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/cafecitohq/cafecito/agents-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/agents-md)<a href="https://agentmods.dev/instructions/cafecitohq/cafecito/agents-md"><img src="https://agentmods.dev/badge/instructions/cafecitohq/cafecito/agents-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 | $0.00206 | $0.00206 |
| Opus 5 | $0.00103 | $0.00103 |
| Sonnet 5 | $0.00041 | $0.00041 |
| Haiku 4.5 | $0.00021 | $0.00021 |
Grade A, and why
cafecito AGENTS.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.
What it actually says
Landing changes (cafecito)
Changes reach cafecito/main through the cafecito control plane — by landing, not by
pushing. Read-only work needs none of this.
Before you edit, sync for your base and reserve the files or symbols you'll touch, so
contention surfaces before the work is done. Then commit and submit the sha: separate
changesets land in parallel, overlaps regenerate from both sides' intent, contradictions
come back to a human, and every landing runs the gate. cafecito status shows the state.
If neither the cafecito tools nor the CLI are here, don't commit around the plane anyway — leave the work uncommitted or on a side branch and say so. A repo-specific exception (a release ritual, say) counts only if it is written down inside this block.
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 · 16 lines · 206 tokens per session scan A b21159fc80ec
cafecito AGENTS.md is an instructions file published in the GitHub repository Cafecitohq/cafecito (0 stars, last pushed 9d ago), licensed Apache-2.0. It adds 206 tokens to every session, about $0.0010 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 2026-09-01.
Other instructions, from other repositories
submitqueue AGENTS.md
Instructions for uber/submitqueue, covering submitqueue repository guide, key concepts, architecture, project layout and platform notes.
skills CLAUDE.md
Claude Code instructions for starslingdev/skills, covering starslingdev/skills, repository layout, working in this repo, opt-in debug logging (off by default) and registry audit triage (maintainers-only).
skills AGENTS.md
AGENTS.md instructions for starslingdev/skills, covering agents.md, what this repo is, repository layout, running tests and pull requests.
mergetrain AGENTS.md
AGENTS.md instructions for yongjip/mergetrain, covering agents.md, agent operating rules, useful commands, github cli authentication and boundaries.
mergetrain CLAUDE.md
Claude Code instructions for yongjip/mergetrain, covering claude.md — operating mergetrain from dispatch, shared operating protocol, rules, safety boundary and stable machine contract.
harmont-cli CLAUDE.md
Instructions for harmont-dev/harmont-cli, covering testing, documentation, dsl and keep the sdk, hm init templates, and docs in sync.