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 repair-disciplinegit 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/repair-discipline)<a href="https://agentmods.dev/skills/shimo4228/claude-harness/repair-discipline"><img src="https://agentmods.dev/badge/skills/shimo4228/claude-harness/repair-discipline/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/repair-discipline"><img src="https://agentmods.dev/badge/skills/shimo4228/claude-harness/repair-discipline.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 | $0.00140 | $0.01065 |
| Opus 5 | $0.00070 | $0.00532 |
| Sonnet 5 | $0.00028 | $0.00213 |
| Haiku 4.5 | $0.00014 | $0.00106 |
Grade A, and why
repair-discipline 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.
What it actually says
Repair Discipline
直す前に、いま何が真かを一次証拠で確定する。5 原則、いずれも実地の失敗から （出所は CA repo での実測。原則自体はどの repo でも同じ形で壊れる）。
1. 着手前に既済照合
残課題ファイル・古い TODO・引き継ぎメモは書かれた時点の観測。着手前に git log と 実コードで「もう直っていないか」を照合する。台帳だけが古いまま残る drift は 「作業 → 資料 → 台帳」の最後の 1 ホップで起きる — 見つける経路は日付でなく 正本資料との突き合わせ。 （出所: 2 ヶ月前に決着済みのタスク 2 件が store で open のまま残っていた 2026-08-16 の棚卸し）
2. schema / storage 変更は全消費者を同じ変更で棚卸す
データ形式・保存場所・フィールドを変えたら、その形式を読む側を全部 grep して同じ PR で追随させる。書き手だけ直した変更は、読み手が静かに空を返す形で壊れる — エラーでなく「何も無い」に見えるのが最悪の壊れ方。消費者は自コードとは限らない （skill 本文・doc・別 script が名指しで読んでいることがある）。
3. bypass は単一ゲートでなく全ゲートを短絡すると知って使う
VERIFY_BYPASS=1 型の逃げ道は、既知の 1 件を通すためのつもりでも hook が束ねる
全検査（format / lint / security）を一緒に飛ばす。使う前に「この bypass が黙らせる
検査の全リスト」を言えるか確認し、言えないなら個別の除外手段を探す。
4. プロセスの CPU が低い ≠ stuck
I/O バウンドなプロセス（LLM 推論・ネットワーク待ち）は CPU がほぼ 0 でも正常に進行 している。kill する前に一次ログと相手側の状態（サーバの load 状況・進捗ログの タイムスタンプ）を見る。「反応がない気がする」は証拠でない。
5. テストの再試行はフォアグラウンド 1 回
失敗したテストをバックグラウンドで連発しない。1 回フォアグラウンドで走らせ、出力を 読み切ってから次の仮説へ。連発は失敗ログを積むだけで情報を増やさず、リソース競合で 新しい偽の失敗を作る。
使い方
修理・変更の着手時に該当原則を 1 つ名指しして通す（「原則 1 — この課題、git log で 既済照合した？」）。機構を足す修理はこの skill の外 — implementation-chain の 機構ゲート（agent: architect）が正本。
失効条件
- substrate がこれらの照合を着手時に自発するようになったら退役（Scaffold Dissolution）
- 原則の出所となった実測が反証されたら該当原則を削る
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 First seen · 57 lines · 140 tokens per session scan A eddcfd20bddd
repair-discipline is a skill published in the GitHub repository shimo4228/claude-harness (3 stars, last pushed 5d ago), licensed MIT. It adds 140 tokens to every session and 1,065 once invoked, about $0.0007 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.
Other skills, from other repositories
iterate
Autonomous multi-cycle problem solver for complex tasks that require diagnosis → fix → test → verify loops. Use when the user says things like "make this work", "test this end-to-end", "fix and verify", "iterate until working", "do cycles", "keep going until it passes", or when a task clearly requires multiple rounds…
troubleshoot-terva
Diagnose terva itself. Symptoms include an extension that will not load, a connector or bot that is down, missing tools, or MCP trouble. A bloated context or session/resume confusion also qualifies. Use when terva misbehaves, or when something that should be available is absent. Also use when the user asks why terva…
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…
debug-help
Help debug an issue systematically.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.