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/mbanderas/maestro/claude-mdgit clone --depth 1 https://github.com/mbanderas/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/mbanderas/maestro/claude-md)<a href="https://agentmods.dev/instructions/mbanderas/maestro/claude-md"><img src="https://agentmods.dev/badge/instructions/mbanderas/maestro/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 | $0.00338 | $0.00338 |
| Opus 5 | $0.00169 | $0.00169 |
| Sonnet 5 | $0.00068 | $0.00068 |
| Haiku 4.5 | $0.00034 | $0.00034 |
Grade A, and why
maestro 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 3d 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.
What it actually says
CLAUDE.md — Maestro for Claude Code
@AGENTS.md
Claude Code Runtime Rules
- Subagents in single session by default; scope tools per subagent. Agent teams only for long-running parallel workstreams with shared state.
- Worktree isolation: 2+ specialists in one group modifying files —
pass
isolation: "worktree"per Agent call. Skip for read-only specialists, a single writer, or disjoint <=3-file scopes. - Hooks > prompt reminders for structural checks; the shipped pack
(gate-reminder, subagent-guard, loop-guard, phase-scope,
gate-telemetry, doctrine-guard) lives in
hooks/. - Read tool: 2,000 lines/call; results >50,000 chars truncate silently; a "PARTIAL view" notice means re-issue with offset/limit.
- S10 mapping:
/loop <interval>or/schedule(durable cloud); no interval = self-paced ScheduleWakeup (polling <=270s, otherwise 1200s+; never poll harness-tracked work — completion notifies). Event waits: persistent Monitor primary, wakeup as fallback heartbeat. Checkpoint:_<task>.mdin repo root (gitignore_*). Workflow tool only on explicit user opt-in; S9 caps apply.
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.
- 3d ago First seen · 30 lines · 338 tokens per session scan A 4422f9504cac
maestro CLAUDE.md is an instructions file published in the GitHub repository mbanderas/maestro (5 stars, last pushed 7d ago), licensed MIT. It adds 338 tokens to every session, about $0.0017 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
sigmap AGENTS.md
AGENTS.md instructions for manojmallick/sigmap, covering sigmap — agents.md, append strategy (required), auto-generated signatures, code signatures and sigmap commands.
llm-ide-rules react.instructions.md
Instructions for iloveitaly/llm-ide-rules, covering react, mock data, react hook form and styling.
obsidian-mcp-rs CLAUDE.md
Instructions for MrRefactoring/obsidian-mcp-rs, covering claude.md, commands, build / run, tests and lint gates enforced by ci (.github/workflows/ci.yml).
llm-ide-rules typescript.instructions.md
Instructions for iloveitaly/llm-ide-rules, covering typescript and dates & times.
carrymem CLAUDE.md
Instructions for lulin70/carrymem, covering claude.md — carrymem ai 协作指引, 项目概述, 安装与构建, 用户安装（已发布到 pypi） and 完整功能安装.
llm-ide-rules python-route-tests.instructions.md
Instructions for iloveitaly/llm-ide-rules, a project described as: Centralized LLM prompt instructions for Copilot and Cursor, including scripts to convert and sync rules for Python, React, Shell, and TypeScript. Designed for rapid reuse and contribution across projects.