litclaude-ai 0.3.22 → 0.3.26

package/CHANGELOG.md

@@ -1,8 +1,34 @@
 # Changelog
 
-## 0.3.22 - 2026-07-07 — full lit-family bare invocation release prep
+## 0.3.26 - 2026-07-11 — planning quality and orchestration safety
 
-- Prepare `litclaude-ai@0.3.22` for npm publication after extending bare lit-family prompt-hook routes to inject the installed `SKILL.md` body.
+- Make `lit-plan` checklist depth adaptive: one bounded objective, explicit
+  non-goals, resolved or gated unknowns, Action/Output/Verification items,
+  decision branches, proportionate evidence, and a replayable DoneClaim.
+- Add `review-work` plan-review mode with scope, objective-achievability,
+  checklist-atomicity, evidence, failure, and cleanup audits while preserving
+  the completed-work 5-lane review and the planning-only no-implementation
+  boundary.
+- Harden orchestration readiness against disabled or malformed user, project,
+  and managed-policy settings; remove delegation from the standalone planner
+  and document bounded workflow lifecycle and cleanup behavior.
+
+## 0.3.25 - 2026-07-09 — portable and public-read release prep
+
+- Prepare `litclaude-ai@0.3.25` after aligning installed portable details,
+  `public-read`, `litgoal status --json`, evidence wording, and release docs for
+  manual npm publication.
+- Preserve local `HANDOFF_litclaude.md` continuation state outside product
+  commits.
+
+## 0.3.24 - 2026-07-08 — auxiliary skill inventory and advisory probes
+
+- Prepare `litclaude-ai@0.3.24` after aligning public auxiliary skill inventories for `frontend-ui-ux`, `git-master`, `lsp-setup`, and `visual-qa` without adding slash-command routes.
+- Add non-mutating advisory probe coverage for shipped LSP setup and visual QA helper scripts while preserving local `HANDOFF_litclaude.md` state outside product commits.
+
+## 0.3.23 - 2026-07-08 — full lit-family clean-room release prep
+
+- Prepare `litclaude-ai@0.3.23` for npm publication after extending bare lit-family prompt-hook routes to inject the installed `SKILL.md` body.
 - Keep the safe natural-language `lit start work` BLOCKED handoff while explicit bare skill routes carry full prompt context.
 
 ## 0.3.21 - 2026-07-07 — full bare skill-body routing
@@ -176,7 +202,7 @@
   **user-typed slash command** that sets an autonomous completion condition — it is **not a
   model-facing tool**, and a hook or skill **cannot invoke it**. The previous guidance led with a
   `get_goal`/`create_goal`/`update_goal` "native goal tool" path that does not exist in any current
-  Claude Code (a residue of the upstream Codex lineage), which buried the only real mechanism.
+  Claude Code (a residue of retired non-Claude lineage), which buried the only real mechanism.
 - Now, when a goal is worth binding (hook injection on `lit`/`litwork`/`/litgoal`, and the `lit-loop`,
   `lit-plan`, `start-work`, `litgoal` skills), LitClaude **proposes a concrete, ready-to-paste
   `/goal <completion condition>`** for the user and keeps the durable record in the local litgoal
@@ -210,11 +236,9 @@
   explore-subagent scaling, a weighted scoring matrix, AGENTS.md templates, and quality gates. All
   reference orchestration/LSP calls are re-authored to Claude Code surfaces (`Agent`/`Task` background
   subagents, the `LSP` tool, `Workflow` for parallel generation, `TodoWrite`) — no literal calls to
-  missing tools, no Codex/opencode tokens.
-- Add `plans/litclaude-reference-parity-sdd.md`: a decision-complete SDD plan capturing the full
-  OmO-reference parity audit (all 11 shared skills + both auxiliary packs are byte-identical) and the
-  remaining portable ports (`init-deep` done; `visual-qa` and `lsp-setup` planned), plus a verified
-  deliberate-omission (N/A) registry. Allowlisted as a non-shipped doc-class file.
+  missing tools, no non-Claude runtime tokens.
+- Capture the portable parity audit in an internal plan, with `init-deep` completed and
+  `visual-qa` / `lsp-setup` planned, while keeping public package surfaces brand-clean.
 
