Borrowing it
Nothing to install: this file belongs to 23blocks-OS/ai-maestro. 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/23blocks-OS/ai-maestro/main/CLAUDE.mdgit clone --depth 1 https://github.com/23blocks-OS/ai-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/23blocks-os/ai-maestro/claude-md)<a href="https://agentmods.dev/instructions/23blocks-os/ai-maestro/claude-md"><img src="https://agentmods.dev/badge/instructions/23blocks-os/ai-maestro/claude-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/23blocks-os/ai-maestro/claude-md"><img src="https://agentmods.dev/badge/instructions/23blocks-os/ai-maestro/claude-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 | $0.01979 | $0.01979 |
| Opus 5.5 | $0.00792 | $0.00792 |
| Sonnet 5.5 | $0.00396 | $0.00396 |
| Haiku 4.5 | $0.00198 | $0.00198 |
Grade A, and why
ai-maestro CLAUDE.md scanned grade A with 1 finding 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 21d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Is the server up? `curl localhost:23000/api/sessions` (there is no `/api/health`). How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
AI Maestro is a dashboard and orchestrator for fleets of AI coding agents
(Claude Code, Codex, Grok Build, others) running in tmux, on one machine or across hosts.
Next.js 14 (App Router) + a custom server.mjs (HTTP and WebSockets on one
port), React 18, xterm.js, node-pty, Tailwind, CozoDB per agent. Port 23000.
How the subsystems work is in docs/ARCHITECTURE.md; read the section you need.
Commands
yarn install
yarn dev # dev server with hot reload, http://localhost:23000
yarn build && yarn start # production
yarn headless:prod # API-only mode (no UI), used on worker hosts
yarn test # vitest; CI runs it on every push
pm2 restart ai-maestro # restart the production server
- Is the server up?
curl localhost:23000/api/sessions(there is no/api/health). - Never run
yarn buildin the checkout a live server runs from. It replaces.next/under the running process, and the UI stops loading (it asks for chunks that no longer exist). Build in a separate worktree, or build and restart together.
Versions and pull requests
- Bump with
./scripts/bump-version.sh patch|minor|major. It updates every version reference; do not edit version numbers by hand. Every PR to main carries a version bump and a CHANGELOG entry. - Before a PR:
yarn testpasses,yarn buildpasses (outside the live checkout), version bumped. aimaestro-agent.sh(the agents CLI) has its ownv1.xversion, released through the plugin.- Draft an X post (in
marketing/, which is gitignored) for releases only, not for every PR.
The Claude Code hook has one source of truth
ai-maestro-hook.cjs ships from three byte-identical copies. Edit only
scripts/claude-hooks/ai-maestro-hook.cjs, then run
bash scripts/sync-plugin-hook.sh. tests/plugin-hook-sync.test.ts fails CI
if the copies drift.
The plugin (plugin/ submodule)
plugin/ is the plugin builder (23blocks-OS/ai-maestro-plugins), not a
plugin. plugin.manifest.json lists sources; build-plugin.sh --clean
assembles them into plugin/plugins/ai-maestro/ (build output, committed).
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.
- 21d ago Changed · +4 tokens per session 3dd3955da87d
- 26d ago Changed · -901 lines · -8,547 tokens per session 70f6e105fd94
- 1mo ago Changed · +7 lines · +80 tokens per session 1c518925a835
- 1mo ago Changed · +39 lines · +505 tokens per session 47ca4cea22db
- 1mo ago Changed · +4 lines · +150 tokens per session a88d07f5e34d
- 1mo ago First seen · 1,010 lines · 9,787 tokens per session scan A 9838e3c697f1
ai-maestro CLAUDE.md is an instructions file published in the GitHub repository 23blocks-OS/ai-maestro (839 stars, last pushed today), licensed MIT. It adds 1,979 tokens to every session, about $0.0079 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.