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/myrtlepn/gran-maestro/agents-mdgit clone --depth 1 https://github.com/myrtlepn/gran-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/myrtlepn/gran-maestro/agents-md)<a href="https://agentmods.dev/instructions/myrtlepn/gran-maestro/agents-md"><img src="https://agentmods.dev/badge/instructions/myrtlepn/gran-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 | $0.03103 | $0.03103 |
| Opus 5 | $0.01551 | $0.01551 |
| Sonnet 5 | $0.00621 | $0.00621 |
| Haiku 4.5 | $0.00310 | $0.00310 |
Grade B, and why
gran-maestro AGENTS.md scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
3. **User-global environment hooks**: `~/.claude/settings.json`의 `maestro-guard.sh`, `log-prompt.sh`, `check-version.sh` 등은 사용자 전역 환경 hook 계층이며 MST core SessionStart/Stop hook이 아닙니다. Copies of this mod
1 near-identical copy found in the catalogue:
- gran-maestro CLAUDE.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gran Maestro — Project Instructions
플러그인 세계관 및 스킬 레퍼런스: docs/CLAUDE.md 릴리스 체크리스트: docs/RELEASE.md
Hook 책임 경계 및 수정 규칙 (CRITICAL)
MST hook runtime은 3계층으로 구분합니다:
- Plugin core canonical runtime:
.claude-plugin/plugin.json의"hooks": "./hooks/hooks.json"와hooks/hooks.json의${CLAUDE_PLUGIN_ROOT}/hooks/...command가 일반 프로젝트의 유일한 canonical MST core hook 등록 경로입니다. - Project legacy / source-dev helper:
.claude/hooks/mst-*.sh또는$CLAUDE_PROJECT_DIR/.claude/hooks/...에 남아 있는 사본은 일반 프로젝트 canonical runtime이 아닙니다. 이 저장소에서 source-dev 보조·레거시 호환·cleanup/doctor 진단 대상으로만 취급합니다. - User-global environment hooks:
~/.claude/settings.json의maestro-guard.sh,log-prompt.sh,check-version.sh등은 사용자 전역 환경 hook 계층이며 MST core SessionStart/Stop hook이 아닙니다.
.claude/hooks/ 파일은 직접 수정 금지. /mst:on은 일반 프로젝트에 .claude/hooks 사본이나 settings.local.json hooks block을 canonical runtime으로 주입하면 안 됩니다.
이 플러그인의 MST core hook을 수정하려면 최종 source of truth는 /Users/brandev/mygit/gran-maestro/hooks/ 하위 파일입니다.
Hook 수정이 필요할 때는 반드시 아래 순서를 따릅니다:
hooks/원본 수정: 프로젝트 루트의hooks/디렉토리 파일을 수정- canonical 등록 확인:
.claude-plugin/plugin.json의"hooks": "./hooks/hooks.json"와hooks/hooks.json의${CLAUDE_PLUGIN_ROOT}/hooks/...command가 변경 의도와 일치하는지 확인 - source repo 보조 사본 동기화가 필요한 경우에만 복사: 이 저장소의 legacy/source-dev 진단을 위해 필요한 경우
cp hooks/*.sh .claude/hooks/실행. 일반 프로젝트/mst:on동작으로 해석하지 않습니다. - 플러그인 캐시에 복사: 릴리스/검증 목적상 필요한 버전에
cp hooks/*.sh ~/.claude/plugins/cache/gran-maestro/mst/{버전}/hooks/및 legacy 보조가 필요한 경우에만cp hooks/*.sh ~/.claude/plugins/cache/gran-maestro/mst/{버전}/.claude/hooks/ - 커밋:
hooks/와 실제로 동기화한 보조 사본 변경사항을 함께 커밋
hooks/ ← 플러그인 소유 원본 및 canonical command 대상 (수정 대상)
hooks/hooks.json ← plugin core canonical hook registration
.claude/hooks/ ← source repo legacy/source-dev 보조 사본 (일반 프로젝트 canonical runtime 아님)
~/.claude/settings.json ← user-global environment hook 계층 (MST core hook 아님)
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 · 172 lines · 3,103 tokens per session scan B df9ceb5592ae
gran-maestro AGENTS.md is an instructions file published in the GitHub repository myrtlepn/gran-maestro (24 stars, last pushed 16d ago), licensed MIT. It adds 3,103 tokens to every session, about $0.0155 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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).
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.
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 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.