 ## 0.3.2 - 2026-06-14 — port the git-master skill
 
@@ -235,20 +259,19 @@
 
 ## 0.3.0 - 2026-06-14 — LitClaude rebrand + lit-family vocab + neon HUD
 
-- Rename `ulw`/`ultra*` trigger vocabulary to the **lit family**: `lit`, `litwork`, `lit-loop`,
+- Rename the retired trigger vocabulary to the **lit family**: `lit`, `litwork`, `lit-loop`,
   `lit-plan`, and `litgoal` end-to-end across hooks, skills, commands, and documentation.
 - `lit` trigger now maps to `lit-loop` semantics with a soft-confirm step before long execution
   instead of falling through to a plain loop.
 - Ship a neon `[🔥LITCLAUDE]` truecolor-gradient HUD (hot-pink → cyan gradient; bright-magenta
   fallback on 256-color terminals) branded with `[🔥LITCLAUDE vX.Y.Z]`.
-- Rename the project from **LazyClaude / `lazyclaude-ai`** to **LitClaude / `litclaude-ai`**
-  end-to-end: npm package, `litclaude`/`litclaude-ai` bins, `plugins/litclaude/` payload, installer
-  identifiers (`litclaude@litclaude-ai`), 13 `LITCLAUDE_*` env vars, per-project state dir
-  `.litclaude/` (was `.omo/`), HUD banner `[LitClaude vX.Y.Z]` (dropped the 💤), and the 7
-  `litclaude:*` slash commands. See `docs/migration.md` for the upgrade guide.
-- Add a fail-closed legacy-token scanner (`tools/scan-legacy-tokens.mjs`) + allowlist that keeps the
-  shipped surface free of legacy and upstream-lineage tokens and the source-origin handle;
-  `ulw`/`ultrawork` are kept as own vocabulary.
+- Rename the project to **LitClaude / `litclaude-ai`** end-to-end: npm package,
+  `litclaude`/`litclaude-ai` bins, `plugins/litclaude/` payload, installer identifiers
+  (`litclaude@litclaude-ai`), 13 `LITCLAUDE_*` env vars, per-project state dir `.litclaude/`,
+  HUD banner `[LitClaude vX.Y.Z]`, and the 7 `litclaude:*` slash commands. See
+  `docs/migration.md` for current install and state surfaces.
+- Add a fail-closed guarded-token scanner (`tools/scan-legacy-tokens.mjs`) that keeps tracked
+  and shipped surfaces free of retired identity, vocabulary, and source-trace terms.
 - Add a no-publish CI workflow (`.github/workflows/ci.yml`, `permissions: contents: read`) plus
   version-lockstep, CI-integrity, and pack-payload hardening gates.
 - Make the atomic state store durable (fsync), remove the ported `codex:` session-id residue (Claude
@@ -283,11 +306,11 @@
 
 - Align the package and Claude plugin manifests to `litclaude-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 `.litclaude/ultragoal/`.
+- Add the `review-work` 5-lane review route and document its scope/diff,
+  tests/evidence, package/payload and code quality, security/provenance, and
+  real-surface/docs readiness lanes.
+- Add the durable goal CLI/runtime surface for criteria, evidence, checkpoints,
+  steering, and review blocker records under `.litclaude/litgoal/`.
 - Keep the release boundary explicit: this version is prepared for verification
   and publication approval, but no npm publish or marketplace publication is claimed
   here.
@@ -319,7 +342,7 @@
   `/litclaude:deep-interview` routing for a Socratic requirements mode before
   planning or implementation.
 - Ship the `deep-interview` skill and its progress renderer, plus English and
-  Korean README guidance for when to chain it into `/ulw-plan` or `/ulw-loop`.
+  Korean README guidance for when to chain it into the planning or execution routes.
 
 ## 0.1.15 - 2026-06-01
 
@@ -340,11 +363,11 @@
 
 ## 0.1.13 - 2026-06-01
 
-- Fix short slash ULW routing so `/ulw-plan`, `/ulw-loop`, and `/start-work`
-  map to their matching LitClaude disciplines instead of falling through to
-  plain `ulw` loop activation.
-- Preserve punctuation-delimited triggers such as `ulw.` and `/ulw-plan, ...`
-  while ignoring hyphenated near-misses such as `/ulw-plan-ish`.
+- Fix short slash route handling so planning, execution, and `/start-work`
+  map to their matching LitClaude disciplines instead of falling through to a
+  plain loop activation.
+- Preserve punctuation-delimited short triggers while ignoring hyphenated
+  near-misses.
 - Round HUD context/rate-limit percentages before rendering, so floating-point
   values such as `7.000000000000001%` never leak into the status line.
 - Ignore transcript entries that start with `<local-command-stdout>` or
@@ -368,8 +391,8 @@
   generation to `litclaude-ai@0.1.11`.
 - Refresh README, reference metadata, and workflow
   compatibility audit wording.
-- Deepen trigger-specific hook routing for `$ulw-plan`, `$ulw-loop`, and
-  `$start-work`, with safer post-edit diagnostic guidance.
+- Deepen trigger-specific hook routing for planning, execution, and `$start-work`,
+  with safer post-edit diagnostic guidance.
 
