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.
npx skills add shimo4228/claude-harness --skill implementation-chaingit clone --depth 1 https://github.com/shimo4228/claude-harnessWrote 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.
[](https://agentmods.dev/skills/shimo4228/claude-harness/implementation-chain)<a href="https://agentmods.dev/skills/shimo4228/claude-harness/implementation-chain"><img src="https://agentmods.dev/badge/skills/shimo4228/claude-harness/implementation-chain/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.
<a href="https://agentmods.dev/skills/shimo4228/claude-harness/implementation-chain"><img src="https://agentmods.dev/badge/skills/shimo4228/claude-harness/implementation-chain.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00062 | $0.05265 |
| Opus 5.5 | $0.00025 | $0.02106 |
| Sonnet 5.5 | $0.00012 | $0.01053 |
| Haiku 4.5 | $0.00006 | $0.00526 |
Grade A, and why
implementation-chain 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementation Chain
実装に着手する前にタスク種別を判定し、対応する chain を plan に front-load する。 実装中は判定をやり直さず、定義済みの chain をそのまま実行する。 commit / push / 公開の権限は task request と substrate が持つ。この skill は追加の人間 gate を作らない。
タスク種別判定（最初の plan ステップ）
| 種別 | 判定基準 | 例 |
|---|---|---|
feat |
新規機能・新規モジュール追加 | API 追加, 新ページ |
fix |
バグ修正（再現可能な不具合） | crash, 誤動作 |
refactor |
振る舞いを変えない構造変更 | 抽出, 改名, 整理 |
chore |
設定 / 依存更新 / コード付随の docs 追従 | settings, CI |
prototype |
学習・スパイク・本番外コード | 検証スクリプト |
writing |
文書自体が一次成果物 | README 改稿, 記事, 論文, llms.txt |
prototype を選ぶ場合は 「prototype として扱う理由」を plan に必須記載（fix/feat の悪用防止）。
harness 自体の変更: 対象が ~/.claude の rules / skills / hooks / agents / settings なら、種別に関わらず Plan で skill: harness-boundary を 1 回通す（どの層に置くか・モデルに任せられないか・runtime 交換後も残すか。1 行の判断で足りる）。
README の種別判定: README 自体の改善・書き直しが目的なら writing（Writing Chain → readme-writer）。コード変更に付随する README 追従更新はコードチェーンの Doc Sync で、readme-writer の Incremental モードを使う。
大きい feat の Plan の補助: 探索が互いに独立した複数の領域にまたがるときは Explore agent を並列で使い、 各 agent に「主ループが読むべきファイル 5〜10」を返させて読む。設計代替は主ループが並べて比較し、推奨を 添えてユーザーに選ばせる（収束の所在は Matrix の Plan 行）。
実行者の決定（Plan の最後、必須）: plan が固まったら
「このセッションが実装するか」を 1 行で決める。判断が要るのは judge-tier のセッション（Fable）で
走っているとき — そのまま実装に入ると、Review 群まで judge-tier を消費する（built-in /code-review
と /simplify はセッションのモデルを継いで走り、モデル引数は無い。pin できるのは自作 agent と
plugin agent の model: だけ）。judge-tier の既定は dispatch: 実装は build-tier の新規セッション
へ渡し、本セッションは packet を書いて検証側に残る。dispatch 先の既定は Claude Code cloud
session（bash ~/.claude/scripts/cloud-dispatch.sh <repo> <packet-file> --effort <packet の Effort> — GitHub の origin/main を
clone し、claude/ branch に push、verify は repo の CI が走らせる。ADR-0075）。cloud に出せない
条件と、そのときの代替（Agent tool / skill: spawn-session）の正本は skill: task-triage §3 の表
（ここに複製しない）。dispatch 条件の照合も task-triage — 前提が file:line で検証済み /
branch で可逆 / 受け入れ条件が判定可能 / 1 セッションに収まる / rule 変更を含まない。
三役とティアの正本は task-triage の役割表（ここには複製しない）。
このセッションで実装してよいのは、次のいずれかを plan に 1 行記録したときだけ:
(a) 設計文書・ADR・skill / rule の散文編集（judge-tier の本業）、(b) dispatch 条件を満たせない
具体的理由がある、(c) ユーザーの明示指示。自己実装する場合も Review 群は下の
「Review の実行モデル pin」で build-tier に降ろす（人間の /model 切替を待たない）。
文脈損失（ADR-0016「model 継承は能力しか救わず文脈損失は救わない」）を dispatch を避ける理由に
しない — packet の充実で救う（packet の形は task-triage が正本）。
（失効条件: モデルのティア区別と使用限度が消えた、または substrate がセッション単位の model
routing を自発的に行うようになったら、この段落を外す。）
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.
- 11d ago Changed · -127 tokens per session a149a69c0a6c
- 13d ago Changed · +3 lines · -3 tokens per session 3d772ee10bde
- 14d ago Changed 2a02ae8836e8
- 23d ago Changed · +3 lines · -4 tokens per session a6f8c7a8ccfa
- 24d ago Changed · +12 lines 8f54e5af2c0f
- 25d ago Changed · -2 lines 4a5c971452e7
- 1mo ago Changed · -3 lines 61c31a9c6341
- 1mo ago Changed · +7 lines fedba0968397
- 1mo ago Changed d3a5e907f7ad
- 1mo ago First seen · 185 lines · 196 tokens per session scan A 871949a4616a
implementation-chain is a skill published in the GitHub repository shimo4228/claude-harness (3 stars, last pushed 2d ago), licensed MIT. It adds 62 tokens to every session and 5,265 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
agent-adoption-triage
Five-question triage for routing AI work to the right architecture — script, algorithmic search, LLM workflow, or autonomous agentic loop — before any agent is built. Use when someone says "let's build an agent for X", when deciding whether a use case actually needs an autonomous agent, when reviewing an agent…
git-commit
A guided Git commit workflow that examines changes and creates a commit message using the Conventional Commits format, a shared style for labeling changes such as features, fixes, tests, or documentation.
zod
Zod v4 best practices, patterns, and API guidance for schema validation, parsing, error handling, and type inference in TypeScript applications. Covers safeParse, object composition, refinements, transforms, codecs, branded types, v3→v4 migration, and testing schemas with Jest or Vitest. Baseline: zod ^4.6.0. Triggers…
pi-triage
Decide whether an upstream pi change needs porting to the Go port. Use when assessing upstream commits/PRs ("should we port X?"), or as the triage stage of /pi-sync. Outputs a WHY/WHAT/SCOPE verdict per change.
trailhead-work
Skill "trailhead-work" from ToRvaLDz/trailhead, covering load first, in order, routing: verb to engine, work the map: work, work one ticket whole, without splitting: quick and pause, resume, split.
pi-parity-review
Adversarially verify that a ported change is faithful to the original pi implementation (TS source + published npm build). Use after porting upstream pi changes, or standalone on any area of this repo ("is X faithful to pi?").