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.
/plugin marketplace add YoungjaeDev/my-claude-plugins/plugin install docsWrote 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.
[](https://agentmods.dev/skills/youngjaedev/my-claude-plugins/skill-audit)<a href="https://agentmods.dev/skills/youngjaedev/my-claude-plugins/skill-audit"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/skill-audit.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00181 | $0.01575 |
| Opus 5 | $0.00090 | $0.00788 |
| Sonnet 5 | $0.00036 | $0.00315 |
| Haiku 4.5 | $0.00018 | $0.00158 |
Grade A, and why
skill-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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
skill-audit
Diagnose one skill. Report what is wrong, at what severity, with the edit that fixes it.
Overview
Measurement first, judgment second. Numbers settle the mechanical axes for free, which keeps the expensive reading focused on the axes a script cannot reach: whether the description encodes real trigger conditions, whether steps distinguish done from not-done, whether the body still describes where it used to live.
The rules being applied belong to docs:skill-forge and live in its bundled references. Read
them there rather than restating them; this skill is the diagnostic pass over one target.
When to use
Audit one named skill: after writing it, after moving it between plugins, when it does not trigger, when it loads on one runtime and not another, or when its body outgrew its job.
Do not use it to write or rewrite a skill (docs:skill-forge), or to sweep the whole
repository (docs:skill-fleet-review).
Procedure
1. Measure
Resolve the plugin root, then measure the tree that contains the target. Pass that tree
explicitly: with no argument the script defaults to plugins/ when it exists, so auditing a
skill under .claude/skills/ in a repository that also has plugins/ silently measures a
different tree and the target never appears in the output.
Set TARGET_ROOT to the directory holding the target and its siblings: plugins/<plugin>/skills,
.claude/skills, or whatever contains it. Siblings matter: the pointer axis is judged against them.
# Honor a caller-supplied PLUGIN_ROOT first — the abort message below tells the user to
# export it, and starting from CLAUDE_PLUGIN_ROOT would overwrite that escape hatch.
PLUGIN_ROOT="${PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-}}"
[ -z "$PLUGIN_ROOT" ] && [ -d plugins/docs/skills ] && PLUGIN_ROOT=plugins/docs
if [ -z "$PLUGIN_ROOT" ]; then
# Rank Codex cache candidates on the version basename, not the whole path: a plain
# sort puts 0.9.0 above 0.10.0 and lets the marketplace directory outrank the version.
cache_root="${CODEX_PLUGIN_CACHE:-$HOME/.codex/plugins/cache}"
if sort -V </dev/null >/dev/null 2>&1; then vsort="sort -V"; else vsort="sort -t. -k1,1n -k2,2n -k3,3n"; fi
PLUGIN_ROOT=$(ls -1d "$cache_root"/*/docs/* 2>/dev/null | awk -F/ '{print $NF "\t" $0}' | $vsort | tail -1 | cut -f2-)
fi
[ -d "$PLUGIN_ROOT/skills" ] || { echo "docs plugin root not found; export PLUGIN_ROOT" >&2; exit 1; }
TARGET_ROOT="${TARGET_ROOT:?set TARGET_ROOT to the directory containing the target skill}"
TARGET_SKILL="${TARGET_SKILL:?set TARGET_SKILL to the skill directory name being audited}"
out=$(node "$PLUGIN_ROOT/skills/skill-forge/scripts/measure-skills.mjs" "$TARGET_ROOT"); rc=$?
printf '%s\n' "$out"
[ "$rc" -eq 0 ] || { echo "measure-skills exited $rc — part of $TARGET_ROOT was unreadable, so this audit's scope is incomplete" >&2; exit 1; }
# Fail closed: a target that is not in the measurement means TARGET_ROOT points elsewhere.
# Continuing would judge the seven axes against rows belonging to other skills.
printf '%s\n' "$out" | grep -qE "(^|[[:space:]])${TARGET_SKILL}([[:space:]]|$)" \
|| { echo "no row for '$TARGET_SKILL' under $TARGET_ROOT — the root is wrong, not the skill" >&2; exit 1; }
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.
- 3d ago Changed · -4 tokens per session 60f6dd5134d0
- 8d ago First seen · 113 lines · 185 tokens per session scan A 9be67ad29a8a
skill-audit is a skill published in the GitHub repository YoungjaeDev/my-claude-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 181 tokens to every session and 1,575 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
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…
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…