 ## 0.1.10 - 2026-06-01
 
@@ -383,7 +406,7 @@
 
 ## 0.1.7
 
-- Expand the workflow compatibility audit beyond skill frontmatter into upstream legacy
+- Expand the workflow compatibility audit beyond skill frontmatter into portable
   component coverage.
 - Ship the original `ai-slop-remover` skill alias alongside the LitClaude
   `remove-ai-slops` skill.

package/README.md

@@ -9,7 +9,7 @@
 </p>
 <p align="center">
   <img src="https://img.shields.io/badge/npm-litclaude--ai-cb3837" />
-  <img src="https://img.shields.io/badge/version-0.3.22-2ea44f" />
+  <img src="https://img.shields.io/badge/version-0.3.26-2ea44f" />
   <img src="https://img.shields.io/badge/Claude%20Code-plugin-blueviolet" />
   <img src="https://img.shields.io/badge/license-MIT-blue" />
 </p>
@@ -22,10 +22,10 @@
 > `litclaude@litclaude-ai`, so normal `claude` launches can load the
 > LitClaude skills and hooks without a long `--plugin-dir` command.
 
-This checkout is prepared as `litclaude-ai@0.3.22` for personal install
+This checkout is prepared as `litclaude-ai@0.3.26` 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 v0.3.22
+Future package releases still require explicit user approval. The v0.3.26 release material adds adaptive objective-achievable planning, draft-plan review, and orchestration readiness hardening. The v0.3.25 release material aligns portable details, public-read, litgoal status JSON, and evidence wording. The v0.3.24 release material aligns auxiliary skill inventories and advisory probes. The v0.3.23
 release materials inject the bundled skill bodies for bare `hyperplan`,
 `litresearch`, `lit research`, `init-deep`, and explicit `$start-work` prompt-hook routes while
 preserving the v0.3.19 adversarial planning skill, the v0.3.18 read-only `lit-recap` session recap surface, the v0.3.17 separate-worker native `/goal` launcher, the v0.3.16
@@ -60,8 +60,9 @@ activation/read-only polish, and installer permission-preference discipline.
   and MCP `public_source_read` provide a callable JS-only public page reader with
   SSRF/private-host guards, auth/paywall stop reasons, metadata/JSON-LD fallback,
   and route evidence for research lanes
-- **5-lane review** - `/review-work` checks goal/constraint verification,
-  hands-on QA execution, code quality, security, and local-first context mining
+- **5-lane review** - `/review-work` checks scope/diff verification,
+  tests/evidence execution, package/payload and code quality,
+  security/provenance, and real-surface/docs readiness
 - **Native goal guidance** - LIT 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
@@ -71,11 +72,17 @@ activation/read-only polish, and installer permission-preference discipline.
 - **Dynamic workflow/worktree guidance** - large or parallel tasks are steered
   toward Claude Code Dynamic workflow orchestration, subagent delegation, and
   Dynamic worktree isolation
+- **Observable orchestration gates** - `workflow-check --json` fails when locally observable environment, user/project settings, or macOS/Linux managed-policy files disable workflows/background tasks, or when tool concurrency is effectively serial. It reports remote organization policy as not locally observable; a local pass cannot override a remote administrator denial. Claude Code 2.1.207 workflow ceilings (16 concurrent, 1000 total), cost-bearing `acceptEdits` workers, one-team-per-lead ownership, graceful teammate shutdown, and resume/orphan-tmux checks are explicit lifecycle constraints.
 - **Claude skills** - a richer LitClaude-owned corpus: `programming`,
   `debugging`, `refactor`, `ai-slop-remover`, `remove-ai-slops`,
   `korean-ai-slop-remover`, `review-work`, `frontend-ui-ux`,
-  `comment-checker`, `rules`, `lsp`, `litgoal`, `deep-interview`, `hyperplan`,
-  `lit-plan`, `lit-recap`, `lit-loop`, and `start-work`
+  `git-master`, `comment-checker`, `rules`, `lsp`, `lsp-setup`, `litgoal`,
+  `deep-interview`, `hyperplan`, `init-deep`, `litresearch`,
+  `lit-plan`, `lit-recap`, `lit-loop`, `start-work`, and `visual-qa`
+- **Auxiliary Skill-discovery entries** - `frontend-ui-ux`, `git-master`,
+  `lsp-setup`, and `visual-qa` are shipped skill ids discoverable through
+  Claude Code's native Skill discovery; they intentionally do not add extra
+  slash or dollar prompt routes
 - **Auxiliary workflow packs** - ships `programming/references`,
   `programming/scripts`, and `debugging/references` for deeper language and
   runtime guidance
@@ -113,7 +120,7 @@ directory, the normal install command works:
 
 ```bash
 cd /tmp
-npx --yes litclaude-ai@0.3.22 install
+npx --yes litclaude-ai@0.3.26 install
 ```
 
