corrections-audit

corrections-audit is a skill for Claude Code from haabe/mycelium. It costs 28 tokens per session (3,699 once invoked), scanned A, original, MIT.

An audit of a corrections log, which is a record of mistakes and the changes made after them. It uses a script to find recurring correction patterns and measure how often a hook or other check caught a mistake.

In plain words
What is it for?
Use it to review correction trends, check the evidence behind escape-rate numbers, save dated metric snapshots, and turn repeated corrections into guardrails or anti-patterns.
Why use it?
It replaces occasional manual review with a repeatable view of which problems keep returning and whether automated checks are catching them.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions CLAUDE.md.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the mycelium plugin — 61 skills, 6 hooks shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add haabe/mycelium
Claude Code
/plugin install mycelium

Made for: Claude Code.

Or install mycelium, the plugin that ships this one along with the rest of its 61 skills, 6 hooks.

Wrote 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.

agentmods badge for corrections-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/haabe/mycelium/corrections-audit.svg)](https://agentmods.dev/skills/haabe/mycelium/corrections-audit)
Your own site
<a href="https://agentmods.dev/skills/haabe/mycelium/corrections-audit"><img src="https://agentmods.dev/badge/skills/haabe/mycelium/corrections-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,699 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00028 $0.03699
Opus 5 $0.00014 $0.01850
Sonnet 5 $0.00006 $0.00740
Haiku 4.5 $0.00003 $0.00370

Measured 6d ago against content hash b673f97a3381, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

corrections-audit 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 6d 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.

plugins/mycelium/skills/corrections-audit/SKILL.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Corrections Audit Skill

Analyze corrections.md for trends, recurring patterns, and actionable insights.

Attribution: run the script, do not count by hand

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/check_correction_attribution.py" --root . --snapshot

Added 2026-08-03. This audit's headline number — who caught the mistake — was computed by hand and had been produced exactly twice, six weeks apart, each time because a human remembered to look. It is the only number that answers the question the correction loop exists to answer: more harness, or more context.

The script reports the escape rate and its denominator, every time. At the time of writing 14 of 72 entries carry a catcher, so the rate covers 19% of the corpus — quoting it without that is a claim about the whole wearing borrowed clothes, which is the failure this repo spent 2026-08-02/03 removing from its own checks. If it prints NO RATE AVAILABLE, that is not 0%: it means nothing in the corpus says who caught anything.

--snapshot appends the reading to .claude/evals/metrics/corrections/<date>.json, the same layout the other metric adapters use. The level is not the signal. Trend caught_by_hook_or_check rising in absolute terms; the ratio can also be improved by logging fewer user-caught mistakes, which is why this script never gates on it.

Attribution is a HARD RULE at write time, not a suggestion — see engine/agent-operating-contract.md. It was advisory until 2026-08-03 and 72 of 100 entries carry no catcher as a result. Do not backfill those in bulk: who caught a mistake six weeks ago is not recoverable by inference, and a guessed catcher corrupts the only number this loop produces.

For entries written before the rule, add one phrase per new entrycaught by user, caught by hook, caught by review, self-caught. The parser reads the prose forms already present rather than requiring a new field, so nothing existing needs rewriting.

When to Use

Read the full file on GitHub · 194 lines

Changes

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.

  1. 6d ago First seen · 194 lines · 28 tokens per session scan A b673f97a3381

Subscribe to this mod's changes

corrections-audit is a skill published in the GitHub repository haabe/mycelium (45 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 3,699 once invoked, about $0.0001 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 2026-08-30.

Related

Other skills, from other repositories

skill-finder

Find the right Affitor skill for your goal. Triggers on: "which skill should I use", "find me a skill", "what skills are available", "help me choose a skill", "skill for SEO", "skill for email", "explore skills", "I'm new to Affitor", "what can Affitor do", "search skills", "skill for blog writing", "skill for landing…

Affitor/affiliate-skills · 94 tokens

meraki-network-ops

Cisco Meraki organization and network operations (read-only) — org discovery, network inventory, device inventory, clients, group policies, admins, licensing, alert settings via Cisco's official Meraki MCP. Use as the entry point for any Meraki question, to discover org and network IDs, or to inventory Meraki networks…

automateyournetwork/netclaw · 72 tokens

auto

Intent-classified router, the front door to OrchestKit and the DEFAULT entry point for any goal-shaped request. Classifies a plain-English goal and routes it to the right specialist skill. Routing is never overhead, so use it even when the target skill seems obvious; skip only when already executing inside another…

yonatangross/orchestkit · 99 tokens

gingiris-user-interview

🇺🇸 User Interview & Cold-Start Operations Playbook — Battle-tested framework from HeyGen's 937 interviews to PMF. Complete SOP for user screening, interview execution, Beta testing methodology, cold-start user operations, churn analysis, and user grading systems. 🇨🇳 用户访谈与冷启动运营实战手册 — 基于 HeyGen 937 场访谈验证的 PMF…

Gingiris-1031/gingiris-skills · 369 tokens

tao-setup

One-time session setup and orchestration map for the TAO skill bank. Run this first when the TAO skills were installed individually (e.g. from a public skills catalog) so the session gets the cross-skill discovery flow, credential checks, and host preflight that the bundled plugin hook would otherwise inject…

NVIDIA-TAO/tao-skill-bank · 97 tokens

tao-list-capabilities

Answer what the TAO Skill Bank plugin can do by generating the response from packaged application, data, model, AutoML, and platform manifests. Use when the user asks "what can TAO Skill Bank do", "list TAO models", "which TAO workflows are available", or "what supports AutoML".

NVIDIA-TAO/tao-skill-bank · 70 tokens