Skip to content

/kit-audit

Audit guardrails-kit compliance of the current session — run the transcript marker scorecard. Use when asked to audit compliance, check which guardrail rules fired or were missed, or score the session.

shell
$ npx -y skills add altafino/FableClaudeMDForOpus --skill kit-audit --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
  • You can call itInvoke it directly when you want it.
  • Slash command/kit-audit
How auto-invocation works

Context preview

The summary Claude sees to decide when to auto-load this skill.

Audit guardrails-kit compliance of the current session — run the transcript marker scorecard. Use when asked to audit compliance, check which guardrail rules fired or were missed, or score the session.

SKILL.md

kit-audit.SKILL.md
name: kit-audit
description: Audit guardrails-kit compliance of the current session — run the transcript marker scorecard. Use when asked to audit compliance, check which guardrail rules fired or were missed, or score the session.

1. Run `python3 scripts/audit-transcript.py --latest` (or pass an explicit transcript path). 2. Summarize the scorecard: which trigger checks FIRED/MISSED, and notable zero-count marker families. 3. For each MISSED check, name the kit rule that should have fired and quote the event evidence. 4. Record heuristic false positives as `NOTED (not done):` lines — they feed the F16 rule-lifecycle tuning.

Read it on GitHub ↗
Ships withfableclaudemdforopus

A portable CLAUDE.md + documentation set that makes Claude Opus / Sonnet operate as close to frontier (Fable) level as possible inside Claude Code: fewer logic errors, fewer introduced bugs, fewer wasted tokens.

Get the whole plugin, auto-invoked
Stats
6
Stars
0
Views
0
Forks
Active
Maintenance
Python
Language
24d ago
Last commit
27d ago
Created

Repo: altafino/FableClaudeMDForOpus