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/joouis/agent-maestro/agents-mdgit clone --depth 1 https://github.com/Joouis/agent-maestroWrote 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/joouis/agent-maestro/agents-md)<a href="https://agentmods.dev/instructions/joouis/agent-maestro/agents-md"><img src="https://agentmods.dev/badge/instructions/joouis/agent-maestro/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 5.1 | $0.01498 | $0.01498 |
| Opus 5 | $0.00749 | $0.00749 |
| Sonnet 5 | $0.00300 | $0.00300 |
| Haiku 4.5 | $0.00150 | $0.00150 |
Grade A, and why
agent-maestro 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 yesterday.
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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents working in this repository. Human contributors should read README.md first.
Project overview
Agent Maestro is a VS Code extension that:
- Orchestrates third-party AI coding extensions (Cline, Roo Code, Kilo Code, etc.) via internal adapters.
- Exposes a local proxy server (default port
23333) presenting OpenAI-, Anthropic-, and Gemini-compatible APIs backed by the VS Code Language Model API (GitHub Copilot models), used by clients such as Claude Code, Codex, and Gemini. - Runs an MCP server (default port
23334) for Model Context Protocol clients.
Primary language: TypeScript (ESM, Node ≥ 22, VS Code ≥ 1.100). Package manager: pnpm 11.
Repository layout
src/extension.ts— extension entry point.src/commands/— VS Code command handlers registered inpackage.json.src/core/— adapters for third-party extensions (ClineAdapter,RooCodeAdapter, etc.) and the centralcontroller.src/server/— proxy + MCP servers.routes/anthropicRoutes.ts,routes/openai/— API-compatible endpoints.schemas/— Zod request/response schemas (also drive OpenAPI).utils/— request conversion helpers between Anthropic/OpenAI and the VS Code LM API.
src/utils/— shared utilities (logger, config, chat-model resolution, Claude Code helpers).src/test/— Mocha tests run via@vscode/test-electron.docs/,website/— user-facing documentation..changeset/— pending release notes (Changesets).
Known upstream (VS Code) issues
- Image MIME re-encode — the VS Code LM API re-encodes images to PNG when both dimensions exceed 768px without updating their declared MIME type, which breaks providers that sniff bytes (e.g. Anthropic vision). Worked around in
src/server/utils/imageMime.ts. Re-check this whenever bumpingengines.vscode— if upstream starts preserving the source format, the workaround must be removed or it will cause a new mismatch. Seedocs/vscode-image-mime-defect.md.
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.
- yesterday First seen · 103 lines · 1,498 tokens per session scan A c47d137ce603
agent-maestro AGENTS.md is an instructions file published in the GitHub repository Joouis/agent-maestro (205 stars, last pushed today), licensed MIT. It adds 1,498 tokens to every session, about $0.0075 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 2026-09-04.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
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 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).