 Validate the installed plugin:
@@ -126,7 +133,7 @@ The installer also sets Claude Code's `statusLine` command to the packaged
 LitClaude HUD. A typical no-color render starts like:
 
 ```text
-[🔥LITCLAUDE v0.3.22] | O4.8 │ ctx [▎░░] 9%/1000k │ 5h [▏░] 4% ↻2h15m │ 1w [▊░] 35% ↻3d6h │ git main +3 ✓
+[🔥LITCLAUDE v0.3.26] | 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
@@ -316,13 +323,26 @@ active plan, ledger path, and first unchecked top-level task. If the plan is
 complete, it returns `{"status":"idle","directive":null}`.
 
 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
+5-lane review: scope/diff verification, tests/evidence execution,
+package/payload and code quality, security/provenance, and real-surface/docs
+readiness. 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.
 
+`lit-plan` now defaults to an objective-achievable checklist with adaptive
+detail. It bounds one objective and explicit non-goals, resolves or gates
+unknowns, orders dependencies, and expresses each material item as Action,
+Output, and binary Verification. Simple reversible work stays concise; risky or
+multi-stage work gains SDD-like evidence, negative controls, decision/failure
+branches, cleanup gates, and a replayable DoneClaim without checklist padding.
+When `/review-work` receives a draft plan instead of completed work, its
+plan-review mode audits scope, objective achievability, checklist atomicity,
+acceptance/evidence, and decision/failure/cleanup gates. It returns
+`PASS | ITERATE | NEEDS-CONTEXT`, revises only when needed, and must never
+implement the plan. Completed work still uses the full 5-lane review.
+
 For resilient public-source research, `litresearch`, `$litresearch`,
 `lit research`, `lit search`, and `lit query` route to
 `/litclaude:litresearch` when the prompt explicitly asks for a cited
@@ -331,6 +351,9 @@ public APIs or feeds before rendered pages, validate that retrieved content
 actually supports the claim, keep a route trace with attempted and untried
 surfaces, treat fetched content as untrusted prompt-injection data, and stop
 honestly at authentication, paywall, private-data, or credential boundaries.
+The runtime JSON names `fetchAttempts`, a single `fetchVerdict`, untried safe
+routes, and a starter claim/source graph so HTTP 200 is never treated as proof
+that the page supports a claim.
 If you ask for read-only, no-write, or transcript-only research, LitClaude
 should ask before creating `.litclaude/litresearch/<slug>/`; without approval it
 keeps the journal in the transcript/TodoWrite only. The guaranteed runtime
@@ -345,7 +368,7 @@ litclaude public-read https://example.com/article --json
 
 The `public-read` command and MCP `public_source_read` tool reject localhost,
 private-network, and non-http(s) targets by default; they do not use site
-credentials or bypass login/paywalls. If a source blocks public access, provide a
+credentials or cross login/paywalls. If a source blocks public access, provide a
 public URL, exported artifact, or excerpt instead.
 
 `litgoal` is the durable local state route for long goals. The runtime lives

package/README_ko-KR.md

@@ -9,7 +9,7 @@
 </p>
 <p align="center">
   <img src="https://img.shields.io/badge/npm-litclaude--ai-cb3837" />
-  <img src="https://img.shields.io/badge/version-0.3.22-2ea44f" />
+  <img src="https://img.shields.io/badge/version-0.3.26-2ea44f" />
