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/biomejs/biome/agents-mdgit clone --depth 1 https://github.com/biomejs/biomeWrote 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/biomejs/biome/agents-md)<a href="https://agentmods.dev/instructions/biomejs/biome/agents-md"><img src="https://agentmods.dev/badge/instructions/biomejs/biome/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 | $0.00984 | $0.00984 |
| Opus 5 | $0.00492 | $0.00492 |
| Sonnet 5 | $0.00197 | $0.00197 |
| Haiku 4.5 | $0.00098 | $0.00098 |
Grade A, and why
biome 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 today.
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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guidelines for Contributing to Biome
This file contains rules that apply to every automated contribution. Detailed workflows live in .claude/skills/ or the contributing guides they reference.
[!NOTE] Automated agents may add 🤖🤖🤖 to the end of a PR title to opt into the streamlined merge process.
Communication
- Keep responses short, factual, and technical.
- Do not use emojis in source, comments, rustdoc, diagnostics, tests, snapshots, commits, issues, PR communication, or agent output. The PR-title marker above is the only exception.
- Do not claim a Biome function, module, behavior, or convention exists without an exact file and line, a source excerpt, or a reproducible command.
- If evidence is unavailable, state that rather than presenting the claim as fact.
Before Editing
- Read files in full before wide-ranging changes, before editing an unfamiliar file, and whenever the user requests an investigation or audit.
- Inspect the surrounding implementation and current contributing guide instead of copying remembered APIs or commands.
- Preserve unrelated worktree changes. Never revert or rewrite changes you did not make.
Implementation Gate
- Make the smallest change that satisfies the requested behavior.
- Add tests for code changes. Bug fixes require a case that fails without the fix.
- Run the narrowest relevant tests first, then broader checks when justified.
- Run the tests of the current crate to check possible regressions.
- Review generated snapshots as behavior, not disposable output.
- Run
just fandjust lbefore committing.
Load testing-codegen for test fixtures, snapshots, and generator selection.
Required generated artifacts:
| Changed source | Required command |
|---|---|
Grammar .ungram |
just gen-grammar <lang> |
Lint rule in *_analyze |
just gen-rules and just gen-configuration if you changed rule name |
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.
- today Changed · +7 tokens per session d82fedc09a8f
- 4d ago First seen · 80 lines · 977 tokens per session scan A 0d0159497979
biome AGENTS.md is an instructions file published in the GitHub repository biomejs/biome (25,705 stars, last pushed today), licensed Apache-2.0. It adds 984 tokens to every session, about $0.0049 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 2026-08-30.
Other instructions, from other repositories
electron CLAUDE.md
Instructions for electron/electron, covering electron development guide, running nodemodules binaries, project overview, directory structure and build tools setup.
electron copilot-instructions.md
Instructions for electron/electron, covering copilot instructions for electron, build system, linting, running a single test and example: npm run test -- -g "ipc".
oxc AGENTS.md
Instructions for oxc-project/oxc, covering agents.md - ai assistant guide for oxc, ai usage policy for contributors, repository structure, core crates and development commands.
oxc copilot-instructions.md
Instructions for oxc-project/oxc: When reviewing pull requests in this repository.
fallow
Rust-native codebase analyzer for TypeScript and JavaScript projects.
static-analysis AGENTS.md
Instructions for analysis-tools-dev/static-analysis, covering guidelines for ai agents and assistants and 🤖 instructions for the ai.