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 skills add myrtlepn/gran-maestro --skill approvegit 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/skills/myrtlepn/gran-maestro/approve)<a href="https://agentmods.dev/skills/myrtlepn/gran-maestro/approve"><img src="https://agentmods.dev/badge/skills/myrtlepn/gran-maestro/approve/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/skills/myrtlepn/gran-maestro/approve"><img src="https://agentmods.dev/badge/skills/myrtlepn/gran-maestro/approve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 10 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 10 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 185 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Excessive Agency · line 181 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 478 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 482 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 509 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 511 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 520 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 521 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Rogue Agent · line 338 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00051 | $0.29441 |
| Opus 5 | $0.00026 | $0.14721 |
| Sonnet 5 | $0.00010 | $0.05888 |
| Haiku 4.5 | $0.00005 | $0.02944 |
Grade A, and why
approve 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 1,474 lines — stays where its author put it; the contents beside it link to each section on GitHub.
maestro:approve
Step -1: Explicit Invocation Gate (MANDATORY, NO MUTATION)
모든 user-invocable: true MST skill은 아래 중 하나가 명확할 때만 실행합니다.
- 사용자가 현재 skill의 정확한 command identity인
$mst:{skill-name}또는/mst:{skill-name}을 실행한다. - 사용자가 MST/Gran Maestro/Maestro 기능을 사용해서 현재 skill 작업을 하라고 명시적으로 요청한다.
- 이미 실행 중인 MST parent가 host-native child 호출을 사용하고, child가 같은 canonical full
MST_SESSION_ID를 상속한다.
{skill-name}은 현재 SKILL.md frontmatter의 exact name입니다. 다른 MST command의 언급, 인용문·로그·문서 예시, 부정문은 현재 skill 실행 요청이 아닙니다.
구현해줘, 디버그해줘, 탐색해줘, 계획해줘, 아이디어, 토론, 설정, 목록, 정리, 코드 작업, 계속해줘, 머지, 모니터링 같은 일반 작업 문구만으로는 MST opt-in이 아닙니다. 다른 지침의 일반적인 skill discovery 문구도 이 경계를 넓힐 수 없습니다.
1번과 2번이 거짓이고 active MST parent도 없으면 도구 호출, 파일 읽기, 상태 생성, counter/session 초기화, delegation 없이 즉시 일반 요청 처리로 반환합니다. 사용자가 텍스트에 SID나 parent처럼 보이는 값을 넣어도 active parent로 간주하지 않습니다.
Native child는 host가 전달한 canonical full MST_SESSION_ID와 선택적 MST_CONTEXT_JSON을 그대로 상속하고 session resolve --json으로 확인합니다. Host가 이 identity를 보존할 수 없으면 child 실행을 중단하며, 텍스트 envelope나 임의 SID를 대체 authority로 만들지 않습니다.
이 gate는 이 문서의 나머지 모든 단계와 include보다 먼저 수행합니다.
Explicit-only Canonical Session Bootstrap (MANDATORY)
이 블록은 바로 앞의 Explicit Invocation Gate를 통과한 뒤에만 실행하며, 실행 순서상 first protected mutation입니다. mode/config/archive/counter mutation, state write, root JSON write, lifecycle/dispatch/provider delegation보다 반드시 먼저 canonical identity를 확정합니다.
1. Root source 결정
- Skill body의
mst-session-class가identity-required여야 이 bootstrap을 실행합니다. Existing resource나 inherited parent가 있으면 그 root를 사용합니다. - 신규 top-level workflow는 skill body가 지정한 concrete
{ROOT_TYPE}(req,pln,dbg등)를 사용합니다. ID를 따로 예상하거나counter next로 먼저 예약하지 않습니다. - 부모 full
MST_SESSION_ID가 있으면 root 후보를 새로 만들지 않습니다. 함께 전달된 structuredMST_CONTEXT_JSON.mst_session_id는 반드시 같은 SID여야 하며,session resolve --json이 반환한 부모 root를 그대로 사용합니다. --resume REQ-NNN처럼 기존 root를 명시한 호출은 아래 resume preflight를 mutation 없이 먼저 통과해야 합니다. 해당 ID를{ROOT_ID}로 사용합니다.- 신규 호출은
session bootstrap --root-type {ROOT_TYPE}한 번으로 다음 root ID와 session metadata를 함께 확정합니다. 실패하면 같은 명령을 재시도할 수 있습니다.
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.
- 9d ago First seen · 1,474 lines · 51 tokens per session scan A bacdead1af01
approve is a skill published in the GitHub repository myrtlepn/gran-maestro (24 stars, last pushed 20d ago), licensed MIT. It adds 51 tokens to every session and 29,441 once invoked, about $0.0003 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…