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/ifokeev/airbrowser-mcp/claude-mdgit clone --depth 1 https://github.com/ifokeev/airbrowser-mcpWrote 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/ifokeev/airbrowser-mcp/claude-md)<a href="https://agentmods.dev/instructions/ifokeev/airbrowser-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ifokeev/airbrowser-mcp/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 | $0.02649 | $0.02649 |
| Opus 5 | $0.01324 | $0.01324 |
| Sonnet 5 | $0.00530 | $0.00530 |
| Haiku 4.5 | $0.00265 | $0.00265 |
Grade A, and why
airbrowser-mcp 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 5d 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 — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - Important Project Information
Critical Rules
Package Management
Always use uv instead of pip for Python package management:
- Install packages:
uv pip install <package> - Run Python scripts:
uv run python3 <script>(ensures correct environment) - Run tools:
uvx <tool>(e.g.,uvx ruff check src/) - Install from requirements:
uv pip install -r requirements.txt
Git Commits
Use Conventional Commits format: https://www.conventionalcommits.org/
Format: <type>(<scope>): <description>
Types:
feat: New featurefix: Bug fixdocs: Documentation onlystyle: Code style (formatting, semicolons, etc.)refactor: Code change that neither fixes a bug nor adds a featureperf: Performance improvementtest: Adding or fixing testschore: Build process, dependencies, or toolingci: CI/CD configuration
Examples:
feat(api): add browser screenshot endpointfix(launcher): handle missing Chrome binarydocs: update installation instructionschore(deps): upgrade seleniumbase to 4.32.0
Create separate logical commits with scope. Do not bundle unrelated changes into one commit:
- Good: 3 commits for
feat(mcp),docs,refactor(tests) - Bad: 1 commit with "feat(mcp): add feature and update docs and refactor tests"
Do NOT add AI attribution to commits. Never include:
- "🤖 Generated with Claude Code"
- "Co-Authored-By: Claude..."
- Any other AI/Claude attribution text
Token Efficiency
⚠️ MINIMIZE OUTPUT TO REDUCE TOKEN USAGE
When running commands with verbose output (tests, builds, logs):
- Always pipe to
tail -nto show only the final result/summary - Example:
./scripts/run_tests.sh 2>&1 | tail -10 - Never stream full test logs, build logs, or large file contents
File Size Limits
⚠️ Keep files under 1000 lines. Prefer creating multiple smaller files over one large "god object" file.
- If a file approaches 1000 lines, refactor into logical modules
- Split by responsibility: separate concerns into different files
- Better: 5 files at 200 lines each than 1 file at 1000 lines
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.
- 5d ago First seen · 268 lines · 2,649 tokens per session scan A 4999822220da
airbrowser-mcp CLAUDE.md is an instructions file published in the GitHub repository ifokeev/airbrowser-mcp (9 stars, last pushed 2mo ago), licensed MIT. It adds 2,649 tokens to every session, about $0.0132 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 2026-08-31.
Other instructions, from other repositories
opentabs AGENTS.md
Instructions for opentabs-dev/opentabs, covering project instructions for codex, project overview, architecture, you are connected to this project's mcp server and workflow skills.
neobrowser AGENTS.md
Instructions for pitiflautico/neobrowser, covering agents.md — orientation for ai agents & contributors, build, run, test (rust — primary), how it works (rust module map), conventions and ci and release gates.
scout CLAUDE.md
Claude Code instructions for klarlabs-studio/scout, covering claude.md, repository, what this is, commands and build & verify.
empir3-bridge AGENTS.md
AGENTS.md instructions for empir3hq/empir3-bridge, covering empir3 bridge — agent & contributor guide, what lives here, before you edit, run locally and release / publish.
agentpantry AGENTS.md
Instructions for escoffier-labs/agentpantry, covering repository guidance, definition of done, code map, rules and security invariants (do not weaken).
worbrow AGENTS.md
AGENTS.md instructions for noisystreet/worbrow, covering agents.md, project identity, hard constraints (revert on violation), modifying architecture docs and commit conventions.