Borrowing it
Nothing to install: this file belongs to recomposesh/recompose. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/recomposesh/recompose/main/CLAUDE.mdgit clone --depth 1 https://github.com/recomposesh/recomposeWrote 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/instructions/recomposesh/recompose/claude-md)<a href="https://agentmods.dev/instructions/recomposesh/recompose/claude-md"><img src="https://agentmods.dev/badge/instructions/recomposesh/recompose/claude-md.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 | $0.02702 | $0.02702 |
| Opus 5 | $0.01351 | $0.01351 |
| Sonnet 5 | $0.00540 | $0.00540 |
| Haiku 4.5 | $0.00270 | $0.00270 |
Grade A, and why
recompose 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 3d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
recompose project rules
Before starting any work
- Research current industry best practices for the topic (web search), independent of this codebase.
- If a clear standard path exists, bring the codebase into conformance with it first, then do the work.
- When a request sounds like a capability of a platform or tool already in use (GitHub, Electron, pnpm, and so on), search for the built-in or off-the-shelf solution first. Write a custom implementation only after that search comes up empty.
Git workflow
mainstays protected. Never commit to it, locally or remotely.- Every job (feature, fix, docs, config, skills) gets its own worktree and branch, and lands through a PR. One job = one branch.
- Worktrees live at
.claude/worktrees/<name>, never beside the repository. A sibling directory reads as a second project to anyone browsing, andEnterWorktreerefuses to switch into a path outside that directory, which strands a subagent that needs to reach it. The repository's own tooling already assumes the convention:.vale.iniandcspell.jsonboth exclude.claude/worktrees.
CodeRabbit reviews
- Before acting on a finding, compare it with official docs and the actual code, and never apply it without checking first.
- Addressed a finding → reply on its thread naming the fixing commit, then resolve the thread immediately.
- Rejecting or deferring a finding → reply with the reasoning and leave the thread unresolved so CodeRabbit can respond; resolve only when the exchange settles.
- No conversation stays unresolved at the end of the day: when CodeRabbit acknowledges an exchange but leaves the thread open, resolve it yourself.
Skills
- Use the
ponytailskill for everything, since every task starts by invoking it. - Every session starts by invoking
karpathy-guidelinesbefore any other work.
Prose style
- Never use an em dash. Don't patch one out with a colon: rewrite the sentence so it reads as if it never had one.
- All authored markdown passes Vale: Microsoft base style with rules promoted to error, plus the house rules in
.vale/styles/recompose/(docs/adr/0025-vale-prose-gate.md). New vocabulary lands in the committed accept list through the PR diff. Implementation plans underdocs/superpowers/plans/sit outside both prose gates (Vale and cspell) as internal execution artifacts.
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.
- 3d ago First seen · 116 lines · 2,702 tokens per session scan A fce225f4d5e3
recompose CLAUDE.md is an instructions file published in the GitHub repository recomposesh/recompose (27 stars, last pushed 10d ago), licensed MIT. It adds 2,702 tokens to every session, about $0.0135 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 2026-09-03.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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).
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.
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.