Failure Codifier

What it does

When your agent uses it

• Reviewing orchestration logs for failures that keep coming back
• Drafting failure-rule proposals from a Judgment Ledger
• Running the self-learning loop without touching shared rule files
• Checking how confident the codifier is about a repeated failure

Example prompts

• “Run the failure codifier in dry-run mode and show me the proposed rules.”
• “Which failure patterns in the breezing logs have happened at least five times?”
• “Draft failure-rule proposals from the Judgment Ledger, but do not touch patterns.md.”

Requirements

• Breezing orchestration logs and a Judgment Ledger to read
• Go, for the bundled tests
• Pre-approved tools (allowed-tools): Read, Bash, Grep

What it can do on your machine

Read from SKILL.md and the folder at commit 2b2b748. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Bash
  • Grep

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • go

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Failure Codifier loads about 603 tokens when it runs, and up to ~1.2k if it reads all its reference files. Until then it costs about 119 tokens; SKILL.md has 73 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~119

When it runs · the whole SKILL.md, loaded when a task matches

~603

With references · SKILL.md plus every file in references/, read only if the agent opens them

~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Read, Bash, Grep

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Chachamaru127/claude-code-harness at commit 2b2b748, republished under its MIT licence (© Chachamaru127). 73 words, ~603 tokens.

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.

allowed-tools

Read, Bash, Grep

description-en

Extract recurring failure patterns from breezing orchestration logs and Judgment Ledger, emit failure-rule.v1 proposals with confidence scores. SSOT promotion…

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…

argument-hint

[propose|explain]

user-invocable

true

./scripts/failure-codifier-propose.sh --dry-run

cd go && go test ./internal/failurecodifier/... -count=1

© Chachamaru127, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/failure-codifier of Chachamaru127/claude-code-harness.

• SKILL.md
• references/promotion-workflow.md

Open the folder on GitHubat commit 2b2b748