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.
npx agentmods add skills/derjochenmeyer/claude-code-craft/craft-global-auditnpx skills add derjochenmeyer/claude-code-craft --skill craft-global-auditgit clone --depth 1 https://github.com/derjochenmeyer/claude-code-craftWrote 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/derjochenmeyer/claude-code-craft/craft-global-audit)<a href="https://agentmods.dev/skills/derjochenmeyer/claude-code-craft/craft-global-audit"><img src="https://agentmods.dev/badge/skills/derjochenmeyer/claude-code-craft/craft-global-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 | $0.00024 | $0.01597 |
| Opus 5 | $0.00012 | $0.00798 |
| Sonnet 5 | $0.00005 | $0.00319 |
| Haiku 4.5 | $0.00002 | $0.00160 |
Grade A, and why
craft-global-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
craft-global-audit
Scan all projects and audit the Claude Code installation.
Usage:
/craft-global-audit (auto-detects project root)
/craft-global-audit ~/projects (explicit path)
Step 0: Determine scan path
A directory qualifies as a project if it contains at least one of: CLAUDE.md, .git, package.json, .craft/.
A directory qualifies as a projects container if 2 or more of its immediate subdirectories qualify as projects.
If an argument was provided: use it as scan path. Skip to Section 1.
If no argument, run discovery:
PWD_IS_PROJECT=false
PWD_IS_CONTAINER=false
# Check if current dir is a project
for marker in CLAUDE.md .git package.json .craft; do
[[ -e "$PWD/$marker" ]] && PWD_IS_PROJECT=true && break
done
# Check if current dir is a projects container
project_count=0
for d in "$PWD"/*/; do
for marker in CLAUDE.md .git package.json .craft; do
if [[ -e "${d%/}/$marker" ]]; then
((project_count++))
break
fi
done
done
[[ $project_count -ge 2 ]] && PWD_IS_CONTAINER=true
echo "IS_PROJECT=$PWD_IS_PROJECT IS_CONTAINER=$PWD_IS_CONTAINER PROJECT_COUNT=$project_count PWD=$PWD"
Case 1: current dir is a projects container (IS_CONTAINER=true)
→ use $PWD as scan path.
Case 2: current dir is a project (IS_PROJECT=true, IS_CONTAINER=false)
→ check parent directory:
parent=$(dirname "$PWD")
parent_count=0
for d in "$parent"/*/; do
for marker in CLAUDE.md .git package.json .craft; do
if [[ -e "${d%/}/$marker" ]]; then
((parent_count++))
break
fi
done
done
echo "PARENT=$parent PARENT_COUNT=$parent_count"
If parent has 2+ projects → use parent as scan path (note: "Scanning parent directory $parent which contains $parent_count projects").
If parent has fewer → use $PWD as scan path (single-project view).
Case 3: current dir is ~/ (home)
→ check common paths:
for candidate in ~/code ~/projects ~/dev ~/src ~/workspace; do
if [[ -d "$candidate" ]]; then
count=0
for d in "$candidate"/*/; do
for marker in CLAUDE.md .git package.json .craft; do
if [[ -e "${d%/}/$marker" ]]; then
((count++))
break
fi
done
done
[[ $count -ge 2 ]] && echo "CANDIDATE=$candidate COUNT=$count"
fi
done
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.
- 5d ago First seen · 190 lines · 24 tokens per session scan A f8bfe3d443e5
craft-global-audit is a skill published in the GitHub repository derjochenmeyer/claude-code-craft (2 stars, last pushed 4mo ago), licensed MIT. It adds 24 tokens to every session and 1,597 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 2026-08-31.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…