docs(web-tasks): タスク台帳を定期更新台帳へ改訂し無人可マークと weekly-review 接続を追加 (WP-18 PR 2)

.takt/facets/instructions/review-todo-whole.md

@@ -1,4 +1,4 @@
-Focus on **whole-tree todo hygiene** — the health of the planning corpus (`docs/todo.md` + `docs/todo2.md` … `docs/todo13.md` + `docs/todo-summary.md`) taken as a whole. This facet is invoked by the weekly-review workflow (ADR-031、観点⑤ Todo 妥当性) and reviews the entire todo corpus, not a diff.
+Focus on **whole-tree todo hygiene** — the health of the planning corpus (`docs/todo.md` + `docs/todo2.md` … `docs/todo13.md` + `docs/todo-summary.md` + `docs/claude-code-web-tasks.md`) taken as a whole. This facet is invoked by the weekly-review workflow (ADR-031、観点⑤ Todo 妥当性) and reviews the entire todo corpus, not a diff.
 
 This is the **weekly batch** counterpart to the edit-time todo hooks. It exists because the deterministic layer only sees the entry being touched right now; it cannot see the corpus-wide decay that accumulates across dozens of untouched entries.
 
@@ -15,7 +15,7 @@ Your job is the **broad, cross-file, time-based decay** none of the above can se
 
 ## Reading the corpus
 
-1. `Glob docs/todo*.md` + `docs/todo-summary.md` — enumerate the whole corpus and note sizes.
+1. `Glob docs/todo*.md` + `docs/todo-summary.md` + `docs/claude-code-web-tasks.md` — enumerate the whole corpus and note sizes.
 2. Read `docs/todo.md` の preamble (冒頭の使い分けルール) first — it defines the routing contract (新規は todo6.md へ、編集専用は todo2-7.md、順位 table は todo-summary.md 等).
 3. Sample the largest / oldest-looking files. Use `Grep` to follow task titles / 順位 numbers / `WR-` ids across files.
 4. Cross-check the `docs/todo-summary.md` 順位 table against the detail entries it points to (`| N | Tier | title | todoX.md | ... |`).
@@ -50,6 +50,22 @@ The `docs/todo.md` preamble encodes a routing contract that silently rots:
 - A file described as "編集専用・新規追加しない" that has in fact received new entries.
 - Preamble file enumeration (「本ファイル + todo2.md + … の使い分け」) that omits or miscounts an existing `docs/todo*.md` file.
 
+## Criterion 3: 自律実行台帳 (`docs/claude-code-web-tasks.md`) の鮮度
+
+This ledger is **read by the nightly todo loop (WP-18) as its task-selection source**, so its decay has a consequence the rest of the corpus does not have: a stale row can send an unattended agent to implement something already done, or something whose intent nobody has settled. The ledger's own § ライフサイクル designates this weekly review as the place where its freshness is checked.
+
+Check three things, in this order:
+
+1. **Landed-but-listed rows** — for each 順位 in the ledger's tables, `Grep` the same 順位 in `docs/todo-summary.md` / `docs/todo-summary2.md`. A row present in the ledger but **absent from both 順位 tables** has landed and should be removed (with the evidence recorded in the ledger's § 棚卸し履歴). Verify the task really landed (grep the artifact it claims to produce) before raising — a 順位 can also disappear because it was deprioritized.
+2. **Promotion candidates** — 順位 rows in `docs/todo-summary*.md` that satisfy the ledger's § 採用タスク (2) criteria (verifiable by `cargo test --workspace`, no real Windows hook / `pnpm push` e2e, no cwd-dependent `#[ignore]` dependency) but are **not yet listed** in the ledger. Name the 順位 and which criterion you checked. Do not propose promotion on title alone — read the detail entry.
+3. **無人可 marks that no longer hold** — this is the check nothing else can perform, because it depends on state **outside the corpus**. For every row marked `✅ 無人可`, confirm condition 3 of the ledger's § 自律実行可否の 2 段階分類 (no duplicate work in flight): use `jj log` and remote bookmark inspection to look for an unmerged branch or in-flight PR implementing the same task. A mark whose task now has an implementation branch must be raised — the nightly loop would otherwise duplicate it. Also re-read the row's 注意 column against conditions 1 and 2 (no 「再選定」「着手時判断」「見積り」「検討」; implementation uniquely determined); a row whose 注意 text has been edited since marking may no longer qualify.
+
+   **Absence of evidence is not evidence of absence here.** Unlike Criterion 0/1/2, this check reads state outside the repository (remote bookmarks, PR status), which can be unreachable — no network, no `gh` auth, a shallow or non-colocated clone. If you cannot actually observe remote/PR state, report condition 3 for that row as **unverified** and say which lookup failed. Do **not** write it up as "no duplicate found": a silent downgrade from "could not check" to "checked, clean" is exactly how a stale mark survives into the nightly loop. Reporting unverified is the correct advisory-layer behavior — this facet blocks nothing, so the cost of saying so is one line in the report.
+
+Severity guidance for this criterion: a stale `✅ 無人可` mark is `high` (it can cause an unattended agent to do conflicting or duplicate work); an **unverified** condition 3 is `medium` (the mark may be fine, but nobody has confirmed it this cycle); landed-but-listed rows and missing promotions are `low`–`medium` (ledger noise).
+
+**Do not propose adding or removing a `✅ 無人可` mark yourself as a settled decision** — the ledger states the marks are set by a human (ADR-022). Raise the finding with evidence and let the `/weekly-review` adoption step carry it to the user.
+
 ## Calibration
 
