Borrowing it
Nothing to install: this file belongs to eastlondoner/vibe-tools. 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/eastlondoner/vibe-tools/main/AGENTS.mdgit clone --depth 1 https://github.com/eastlondoner/vibe-toolsWrote 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/eastlondoner/vibe-tools/agents-md)<a href="https://agentmods.dev/instructions/eastlondoner/vibe-tools/agents-md"><img src="https://agentmods.dev/badge/instructions/eastlondoner/vibe-tools/agents-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/eastlondoner/vibe-tools/agents-md"><img src="https://agentmods.dev/badge/instructions/eastlondoner/vibe-tools/agents-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 | $0.04457 | $0.04457 |
| Opus 5 | $0.02228 | $0.02228 |
| Sonnet 5 | $0.00891 | $0.00891 |
| Haiku 4.5 | $0.00446 | $0.00446 |
Grade A, and why
vibe-tools 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 10d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- vibe-tools CLAUDE.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This is the vibe-tools repo. Here we build a cli tool that AI agents can use to execute commands and work with other AI agents.
This repo uses pnpm as the package manager and script runner.
use pnpm dev to run dev commands.
We add AI "teammates" as commands that can be asked questions. We add "skills" as commands that can be used to execute tasks.
Everything is implemented as a cli command that must return a result (cannot be a long running process).
The released commands are documented below. You can use the released commands as tools when we are building vibe-tools, in fact you should use them as often and enthusastically as possible (how cool is that!)
Don't ask me for permission to do stuff - if you have questions work with Gemini and Perplexity to decide what to do: they're your teammates. You're a team of superhuman expert AIs, believe in yourselves! Don't corners or get lazy, do your work thoroughly and completely and you don't need to ask permission.
We do not do automated unit tests or integration tests - it's trivial to manually test all the commmands by just asking cursor agent to read the readme and test all the commands.
console.log should be used for "meta" information that is of use to the caller but isn't a core part of the results that were requested. E.g. recording which model is being used to perfom an action.
console.error should be used for error messages.
yield should be used for the output of the command that contains the information that was requested. </logging and outputs>
Usage:
- Run with: pnpm serve-test
- Server starts at http://localhost:3000
- Place test HTML files in tests/commands/browser/
- Access files at http://localhost:3000/filename.html
remember that this will be a long running process that does not exit so you should run it in a separate background terminal.
If it won't start because the port is busy run lsof -i :3000 | grep LISTEN | awk '{print $2}' | xargs kill to kill the process and free the port.
to run test commands with latest code use pnpm dev browser <commands>
For interactive debugging start chrome in debug mode using:
open -a "Google Chrome" --args --remote-debugging-port=9222 --no-first-run --no-default-browser-check --user-data-dir="/tmp/chrome-remote-debugging"
note: this command will exit as soon as chrome is open so you can just execute it, it doesn't need to be run in a background task. </testing browser commands>
description: Global Rule. This rule should ALWAYS be loaded globs: ,**/ alwaysApply: true
description: Global Rule. This rule should ALWAYS be loaded. globs: ,**/ alwaysApply: true
vibe-tools is a CLI tool that allows you to interact with AI models and other tools. vibe-tools is installed on this machine and it is available to you to execute. You're encouraged to use it.
Direct Model Queries:
vibe-tools ask "<your question>" --provider <provider> --model <model> - Ask any model from any provider a direct question (e.g., vibe-tools ask "What is the capital of France?" --provider openai --model o3-mini). Note that this command is generally less useful than other commands like repo or plan because it does not include any context from your codebase or repository. In general you should not use the ask command because it does not include any context. The other commands like web, doc, repo, or plan are usually better. If you are using it, make sure to include in your question all the information and context that the model might need to answer usefully.
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.
- 10d ago First seen · 237 lines · 4,457 tokens per session scan A cd9aa359d57b
vibe-tools AGENTS.md is an instructions file published in the GitHub repository eastlondoner/vibe-tools (4,828 stars, last pushed 1y ago), licensed MIT. It adds 4,457 tokens to every session, about $0.0223 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
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.