Borrowing it
Nothing to install: this file belongs to Cafecitohq/cafecito. 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/Cafecitohq/cafecito/main/CLAUDE.mdgit clone --depth 1 https://github.com/Cafecitohq/cafecitoWrote 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/cafecitohq/cafecito/claude-md)<a href="https://agentmods.dev/instructions/cafecitohq/cafecito/claude-md"><img src="https://agentmods.dev/badge/instructions/cafecitohq/cafecito/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/cafecitohq/cafecito/claude-md"><img src="https://agentmods.dev/badge/instructions/cafecitohq/cafecito/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00902 | $0.00902 |
| Opus 5.5 | $0.00361 | $0.00361 |
| Sonnet 5.5 | $0.00180 | $0.00180 |
| Haiku 4.5 | $0.00090 | $0.00090 |
Grade A, and why
cafecito 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 1mo 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cafecito — conventions for Claude Code sessions
Vocabulary (SPEC.md §1.1 — enforced in code, docs, and commit messages)
Changesets land; collisions commute, regenerate, or escalate. "Merge" is
reserved for git's textual mechanism (merge-tree, 3-way) and the market category
("merge queue"). No cafecito code path resolves a merge conflict.
Hard rules
cafecito/package is stdlib-only — zero runtime dependencies is a feature. pytest is the user's gate command, never our import.- The landing gate gates every landing, clean textual merges included. Never weaken this; two red mains during development are why (see bench/README.md).
phase0/is the frozen evidence base — add new experiments, never refactor old ones.- Commits: DCO sign-off (
-s) required; append-only decision history in docs.
Versions & pushing (the four-heads invariant)
- A session that touched
mainends with all four heads identical —git rev-parse main cafecito/main origin/main origin/cafecito/mainprints one sha four times — and the suite green, or states out loud why not. Local commits mid-session are fine; ending half-synced is the failure mode. - After committing directly to
main:python3 -m cafecito.cli advance --repo ., then push both refs in one command —git push origin main cafecito/main. CI's plane-sync job goes red when a pushedmainleavescafecito/maintrailing. - Tags are releases, not bookmarks. Pushing
v*publishes to PyPI via trusted publishing, and PyPI never reuses a version — so never create a local-onlyv*tag. Release ritual: suite green → bumppyproject.tomlANDcafecito/__init__.py(test_version.py pins them together) → commit, advance, four-heads check → push branches → tagvX.Y.Z→ push the tag in the same breath → watch publish.yml, verify on pypi.org. Versioning is0.MINOR.PATCH: minor for features, patch for fixes.
Commands
- Tests:
phase0/workdir/venv-test/bin/python -m pytest -q cafecito/tests - Engine smoke (live regen, needs
claudeCLI):python3 -m cafecito.tests.smoke --pytest-python phase0/workdir/venv-test/bin/python - Demo dry run:
DEMO_DELAY=0 PYTEST_PY=$PWD/phase0/workdir/venv-test/bin/python ./examples/demo.sh
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.
- 1mo ago First seen · 60 lines · 902 tokens per session scan A c852e6497aab
cafecito CLAUDE.md is an instructions file published in the GitHub repository Cafecitohq/cafecito (0 stars, last pushed 26d ago), licensed Apache-2.0. It adds 902 tokens to every session, about $0.0036 per session on Opus 5.5. 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 2026-09-01.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.