   <img src="https://img.shields.io/badge/Claude%20Code-plugin-blueviolet" />
   <img src="https://img.shields.io/badge/license-MIT-blue" />
 </p>
@@ -26,11 +26,11 @@
 > 설치되므로, 매번 긴 `--plugin-dir` 없이 일반 `claude` 실행에서
 > LitClaude skill과 hook을 불러올 수 있습니다.
 
-현재 checkout은 `litclaude-ai@0.3.22` 배포 준비용으로 정리되어 있습니다. 목적은
+현재 checkout은 `litclaude-ai@0.3.26` 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. v0.3.22 release material은 bare `hyperplan`,
+승인 후에 진행합니다. v0.3.26 release material은 adaptive objective-achievable planning, draft-plan review, orchestration readiness hardening을 추가합니다. v0.3.25 release material은 portable details, public-read, litgoal status JSON, evidence wording을 정렬합니다. v0.3.24 release material은 auxiliary skill inventory와 advisory probe를 정렬합니다. v0.3.23 release material은 bare `hyperplan`,
 `litresearch`, `lit research`, `init-deep`, explicit `$start-work` prompt-hook route에
 bundled skill body를 주입하면서, v0.3.19 adversarial planning
 skill, v0.3.18 read-only `lit-recap` session recap surface, v0.3.17 별도 worker 기반 native `/goal`
@@ -64,8 +64,9 @@ litresearch activation/read-only polish를 유지합니다.
 - **v0.3.13 public-source reader runtime** - `litclaude public-read <url> --json`와
   MCP `public_source_read`가 SSRF/private-host guard, auth/paywall stop reason,
   metadata/JSON-LD fallback, route evidence를 제공하는 JS-only public page reader를 추가
-- **5-lane review** - `/review-work`가 goal/constraint verification,
-  hands-on QA execution, code quality, security, local-first context mining을
+- **5-lane review** - `/review-work`가 scope/diff verification,
+  tests/evidence execution, package/payload and code quality,
+  security/provenance, real-surface/docs readiness를
   한 번에 점검
 - **Native goal guidance** - Claude Code가 `/goal` 또는 `get_goal`,
   `create_goal`, `update_goal` 같은 goal surface를 제공하면 이를 우선
@@ -75,11 +76,17 @@ litresearch activation/read-only polish를 유지합니다.
   아래에 기록
 - **Dynamic workflow/worktree guidance** - 크거나 병렬적인 작업은 Claude
   Code Dynamic workflow, subagent delegation, Dynamic worktree 격리 쪽으로 유도
+- **관측 가능한 orchestration gate** - `workflow-check --json`은 로컬에서 확인 가능한 환경변수, 사용자/프로젝트 설정, macOS/Linux managed-policy 파일이 workflow/background task를 끄거나 tool concurrency가 사실상 직렬이면 실패합니다. 원격 조직 정책은 로컬에서 관측할 수 없다고 명시하므로, 로컬 PASS가 원격 관리자의 deny를 무효화한다는 뜻은 아닙니다. Claude Code 2.1.207의 workflow 상한(동시 16, 누적 1000), 비용이 발생하는 `acceptEdits` worker, lead당 team 1개, teammate graceful shutdown, resume 후 orphan tmux 재확인을 명시적 lifecycle 제약으로 다룹니다.
 - **Claude skills** - LitClaude 스타일을 더 풍부하게 옮긴 corpus:
   `programming`, `debugging`, `refactor`, `ai-slop-remover`, `remove-ai-slops`,
   `korean-ai-slop-remover`, `review-work`, `frontend-ui-ux`,
-  `comment-checker`, `rules`, `lsp`, `litgoal`, `deep-interview`, `hyperplan`,
-  `lit-plan`, `lit-recap`, `lit-loop`, `start-work`
+  `git-master`, `comment-checker`, `rules`, `lsp`, `lsp-setup`, `litgoal`,
+  `deep-interview`, `hyperplan`, `init-deep`, `litresearch`,
+  `lit-plan`, `lit-recap`, `lit-loop`, `start-work`, `visual-qa`
+- **Auxiliary Skill-discovery entries** - `frontend-ui-ux`, `git-master`,
+  `lsp-setup`, `visual-qa`는 Claude Code native Skill discovery로 찾는
+  shipped skill id입니다. 별도의 slash route나 dollar prompt route를 추가하지
+  않습니다.
 - **Auxiliary workflow packs** - `programming/references`,
   `programming/scripts`, `debugging/references`까지 포함해서 언어별,
   런타임별 세부 지침을 보존
@@ -117,7 +124,7 @@ checkout을 먼저 해석해서 `sh: litclaude-ai: command not found`로 실패
 
