skill-usage-audit

skill-usage-audit is a skill for Claude Code, Codex from humanerd-drew/opencode-drewgent. It costs 0 tokens per session (4,773 once invoked), scanned B, original, MIT.

A guide for reviewing which skills in an agent's skills folder are active and which appear unused. The available description does not provide enough detail about its complete audit process.

In plain words
What is it for?
Use it for a skills-folder inventory and usage review when you need to distinguish active skills from possible dead code.
Why use it?
It is intended to reduce clutter and identify skills that may no longer be used, but the supplied information is limited.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Use it for a skills-folder inventory and usage review when you need to distinguish active skills from possible dead code.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/humanerd-drew/opencode-drewgent/skill-usage-audit
Install

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.

Any agent
npx skills add humanerd-drew/opencode-drewgent --skill skill-usage-audit
Clone the repo
git clone --depth 1 https://github.com/humanerd-drew/opencode-drewgent

Made for: Claude Code, Codex.

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 skill-usage-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/humanerd-drew/opencode-drewgent/skill-usage-audit.svg)](https://agentmods.dev/skills/humanerd-drew/opencode-drewgent/skill-usage-audit)
Your own site
<a href="https://agentmods.dev/skills/humanerd-drew/opencode-drewgent/skill-usage-audit"><img src="https://agentmods.dev/badge/skills/humanerd-drew/opencode-drewgent/skill-usage-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,773 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00000 $0.04773
Opus 5 $0.00000 $0.02387
Sonnet 5 $0.00000 $0.00955
Haiku 4.5 $0.00000 $0.00477

Measured 3d ago against content hash 9806e7b223b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

skill-usage-audit scanned grade B with 1 finding 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 3d 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.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

**7b 결과로 발견되는 빈 카테고리는 dead skill removal과 별도 batch** (예: 2026-06-03 audit에서 8개 발견 — creative, media, inference-sh, gifs, feeds, diagramming, domain, index-cache). SKILL.md 0개라서 find 결과엔 안 잡히지만 `ls` 시 빈 폴더로 남음. → 별도 batch

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

skills/skill-usage-audit/SKILL.md · 269 lines

How it starts

The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.


name: skill-usage-audit description: {{AGENT_NAME}} skills/ 디렉토리의 121개 SKILL.md를 3-criteria hard evidence 기준으로 dead/active 분류 — cron 등록, wikilink 참조, mtime 임계치 title: Skill Usage Audit — 3-Criteria Hard Evidence 분류 type: skill space: growth tags: [skill, audit, skills, hygiene, diagnostics, dead-code] created: 2026-06-03 updated: 2026-06-03 links:

  • "[[@identity/brain/{{AGENT_NAME}}-brain/P0-brainstem/禁/禁no_linear_workflow]]"
  • "[[@identity/brain/{{AGENT_NAME}}-brain/P0-brainstem/禁/禁filesystem_truth.neuron]]"
  • "[[skills/filesystem-truth-audit]]"
  • "[[skills/cron-jobs-stalled]]"
  • "[[skills/kanban-dispatcher-stalled]]"
  • "[[@identity/SELF_MODEL]]"
  • "[[@identity/persona/SOUL]]"
  • "[[@identity/brain/rules]]"---

Skill Usage Audit — 3-Criteria Hard Evidence 분류

~/.{{AGENT_NAME_LOWER}}/skills/ 의 모든 SKILL.md를 dead/active로 분류하는 진단 스킬. filesystem_truth + active workflow 매핑으로 판정. P0-brainstem 강제.

Trigger

다음 중 하나:

  • "스킬이 다 사용 중이야?" / "안 쓰는 스킬 있나?" 요청
  • 새 skill batch 추가 후 (hugh 박스 import, 외부 repo 흡수)
  • 6개월 주기 위생 점검
  • context menu / skill picker가 noisy (선택지 너무 많음)
  • 정책 위반 의심 (linear 등)

배경: 왜 3-criteria 인가

{{AGENT_NAME}}는 hugh-kim 박스에서 ~100개 skill을 가져왔는데, 그 중 60%는 한 번도 안 쓰는 dead 코드. 단일 기준 (mtime 또는 위키 wikilink만) 으로는 오판 위험:

  • mtime만 → "최근에 수정 안 했어도 active일 수 있음" (예: kanban-worker는 5/20 이후 mtime 그대로지만 cron에서 매일 호출)
  • wikilink만 → "위키에 언급 안 됐어도 active일 수 있음" (예: YOUR_PREFIX-content-status-enforcement는 6/1에 만들어졌고 6/1부터 매번 YOUR_DOMAIN 빌드 시 사용)
  • cron 등록만 → "cron에 안 올라가도 active일 수 있음" (예: filesystem-truth-audit은 skill_view로 수동 호출)

3가지 hard evidence 모두 모자라야 dead로 판정.

Procedure

Step 1: 인벤토리 — SKILL.md 모두 찾기

find ~/.{{AGENT_NAME_LOWER}}/skills -name SKILL.md 2>/dev/null | wc -l
find ~/.{{AGENT_NAME_LOWER}}/skills -name SKILL.md 2>/dev/null | xargs -I{} dirname {} | xargs -I{} basename {} | sort -u

기대치: 100~150개 (HUGH 박스 + {{AGENT_NAME}} 자체).

Step 2: mtime 분류 — 3-tier 임계치 (5/14, 5/20, 6/1)

for d in ~/.{{AGENT_NAME_LOWER}}/skills/*/; do
  name=$(basename "$d")
  mt=$(stat -f "%Sm" -t "%Y-%m-%d %H:%M" "$d/SKILL.md" 2>/dev/null)
  if [ -n "$mt" ]; then echo "$mt | $name"; fi
done | sort -r

Read the full file on GitHub · 269 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. 3d ago First seen · 269 lines · 0 tokens per session scan B 9806e7b223b3

Subscribe to this mod's changes

skill-usage-audit is a skill published in the GitHub repository humanerd-drew/opencode-drewgent (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,773 tokens. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens