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/b33eep/claude-code-setup/claude-mdgit clone --depth 1 https://github.com/b33eep/claude-code-setupWhat 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 | $0.01886 | $0.01886 |
| Opus 5 | $0.00943 | $0.00943 |
| Sonnet 5 | $0.00377 | $0.00377 |
| Haiku 4.5 | $0.00189 | $0.00189 |
Grade E, and why
claude-code-setup CLAUDE.md scanned grade E with 2 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- PROJECT INSTRUCTIONS START --> Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
HOME=/tmp/claude-manual-test && rm -rf $HOME && mkdir -p $HOME && ./install.sh How it starts
The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Setup
About
A modular, minimal setup for Claude Code with clear workflow and persistent memory via Markdown files. Open source release.
Tech Stack
- Bash (install.sh)
- Markdown (templates, commands)
- Node.js (MCP servers via npx, Nextra docs site)
- GitHub Actions (CI/CD)
Current Status
| Story | Status | Notes |
|---|---|---|
| JetBrains Integration Guide | In Progress | PR #51 — docs-only guide for Debugger MCP + Built-in MCP |
Legend: Open | In Progress | Done
Next Step: Merge PR #51.
Future
| Todo | Priority | Problem | Solution |
|---|---|---|---|
| Docker Matrix Tests | Low | deps.json install commands not tested on real distros | GitHub Actions with Docker matrix (Record 022) |
Recent Decisions
| Date | Decision | Why |
|---|---|---|
| 2026-04-24 | Keep create-slidev-presentation as type: command |
Auto-loading (context) would pull 10+ reference files on any "slidev" match; "slidev" also isn't a tech-stack users list in CLAUDE.md. Progressive disclosure via explicit invocation preserves context budget. |
| 2026-02-27 | 2 agents default + --security/--full flag for 3rd |
Balance between review quality and token cost; security-auditor not needed for every review |
| 2026-02-27 | Tracking update after plugin install, not before | Prevents state mismatch if claude plugin install fails (review feedback) |
| 2026-02-11 | Replaced team-setup.mdx with customizing.mdx | All custom module topics (skills, commands, scripts, MCP) belong in one page; team-setup was redundant; Solo vs Team already in init-project |
Project Instructions
Pull Request Format
When creating PRs, use this structure (see PRs #45, #46 for examples):
## Summary
- Bullet points of what changed
## Problem
Why this change is needed
## Solution
How the problem is solved
## Test plan
- [ ] Test description 1
- [ ] Test description 2
- [ ] All tests pass
## Files Changed (optional)
- List of changed files
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 · 214 lines · 1,886 tokens per session scan E bc738e604405
claude-code-setup CLAUDE.md is an instructions file published in the GitHub repository b33eep/claude-code-setup (56 stars, last pushed 3mo ago), licensed MIT. It adds 1,886 tokens to every session, about $0.0094 per session on Opus 5. A static security scan graded it E with 2 findings (hidden instructions, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
spellbook AGENTS.md
Instructions for majiayu000/spellbook, covering spellbook agent contract, routing, scope rules, threads long-run guardrails and validation.
open-supermarkets AGENTS.md
Instructions for abracadabra50/open-supermarkets, covering agent integration guide, supported frameworks, quick integration, 1. add as skill and 2. agent calls commands.
helm copilot-instructions.md
Instructions for PetePeter/helm, covering gamepad-cli-hub — copilot instructions, project purpose, system overview, data flow pipeline and key controls.
flyto-core CLAUDE.md
Instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.
fusion-skills AGENTS.md
AGENTS.md instructions for CrowdStrike/fusion-skills, covering agents.md, what this is, prerequisites, repository structure and skills ecosystem.
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).