task-stocktake

task-stocktake is a skill for Claude Code from shimo4228/claude-harness. It costs 160 tokens per session (4,586 once invoked), scanned A, original, MIT.

A task-ledger audit for a software repository. A task ledger is one file that records pending and completed work; this workflow finds scattered task notes and consolidates them there.

In plain words
What is it for?
Use it to create or locate the repository's task ledger, collect pending tasks from handoff notes and memory, verify their status, and record the results.
Why use it?
It removes uncertainty about which task list is current and checks listed work against the code and git history. It also archives detail files for tasks that are already finished.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md.

Good fit Use it to create or locate the repository's task ledger, collect pending tasks from handoff notes and memory, verify their status, and record the results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shimo4228/claude-harness/task-stocktake
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add shimo4228/claude-harness --skill task-stocktake
Clone the repo
git clone --depth 1 https://github.com/shimo4228/claude-harness

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for task-stocktake

README.md
[![agentmods](https://agentmods.dev/badge/skills/shimo4228/claude-harness/task-stocktake/github.svg)](https://agentmods.dev/skills/shimo4228/claude-harness/task-stocktake)
Your own site
<a href="https://agentmods.dev/skills/shimo4228/claude-harness/task-stocktake"><img src="https://agentmods.dev/badge/skills/shimo4228/claude-harness/task-stocktake/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for task-stocktake

Your own site · 80×15
<a href="https://agentmods.dev/skills/shimo4228/claude-harness/task-stocktake"><img src="https://agentmods.dev/badge/skills/shimo4228/claude-harness/task-stocktake.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 160 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,586 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00160 $0.04586
Opus 5 $0.00080 $0.02293
Sonnet 5 $0.00032 $0.00917
Haiku 4.5 $0.00016 $0.00459

Measured 3d ago against content hash 5c173d66f2e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

task-stocktake scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/task-stocktake/SKILL.md · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

task-stocktake — Task Ledger Audit & Consolidation

repo の pending タスク追跡を単一台帳に収束させ、台帳の鮮度を git 実態と突合する。 原則の正本は rule common/task-tracking.md(台帳は 1 repo 1 ファイル / 詳細資料に タスク行の正本を持たせない / MEMORY.md はポインタのみ)。本 skill はその手順を持つ。

Phase 1 — Bootstrap(台帳の解決・作成)

  1. 台帳を解決する: .notes/TASKS.md → 既存タスクファイル(TODO.md / TASKS.md / docs/backlog.md 等)の順
  2. 見つかればそれを台帳と確定して Phase 2 へ
  3. 無ければ作成する。「作るか」は聞かない(skill の起動自体が依頼)— 確認するのは置き場所だけ:
    • .notes/ 慣行がある repo は .notes/TASKS.md(gitignored = private)に即決。 無い repo は gitignore 状況を見て private / git-tracked(clone 先でも cold-start 可能)の トレードオフを提示して選んでもらう
    • 初期内容: Phase 2 の sweep 結果を集約して生成

台帳フォーマット(1 タスク 1 行):

# TASKS — <repo name>

> 正本: このファイル。詳細はリンク先。規約: rule common/task-tracking.md

## Pending

| ID | 状態 | タスク | 着手条件 | 詳細 |
|----|------|--------|----------|------|
| T1 | accepted | … | なし | [handoff-….md](…) |
| T2 | blocked | … | 次リリース後 | … |

## Done / Withdrawn

| ID | 結果 | タスク | 完了日 / 判断 | 詳細 |

状態語彙(この skill が正本)

開いている状態は 4 つ。この節が語彙の唯一の正本 — rule / ADR / 他 skill は ここを参照し、定義を複製しない(4 文書に分散した版は誰も刈らず 6 語まで肥大した。 CA 2026-08-16)。語は標準語彙(RFC 標準 + issue-tracker 標準 — 非標準語彙は セッションごとに写像がずれる。ADR-0050)。

状態 定義
draft 採否判断がまだ要る。やるかどうかを決めていない
accepted 採用済みで、今選べば着手できる
in_progress claim 中
blocked 採用済みで、条件成立だけで accepted になる

終端は done / resolved / rejected / withdrawn / obsoleted(下節)。

blocked の入場条件

blocked に置けるのは、本文に次の 3 つを書けるタスクだけ。自由記述の一文でよく、 機械可読フィールドにはしない(台帳を読む機構を足さない — CA ADR-0095)。

再開条件: X(観測可能な事実)
照合先:   Y(PR 番号 / ファイルパス / 依存タスク ID / ログ)
成立時:   accepted

「条件が成立したらもう一度やるか決める」ものは blocked ではないdraft。 この 1 問が効く: 条件成立だけで accepted に移せるか。 移せないなら採否がまだ残っている。

  • 「実害が起きたら考える」型(signal-first)は多くが draft。現時点で受容した リスクであり、発生すれば自然に再発見されるものは将来の自分への予告として保持しないwithdrawn にして起票し直す方が安い
  • 「必要になったら」「保守コストが顕在化したら」「該当領域の再設計サイクルが立ったら」は 文法上は名指しているが照合できない。照合先を書けないなら blocked に入れない

Read the full file on GitHub · 237 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago Changed · -3 lines 5c173d66f2e9
  2. 8d ago First seen · 240 lines · 160 tokens per session scan A 20452a6487b9

Subscribe to this mod's changes

task-stocktake is a skill published in the GitHub repository shimo4228/claude-harness (2 stars, last pushed 3d ago), licensed MIT. It adds 160 tokens to every session and 4,586 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.