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-project-audit-fullnpx skills add derjochenmeyer/claude-code-craft --skill craft-project-audit-fullgit 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-project-audit-full)<a href="https://agentmods.dev/skills/derjochenmeyer/claude-code-craft/craft-project-audit-full"><img src="https://agentmods.dev/badge/skills/derjochenmeyer/claude-code-craft/craft-project-audit-full.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 | $0.00059 | $0.02586 |
| Opus 5 | $0.00030 | $0.01293 |
| Sonnet 5 | $0.00012 | $0.00517 |
| Haiku 4.5 | $0.00006 | $0.00259 |
Grade A, and why
craft-project-audit-full scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- ~/.claude/settings.json (full content) Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Token budget notice: This skill runs 4 parallel research agents at high effort. A full audit takes 2-20 minutes and uses significant token budget. Do not run simultaneously across multiple projects.
For a fast local health check (~15 seconds, no agents):
/craft-project-audit
Step 1: Locate session directory
Run this bash command first:
CWD=$(pwd)
PROJECT_KEY=$(echo "$CWD" | sed 's|/|-|g; s|_|-|g')
SESSIONS_DIR="$HOME/.claude/projects/$PROJECT_KEY"
if [ -d "$SESSIONS_DIR" ] && [ -f "$SESSIONS_DIR/sessions-index.json" ]; then
echo "FOUND:$SESSIONS_DIR"
else
BASENAME=$(basename "$CWD" | sed 's|_|-|g')
CANDIDATE=$(ls "$HOME/.claude/projects/" 2>/dev/null | grep -- "-$BASENAME$" | head -1)
if [ -n "$CANDIDATE" ]; then
echo "FOUND:$HOME/.claude/projects/$CANDIDATE"
else
echo "NOT_FOUND"
fi
fi
Also run: pwd and detect project name from CLAUDE.md or directory name.
Record the actual SESSIONS_DIR. Embed it in the agent prompts below.
Step 2: Launch 4 agents in parallel (single message, all at once)
Critical: spawn all 4 agents in one message. Do not wait.
Agent A: Feature Researcher
Fetch ALL of these. Do not skip any:
- https://docs.anthropic.com/en/release-notes/claude-code
- https://docs.anthropic.com/en/docs/claude-code/overview
- https://docs.anthropic.com/en/docs/claude-code/settings
- https://docs.anthropic.com/en/docs/claude-code/hooks
- https://docs.anthropic.com/en/docs/claude-code/mcp
- https://docs.anthropic.com/en/docs/claude-code/slash-commands
- https://docs.anthropic.com/en/docs/claude-code/memory
- https://docs.anthropic.com/en/docs/claude-code/cli-reference
- https://api.github.com/repos/anthropics/claude-code/releases?per_page=30
Build a complete feature inventory organized by category:
- Built-in slash commands (every one)
- Hook events (every type with triggers and data)
- MCP capabilities
- Skill system (all frontmatter fields)
- Agent/subagent system
- CLI flags and modes
- Settings options
- Status line
- Memory system
- Recent launches (last 60 days)
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 · 242 lines · 59 tokens per session scan A 3f501b923908
craft-project-audit-full is a skill published in the GitHub repository derjochenmeyer/claude-code-craft (2 stars, last pushed 4mo ago), licensed MIT. It adds 59 tokens to every session and 2,586 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). 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…
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…
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…
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…