence-bound. It does
+not imply that an npm publish or remote marketplace publication has happened.
+`/review-work`, `$review-work`, and `/lazyclaude:review-work` run the 5-lane
+review contract: goal/constraint verification, hands-on QA execution, code
+quality, security, and local-first context mining. Manual-QA channels must
+produce artifacts, and all spawned sessions, servers, ports, browser tabs, and
+temp directories need a cleanup receipt before completion.
+
+`/ultragoal`, `$ultragoal`, and `/lazyclaude:ultragoal` bind long work to the
+ultragoal runtime in `plugins/lazyclaude/lib/ultragoal/`. The local state lives
+under `.omo/ultragoal/`, and current docs/test reads are the authority if stale
+state contradicts the checkout.
+
+Use these CLI commands for durable state:
+
+```bash
+lazyclaude ultragoal create-goals --brief "<brief>" --json
+lazyclaude ultragoal record-evidence --criterion <id> --status pass --json '{"artifact":"...","cleanup":"..."}'
+lazyclaude ultragoal checkpoint --status active --note "<progress>" --json
+lazyclaude ultragoal steer --kind scope --note "<what changed and why>" --json
+```
+
+Malformed evidence JSON, unknown criteria, corrupt state, or invalid steering
+kinds must fail with a controlled error.
+
 If OMC/omc is already installed in Claude Code, keep it disabled or start a
 separate Claude Code session without OMC while testing LazyClaude. This repo no
 longer ships a root marketplace skeleton; direct `--plugin-dir` loading avoids