 ```bash
 cd /tmp
-npx --yes litclaude-ai@0.3.22 install
+npx --yes litclaude-ai@0.3.26 install
 ```
 
 설치 상태를 확인합니다.
@@ -130,7 +137,7 @@ installer는 Claude Code의 `statusLine` command도 packaged LitClaude HUD로
 설정합니다. 색상을 제거한 예시는 다음처럼 시작합니다.
 
 ```text
-[🔥LITCLAUDE v0.3.22] | O4.8 │ ctx [▎░░] 9%/1000k │ 5h [▏░] 4% ↻2h15m │ 1w [▊░] 35% ↻3d6h │ git main +3 ✓
+[🔥LITCLAUDE v0.3.26] | O4.8 │ ctx [▎░░] 9%/1000k │ 5h [▏░] 4% ↻2h15m │ 1w [▊░] 35% ↻3d6h │ git main +3 ✓
 ```
 
 `↻` 표시는 rate-limit reset까지 남은 시간을 짧게 보여주는 countdown입니다.
@@ -296,13 +303,26 @@ plan, ledger path, 첫 번째 unchecked top-level task를 출력합니다. Plan
 `{"status":"idle","directive":null}`을 반환합니다.
 
 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
+review는 scope/diff verification, tests/evidence execution,
+package/payload and code quality, security/provenance,
+real-surface/docs readiness를 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.
 
+`lit-plan`은 이제 adaptive detail을 적용한 objective-achievable checklist를
+기본으로 만듭니다. 하나의 bounded objective와 명시적 non-goals를 고정하고,
+unknown을 해소하거나 gate로 전환하며, dependency 순서에 따라 각 핵심 항목을
+Action, Output, binary Verification으로 작성합니다. 단순하고 되돌릴 수 있는
+작업은 짧게 유지하고, 위험하거나 multi-stage인 작업만 SDD-like evidence,
+negative control, decision/failure branch, cleanup gate, replayable DoneClaim을
+갖춥니다. checklist padding은 추가하지 않습니다. `/review-work`가 완료된 diff가
+아니라 draft plan을 받으면 plan-review mode로 scope, objective achievability,
+checklist atomicity, acceptance/evidence, decision/failure/cleanup gate를 점검합니다.
+`PASS | ITERATE | NEEDS-CONTEXT` 중 하나를 반환하며, 필요한 부분만 수정하고
+plan을 must not implement 합니다. 완료된 작업은 기존 5-lane review를 유지합니다.
+
 공개 소스 조사(public-source research)가 필요할 때 `litresearch`,
 `$litresearch`, `lit research`, `lit search`, `lit query`는 명시적인 cited
 investigation 요청에 한해 `/litclaude:litresearch`로 라우팅됩니다. Web lane은

package/RELEASE_CHECKLIST.md

@@ -1,7 +1,10 @@
 # LitClaude Release Checklist
 
-Status: `litclaude-ai@0.3.22` is the current release candidate — a full bare
-skill-body prompt-hook routing release on top of the planning-only Hyperplan skill and read-only `lit-recap`
+Status: `litclaude-ai@0.3.26` is the current release candidate — an adaptive
+planning, draft-plan review, and orchestration-safety release on top of the portable
+details, public-read, litgoal-status, and evidence-wording release and the auxiliary
+skill inventory and advisory-probe release and the full bare
+skill-body prompt-hook routing release, planning-only Hyperplan skill, and read-only `lit-recap`
 session recap surface (command, skill, and bounded hook routing
 including the Korean `리캡` trigger), the dry-run-first native `/goal`
 worker launcher, WSL2 HUD gradient hotfix, Korean AI-slop removal workflow
@@ -12,9 +15,9 @@ side-effect-free, the launcher starts only a separate Claude Code
 print/background worker, and the release preserves the Korean polishing
 command, strict multi-agent review pipeline, fidelity guardrails, package
 hygiene checks, native route gates, and safe start-work handoff behavior.
-`package.json` is aligned to `0.3.22`,
-`plugins/litclaude/.claude-plugin/plugin.json` is aligned to `0.3.22`, and the
-plugin-local MCP server reports `0.3.22`.
+`package.json` is aligned to `0.3.26`,
+`plugins/litclaude/.claude-plugin/plugin.json` is aligned to `0.3.26`, and the
+plugin-local MCP server reports `0.3.26`.
 
 This release carries the v0.2.2 Dynamic workflow hardening surfaces:
 `/dynamic-workflow`, `workflow-check --json`, native `/goal` fallback guidance,
@@ -63,9 +66,9 @@ No npm publication is required for this track.
 Before requesting publication approval, confirm these artifacts from the current
 checkout:
 
-- `package.json` version is `0.3.22`.
-- `plugins/litclaude/.claude-plugin/plugin.json` version is `0.3.22`.
-- `plugins/litclaude/bin/litclaude-mcp.js` reports server version `0.3.22`.
+- `package.json` version is `0.3.26`.
+- `plugins/litclaude/.claude-plugin/plugin.json` version is `0.3.26`.
+- `plugins/litclaude/bin/litclaude-mcp.js` reports server version `0.3.26`.
 - Prompt-hook tests cover bundled `SKILL.md` body injection for bare `hyperplan`, `litresearch`, `lit research`, `init-deep`, and explicit `$start-work`, while natural-language `lit start work` stays BLOCKED.
 - `lit search` and `lit query` route to `/litclaude:litresearch` without activating on slash mentions, code spans, or non-lit prompts.
 - Litresearch web lanes require public API/feed preference, validator-first checks, route traces, prompt-injection quarantine, and honest auth/paywall/private-data stop reasons.
@@ -80,6 +83,12 @@ checkout:
 - PostToolUse hook tests cover patch-shaped mutated-file extraction.
 - SessionStart hook tests cover context-pressure resume guidance.
 - `plugins/litclaude/commands/review-work.md` documents the 5-lane review.
+- `plugins/litclaude/commands/lit-plan.md` documents adaptive
+  Action/Output/Verification checklists and a DoneClaim without fixed checklist
+  padding.
+- `plugins/litclaude/commands/review-work.md` distinguishes plan-review mode
+  (`PASS | ITERATE | NEEDS-CONTEXT`, no implementation) from the completed-work
+  5-lane review.
 - `plugins/litclaude/commands/litgoal.md` documents durable goal state.
 - `plugins/litclaude/lib/litgoal/` ships the runtime CLI/state modules.
