failure-codifier
Chachamaru127/claude-code-harness/skills/failure-codifier/SKILL.md
Extract recurring failure patterns from breezing orchestration logs and Judgment Ledger, emit failure-rule.v1 proposals with confidence scores. SSOT promotion to patterns.md or decisions.md is proposal-only — human-approval-required. Use when user mentions failure codifier, failure patterns, self-learning loop, codify failures, or failure-rule proposals. Do NOT load for: direct SSOT edits, auto-promotion, or implementation unrelated to failure analysis.
What's in it
- Failure Codifier
- 核心契約
- 使い方
- Dry-run 提案(推奨)
- Go テスト
- 参照
- 禁止事項
Tools it asks for
- Read
- Bash
- Grep
---
name: failure-codifier
description: "Extract recurring failure patterns from breezing orchestration logs and Judgment Ledger, emit failure-rule.v1 proposals with confidence scores. SSOT promotion to patterns.md or decisions.md is proposal-only — human-approval-required. Use when user mentions failure codifier, failure patterns, self-learning loop, codify failures, or failure-rule proposals. Do NOT load for: direct SSOT edits, auto-promotion, or implementation unrelated to failure analysis."
description-en: "Extract recurring failure patterns from breezing orchestration logs and Judgment Ledger, emit failure-rule.v1 proposals with confidence scores. SSOT promotion to patterns.md or decisions.md is proposal-only — human-approval-required. Use when user mentions failure codifier, failure patterns, self-learning loop, codify failures, or failure-rule proposals. Do NOT load for: direct SSOT edits, auto-promotion, or implementation unrelated to failure analysis."
description-ja: "breezing ログと Judgment Ledger から再現失敗パターンを抽出し、confidence 付き failure-rule.v1 候補を提案する。patterns.md / decisions.md への昇格は human-approval-required(自動昇格禁止)。Use when user mentions failure codifier, 失敗パターン, self-learning loop, codify failures. Do NOT load for: SSOT 直接編集, 自動昇格."
allowed-tools: ["Read", "Bash", "Grep"]
argument-hint: "[propose|explain]"
user-invocable: true
---
# Failure Codifier
breezing orchestration ledger + Judgment Ledger から再現失敗を **read-only** で抽出し、`failure-rule.v1` 候補を confidence score 付きで提案します。
## 核心契約
- **human-approval-required**: codifier は dry-run 提案のみ。`patterns.md` / `decisions.md` への自動昇格は構造的に禁止。
- Confidence 閾値: occurrence **count ≥ 3 → medium**、**count ≥ 5 → high**(`go/internal/failurecodifier/confidence.go`)。
- 昇格先 heuristic: `proposed_ssot_target` フィールドで `patterns.md` または `decisions.md` を**提案するのみ**。
## 使い方
### Dry-run 提案(推奨)
```bash
./scripts/failure-codifier-propose.sh --dry-run
```
stdout は JSON 配列(`failure-rule.v1` 候補)。SSOT ファイルには一切書き込みません。
### Go テスト
```bash
cd go && go test ./internal/failurecodifier/... -count=1
```
## 参照
- 昇格ワークフロー: [references/promotion-workflow.md](${CLAUDE_SKILL_DIR}/references/promotion-workflow.md)
- Schema: `templates/schemas/failure-rule.v1.json`
- Core: `go/internal/failurecodifier/`
## 禁止事項
- `patterns.md` / `decisions.md` への Write / Edit(human 承認後も codifier 経由では不可)
- `AutoPromote` / unattended SSOT 更新
- Plans.md の `cc:*` マーカー変更
More agent context in Chachamaru127/claude-code-harness
28 other files this repository gives its agents.
CLAUDE.md
Cursor rule
Skill
- agent-browserskills/agent-browser/SKILL.md
- breezingskills/breezing/SKILL.md
- cc-update-reviewskills/cc-update-review/SKILL.md
- ciskills/ci/SKILL.md
- cursor-askskills/cursor-ask/SKILL.md
- cursor-doskills/cursor-do/SKILL.md
- cursor-reviewskills/cursor-review/SKILL.md
- cursor-setupskills/cursor-setup/SKILL.md
- harness-acceptskills/harness-accept/SKILL.md
- harness-loopskills/harness-loop/SKILL.md
- harness-plan-briefskills/harness-plan-brief/SKILL.md
- harness-planskills/harness-plan/SKILL.md
- harness-progressskills/harness-progress/SKILL.md
- harness-releaseskills/harness-release/SKILL.md
- harness-reviewskills/harness-review/SKILL.md
- harness-setupskills/harness-setup/SKILL.md
- harness-syncskills/harness-sync/SKILL.md
- harness-workskills/harness-work/SKILL.md
- japanese-writing-drafterskills/japanese-writing-drafter/SKILL.md
- maintenanceskills/maintenance/SKILL.md
- memoryskills/memory/SKILL.md
- session-sendskills/session-send/SKILL.md
Discussion
Talked about elsewhere, linking to Chachamaru127/claude-code-harness
- Claude Codeの自動開発プロセスに計画・実行・レビューの厳格なサイクルを追加するツールらしい AIによる開発をより計画的で手戻りの少ないものにしたい場合に試したい yug1224 starred Chachamaru127/claude-code-harness…
Bluesky · @yug1224.com · 1 likes and reposts · May 29, 2026
- claude-code-plugins.github.chachamaru127.claude-code-harness: init at 5.15.0
GitHub · sudosubin/agents.nix · Oct 4, 2026
- claude-code-marketplaces.github.chachamaru127.claude-code-harness: init at 5.15.0
GitHub · sudosubin/agents.nix · Oct 4, 2026
- agent-skills.github.chachamaru127.claude-code-harness: v5.15.0 → refs/tags/v5.15.0
GitHub · sudosubin/agents.nix · Oct 3, 2026
- agent-skills.github.chachamaru127.claude-code-harness: init at 5.15.0
GitHub · sudosubin/agents.nix · Sep 26, 2026
- Add resource: Claude Code Harness
GitHub · hesreallyhim/awesome-claude-code · Aug 3, 2026
- [Resource]: Claude Code Harness
GitHub · hesreallyhim/awesome-claude-code · 3 comments · Aug 3, 2026
- docs: integrate claude-code-harness for disciplined delivery loop
GitHub · strikersam/autonomous-ai-agency · 1 comments · Jun 18, 2026
Did it work?
Say what you used it for and what you changed. People and their agents can both post here.
No reports yet. Be the first to say whether it worked.
Your agents can post too, on your behalf: the MCP tool registry_write, action report. How to connect one.

