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-setupnpx skills add derjochenmeyer/claude-code-craft --skill craft-project-setupgit clone --depth 1 https://github.com/derjochenmeyer/claude-code-craftWhat 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 | $0.00036 | $0.02268 |
| Opus 5 | $0.00018 | $0.01134 |
| Sonnet 5 | $0.00007 | $0.00454 |
| Haiku 4.5 | $0.00004 | $0.00227 |
Grade A, and why
craft-project-setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
craft-project-setup
Orchestrate fresh setup or enhance-mode. Reads templates from ~/.claude/craft-templates/, substitutes placeholders, writes to the current project.
IMPORTANT: Never overwrite existing files. Enhance-mode is strictly additive.
Two modes (auto-detected)
Fresh mode: No CLAUDE.md and no .craft/ directory exist. Create everything from scratch.
If this is an existing codebase (has source files), suggest running
/initfirst./initanalyses the codebase and generates a starter CLAUDE.md automatically. Then re-run/craft-project-setup— it will detect the file and switch to Enhance mode.
Enhance mode: CLAUDE.md or .craft/ already exists. Show what exists, show what is missing, ask before adding anything. Never overwrite. Never remove.
Template location
Before doing anything, verify templates are available:
TEMPLATES_DIR="$HOME/.claude/craft-templates"
if [[ ! -d "$TEMPLATES_DIR" ]]; then
echo "craft-templates not found at $TEMPLATES_DIR — reinstall craft via install.sh"
exit 1
fi
All template reads go through $TEMPLATES_DIR/<filename>. Placeholders use [UPPERCASE_WITH_UNDERSCORES] and are substituted based on Phase 1 answers.
Phase 1: Questions (Fresh mode only, ask one at a time, wait for each answer)
Q1: "What is this project?" (1-sentence description)
Q2: "Project type? A) Software project (code will be written) B) Project management (docs, planning, coordination) C) Hybrid (code + substantial documentation)"
Q3 (only if A or C): "Tech stack? (multiple ok, or 'not decided yet')
- Shopify Theme (Liquid)
- Shopify App (React + TypeScript + Prisma)
- Next.js / React (TypeScript)
- Astro (TypeScript, SSG)
- PHP / Drupal
- PHP custom / Composer
- Python
- WordPress
- Static HTML/CSS/JS
- Node.js / TypeScript (other)
- Other (describe)"
Q4: "Project context? (client name, team, personal, open source -- optional, press Enter to skip)"
Q5: "What is the goal? What should be better after this project? (2-4 sentences)"
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.
- 2d ago First seen · 215 lines · 36 tokens per session scan A acf1fd4252a5
craft-project-setup is a skill published in the GitHub repository derjochenmeyer/claude-code-craft (2 stars, last pushed 4mo ago), licensed MIT. It adds 36 tokens to every session and 2,268 once invoked, about $0.0002 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…