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 instructions/derjochenmeyer/claude-code-craft/claude-mdgit 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 | $0.00458 | $0.00458 |
| Opus 5 | $0.00229 | $0.00229 |
| Sonnet 5 | $0.00092 | $0.00092 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
claude-code-craft CLAUDE.md 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.
What it actually says
claude-code-craft — Navigation
Session start (always, no exceptions)
- Read
.craft/PROJECT_STATE.md - Summarize in 2-3 sentences: current state + what's on for today
- Wait for go
Core rules
- No assumptions — if unclear, ask
- Only touch files that belong to the current task
- After each task: update
.craft/PROJECT_STATE.md - New findings and facts are saved to the memory system automatically
- In git commits, always name the exact model (e.g.
Claude Sonnet 4.6) - No
Co-Authored-Byfooter in commits - Never
git pushwithout an explicit instruction
What is this?
A public GitHub project versioning okay.cool's Claude Code setup and making it available to the community. Core skills: craft-project-setup (project setup), craft-project-audit (health check), craft-project-dream (project consolidation).
Cluster / brand
okay.cool
Tech stack
| What | How |
|---|---|
| Skills | Markdown prompts (.md) under skills/ |
| Configuration | JSON (settings.json, keybindings.json) |
| Hooks | Shell/Bash inside settings.json |
| Repo | Public GitHub repository |
| Docs | Markdown (README.md, CLAUDE.md, etc.) |
Deploy
Public GitHub repository — others can clone, fork, star, or download as ZIP. No server deploy.
Project docs
| File | Content |
|---|---|
.craft/PROJECT_STATE.md |
Current state, infra, known issues |
.craft/BACKLOG.md |
Prioritized tasks (P0/P1/P2) |
.craft/HANDOVER.md |
Handover between sessions |
.craft/rules/coding.md |
Project-specific rules |
.craft/DREAM_LOG.md |
Dream history (when, what was consolidated) |
Skills (grow on demand)
Global skills: ~/.claude/skills/
Project-specific skills: .craft/skills/ (create when needed)
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 · 55 lines · 458 tokens per session scan A 924c435019c5
claude-code-craft CLAUDE.md is an instructions file published in the GitHub repository derjochenmeyer/claude-code-craft (2 stars, last pushed 4mo ago), licensed MIT. It adds 458 tokens to every session, about $0.0023 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.