 - `node bin/litclaude-ai.js litgoal --help` prints durable state commands.

package/bin/litclaude-ai.js

@@ -35,7 +35,7 @@ Commands:
   litgoal       Manage litgoal runtime state and evidence.
   workflow-check Verify Dynamic workflow, /goal, and subagent delegation readiness.
   start-work-next Print the next active start-work continuation directive.
-  public-read   Read a public http(s) source with SSRF/auth safety stops.
+  public-read   Read a public http(s) source with FetchAttempt/FetchVerdict JSON.
   update        Reinstall this package version and refresh the Claude plugin registry.
   uninstall     Remove LitClaude-managed install state.
 
@@ -501,6 +501,28 @@ const commandExists = (command) => {
   return !result.error;
 };
 
+const escapeRegex = (value) => value.replace(/[.*+?^${}()|[\]\\]/gu, "\\$&");
+
+const assertCurrentPluginDetails = (detailsOutput) => {
+  const missing = [];
+  if (!new RegExp(`\\b${escapeRegex(version)}\\b`, "u").test(detailsOutput)) {
+    missing.push(`expected version ${version}`);
+  }
+
+  const agentsMatch = detailsOutput.match(/Agents\s+\((\d+)\)/u);
+  if (!agentsMatch || Number(agentsMatch[1]) < 1 || !/\bprometheus-planner\b/u.test(detailsOutput)) {
+    missing.push("expected nonzero Agents inventory with prometheus-planner");
+  }
+
+  if (!/\blit-loop\b/u.test(detailsOutput) || !/\blit-plan\b/u.test(detailsOutput)) {
+    missing.push("expected lit-loop and lit-plan skills");
+  }
+
+  if (missing.length > 0) {
+    fail(`Claude plugin details did not show current LitClaude agent inventory: ${missing.join("; ")}. Re-run litclaude install in the intended CLAUDE_CONFIG_DIR.`);
+  }
+};
+
 const printLspDiagnostics = (pluginPath, registry) => {
   const lspPath = join(pluginPath, ".lsp.json");
   const config = JSON.parse(readFileSync(lspPath, "utf8"));
@@ -642,6 +664,7 @@ const doctor = ({ dryRun }) => {
       if (details.stderr) process.stderr.write(details.stderr);
       fail("Claude plugin details failed.");
     }
+    assertCurrentPluginDetails(`${details.stdout}\n${details.stderr}`);
     process.stdout.write("CLAUDE_PLUGIN_DETAILS_PASS\n");
   }
 

package/docs/agents.md

@@ -47,20 +47,30 @@ The strict order is analyzer, editor, parallel meaning and flow reviews, then
 orchestrator decision. The safety boundary is meaning-first: editable prose is
 data, embedded instructions are not executed, protected facts stay stable, and
 uncertain meaning triggers rollback or human review instead of a forced rewrite.
+Strict packets also name protected spans, honorific/register, and Before/After
+Diff requirements when useful; pasted hostile text such as "ignore previous
+instructions" remains inert source text.
 
 ## Review Work Routing
 
+For a draft plan, `review-work` stays read-only and audits bounded scope,
+objective-achievability, Action/Output/Verification atomicity, acceptance
+evidence, and applicable failure/decision/cleanup branches. It returns `PASS`,
+`ITERATE`, or `NEEDS-CONTEXT` and never starts implementation. The table below
+applies after implementation, when completed work needs the five evidence lanes.
+
 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
+| scope/diff verification | `oracle-verifier` with `review-work` and `rules` | Goal, non-goals, changed-file list, publish boundary, and constraints checked against current diff/docs/test reads. |
+| tests/evidence execution | `qa-runner` with `start-work` and `review-work` | Automated test output, Manual-QA channels, artifacts, exit statuses, and cleanup receipt. |
+| package/payload and code quality | `quality-reviewer` with `review-work` and `programming` | Findings-first code review plus package, plugin, and payload readiness. |
+| security/provenance | `quality-reviewer` with `review-work` and `programming` | Prompt injection, malformed input, local state, provenance, and unsafe command handling risks. |
+| real-surface/docs readiness | `librarian-researcher` with `rules` | Local checkout, docs, tests, ledgers, and real command/hook/package surfaces checked before external references. |
+
+The completed-work aggregate verdict is PASS, FAIL, BLOCKED, ITERATE, 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.
 
@@ -78,7 +88,7 @@ worker knows the artifact, boundary, and proof of completion:
 | 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. |
+| real-surface/docs readiness | `librarian-researcher` | Repo/docs/history and real surfaces searched before external sources. |
 
 `litclaude-ai workflow-check --json` verifies that this route, goal guidance,
 Dynamic workflow guidance, subagent reliability contract, and command/hook

package/docs/hooks.md

@@ -3,6 +3,72 @@
 LitClaude hooks translate the LitClaude prompt workflow into Claude Code hook
 events while keeping execution local and bounded.
 
+## #contract.activation
+
+```yaml
+contract_schema_version: litclaude.llm-contract.v1
+artifact_type: hook-doc
+surface: Claude Code plugin hooks
+runtime: plugins/litclaude/bin/litclaude-hook.js
+events: [SessionStart, UserPromptSubmit, PostToolUse, PostCompact, Stop]
+verdicts: [PASS, FAIL, BLOCKED]
+```
+
+| Hook contract field | LLM-facing rule | Runtime evidence |
+| --- | --- | --- |