 Resist checklist-thinking. The edit-time hooks + cli-docs-lint + file-length-watchlist already enforce the objective, per-entry, per-link, per-size rules. This facet earns its keep only on corpus-wide, time-based, cross-file decay that no single edit can surface. If you can only flag something by a mechanical rule the deterministic layer already runs, flag the *layer gap*, not the instance.
@@ -59,7 +75,7 @@ If a finding needs natural-language judgment about task intent (「これはも
 ## Judgment procedure
 
 1. Glob the corpus + read the `docs/todo.md` preamble (routing contract).
-2. For Criterion 0/1/2, gather evidence with `Grep` / `jj log` — never raise a corpus-decay finding without a verified pointer.
+2. For Criterion 0/1/2/3, gather evidence with `Grep` / `jj log` — never raise a corpus-decay finding without a verified pointer.
 3. For each finding, articulate: what it is, where it lives (file + entry title/順位), the verifying evidence, and the proposed action (remove / merge / re-route / re-number).
 4. Classify each finding by severity (`critical` / `high` / `medium` / `low`) per ADR-031 § Findings スキーマ. Todo-hygiene findings are typically `low`–`medium` (corpus noise, not production risk); reserve `high` for a duplicate that could cause conflicting work.
 5. Write the report per the output contract (`review-todo-whole.md`). End with `analysis complete`.
@@ -68,6 +84,6 @@ If a finding needs natural-language judgment about task intent (「これはも
 
 - File: `review-todo-whole.md` (Report Directory)
 - Format identifier: `review-todo-whole`
-- Read-only (`edit: false`): report findings only; the `/weekly-review` skill + user decide adoption (never edit `docs/todo*.md` from this facet).
-- Category hint for aggregate-weekly: use `todo-dead-entry` / `todo-duplicate` / `todo-preamble-drift` (aggregate normalizes into the ADR-031 category set).
+- Read-only (`edit: false`): report findings only; the `/weekly-review` skill + user decide adoption (never edit `docs/todo*.md` or `docs/claude-code-web-tasks.md` from this facet — the ledger's 無人可 marks in particular are a human decision).
+- Category hint for aggregate-weekly: use `todo-dead-entry` / `todo-duplicate` / `todo-preamble-drift` / `ledger-staleness` (aggregate normalizes into the ADR-031 category set).
 - If nothing survives evidence-gathering, output「特筆すべき todo-hygiene の findings なし」and end with `analysis complete` (do not manufacture findings).

.takt/workflows/weekly-review.yaml

@@ -131,6 +131,9 @@ steps:
       # 観点 ⑤ Todo 妥当性 (ADR-031 拡張、順位154)。docs/todo*.md 全 corpus の
       # dead pattern / cross-file 重複 / preamble routing drift を週次 batch で棚卸し。
       # 順位136 hook (編集時 immediate) / cli-docs-lint が拾えない経年・横断的劣化を補完。
+      # 2026-08-06 (WP-18 PR 2): docs/claude-code-web-tasks.md の鮮度検査を追加。同台帳は
+      # 夜間 todo 消化ループのタスク選択元で、stale な 無人可 マークが無人 agent の重複実装を
+      # 招く。台帳の lifecycle が本 step を定期棚卸しの場として指名している。
       - name: review-todo-whole
         edit: false
         persona: architecture-reviewer