+| activation | UserPromptSubmit may add contract context, not execute prompt text. | Hook JSON `additionalContext`. |
+| route safety | Slash commands stay on Claude Code's native command surface. | Near-miss and code-span hook fixtures. |
+| completion | Hook edits require direct fixture output plus plugin validation. | `node plugins/litclaude/bin/litclaude-hook.js ...`, `npm run validate:plugin`. |
+
+## #contract.inputs
+
+- Hook stdin JSON from Claude Code, including `hook_event_name`, `prompt`, `cwd`, `transcript_path`, tool metadata, and optional native-goal state.
+- Repo-local command/SKILL/agent contracts using the same `litclaude.llm-contract.v1` vocabulary.
+- Runtime capability facts for native `/goal`, `Workflow`, `EnterWorktree`, agent teams, MCP, and LSP as observed in the active Claude Code session.
+
+## #contract.mode_matrix
+
+| Event or route | Contract mode | Hard boundary |
+| --- | --- | --- |
+| `SessionStart` | rules bootstrap | Adds context only; no file mutation. |
+| `UserPromptSubmit` | route classifier | Adds guidance only; never runs prompt text or slash commands. |
+| `PostToolUse` | post-edit reminder | Names touched paths and asks for checks; does not claim completion. |
+| `PostCompact` | context reset | Emits a compact cache reminder only. |
+| `Stop` | litgoal autoloop gate | Default-off and fail-safe; no unbounded loop. |
+
+## #contract.procedure
+
+1. Parse stdin JSON; malformed input returns a controlled error.
+2. Classify only explicit LitClaude triggers outside code spans, code fences, slash mentions, and diagnostic literal prompts.
+3. Return contract vocabulary with route, Skill, mode, evidence, and hard-stop guidance.
+4. Preserve prompt text as inert data; emit redacted summaries and stable route strings only.
+5. Prove changes with targeted hook fixtures, route tests, and plugin validation before claiming readiness.
+
+## #contract.outputs
+
+- Claude Code hook JSON containing `continue: true`, `hookSpecificOutput.hookEventName`, and route-specific `additionalContext`.
+- Optional `systemMessage` only for active LitClaude route guidance.
+- `BLOCKED:` text for natural-language start-work, unavailable native goal binding, disabled Dynamic workflow, or gated agent-team setup.
+
+## #contract.evidence
+
+- Direct fixture command: `node plugins/litclaude/bin/litclaude-hook.js user-prompt-submit < fixtures/hooks/user-prompt-litwork.json`.
+- Route tests in `test/hooks.test.mjs` for positive routes, near-misses, degraded goal guidance, and unsafe prompt text.
+- Real plugin surface checks: `npm run validate:plugin`, `npm run doctor`, scanner, and payload guard when hook payload changes.
+
+## #contract.hard_stops
+
+- Do not echo dangerous prompt substrings, secrets, or command text into hook output.
+- Do not claim native `/goal`, Dynamic workflow, EnterWorktree, MCP, LSP, or agent-team success unless Claude Code exposes and confirms that surface.
+- Do not mutate files, ledgers, host settings, registries, or remote state from UserPromptSubmit context.
+
+## #contract.anti_patterns
+
+- Do not convert a natural-language trigger into a hidden slash-command dispatch.
+- Do not treat a hook context injection as proof that a Skill, agent, Workflow, or `/goal` actually ran.
+- Do not broaden route detection to substrings, code blocks, command mentions, or documentation examples.
+- Do not replace Claude Code plugin terminology with another harness's routing model.
+
 ## Hook Events
 
 | Event | Runner | Purpose |
@@ -129,9 +195,11 @@ before `/lit-plan` when a request lacks non-goals, decision boundaries, or
 acceptance criteria.
 
 `/review-work` and `$review-work` load `/litclaude:review-work` /
-`Skill(review-work)`. That route runs the v0.2.0 workflow parity 5-lane review:
-goal/constraint verification, hands-on QA execution, code quality, security,
-and local-first context mining. `/litgoal` and `$litgoal` load
+`Skill(review-work)`. For a draft plan, that route performs a read-only
+objective-achievability audit and returns `PASS`, `ITERATE`, or `NEEDS-CONTEXT`
+without implementing. For completed work it runs the 5-lane review: scope/diff
+verification, tests/evidence execution, package/payload and code quality,
+security/provenance, and real-surface/docs readiness. `/litgoal` and `$litgoal` load
 `/litclaude:litgoal` / `Skill(litgoal)` for durable local goal state and
 the litgoal CLI.
 
@@ -154,9 +222,11 @@ paywall, private-data, or credential boundaries. If the user requests read-only,
 no-write, or transcript-only research, ask before creating
 `.litclaude/litresearch/<slug>/` and otherwise keep the journal in the
 transcript/TodoWrite. The guaranteed runtime surface is direct public URL reads
-through `public_source_read` or `litclaude public-read`; Dynamic `Workflow`,
-`/deep-research`, browsing, and namespaced subagents are host-dependent and need
-fallbacks.
+through `public_source_read` or `litclaude public-read`; its JSON includes
+`fetchAttempts`, `fetchVerdict`, untried safe routes, and a starter claim graph
+so HTTP 200 is not treated as success without content validation. Dynamic
+`Workflow`, `/deep-research`, browsing, and namespaced subagents are
+host-dependent and need fallbacks.
 
 ## Safety