Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/myrtlepn/gran-maestronpx agentmods add skills/myrtlepn/gran-maestro/resumeWrote 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/resume)<a href="https://agentmods.dev/skills/myrtlepn/gran-maestro/resume"><img src="https://agentmods.dev/badge/skills/myrtlepn/gran-maestro/resume/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/resume"><img src="https://agentmods.dev/badge/skills/myrtlepn/gran-maestro/resume.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00072 | $0.03311 |
| Opus 5 | $0.00036 | $0.01656 |
| Sonnet 5 | $0.00014 | $0.00662 |
| Haiku 4.5 | $0.00007 | $0.00331 |
Grade A, and why
resume 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
maestro:resume
목적: .gran-maestro/pending.ndjson queue에서 다음 action을 하나 pop하여 해당 스킬을 호출한다. interactive resume과 외부 wrapper(scripts/mst-loop.sh)는 같은 queue contract를 공유하지만, headless runtime implementation path는 python3 {PLUGIN_ROOT}/scripts/mst.py queue drain-headless --json 이다. 세션 교차/재진입/동시 세션에서는 queue를 1순위 SSoT로 사용하고, queue가 비어 있을 때만 resolver fallback(workflow_state, wakeup-hint)으로 다음 action을 큐에 복원한다. Claude print-mode로 /mst:resume를 직접 호출하던 방식은 historical 설명 문자열일 뿐 active runtime path가 아니다.
질문 답변으로 재개
--answer Q-... --value "..."가 있으면 일반 queue 처리 전에 저장된 질문에 답을 기록하고 소비한다.
python3 {PLUGIN_ROOT}/scripts/mst.py question answer {Q_ID} --answer "{ANSWER_VALUE}" --json
python3 {PLUGIN_ROOT}/scripts/mst.py question consume {Q_ID} --json
두 명령이 성공하면 question artifact에 저장된 resume_skill/resume_args가 queue에 한 번 들어간다. 이후 아래의 기존 peek → pop → skill 호출 흐름을 그대로 수행한다. 호출 인자로 resume target을 새로 받거나 바꾸지 않는다. Codex request_user_input이 여러 답을 객체로 반환한 경우에는 그 JSON을 파일로 저장해 첫 명령의 --answer-file에 전달한 뒤 같은 consume 흐름을 사용한다.
Gate
Entry
.gran-maestro/pending.ndjsonqueue에서 정확히 한 개의 action만 pop하여 실행한다.- AUTO_MODE 판정은 queue entry의
auto필드와args내-a플래그를 그대로 사용한다. 재판단 금지.
경로 우선순위 (MANDATORY)
resume 경로는 queue entry를 SSoT로 사용합니다. plan.json 또는 tmp/mst-state-{PPID}.json의 next_action.auto_mode 등을 fallback으로 읽어 args를 재조합하지 않습니다. 자율 모드 의도는 enqueue 시점에 queue entry의 auto 필드와 args 내 -a 토큰으로 함께 표현되어야 하며, 이 불변 계약은 scripts/mst_cmds/_common.py::queue_enqueue가 강제합니다 (REQ-639 T01 참조).
DOD-007 canonical identity boundary: MST_SESSION_ID / mst_session_id만 canonical identity source다. Legacy-only input(MST_STATE_PPID, owner_ppid, owner_session_id, owner_pid, Claude hook session_id, transcript UUID, MST_SNAPSHOT_SESSION_ID, legacy aliases sessionId/session_id)은 diagnostic-only이며 canonical source, fallback, alias, migration requirement가 아니다. Legacy-only input은 session/state/history/snapshot/recovery/lock mutation 없이 structured non-success로 종료해야 한다. Canonical MST_SESSION_ID/mst_session_id와 legacy 값이 충돌하면 canonical identity가 우선하고 legacy 값은 override/repair/merge/persist source가 될 수 없다.
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 · 177 lines · 72 tokens per session scan A d1a77fd0f83b
resume is a skill published in the GitHub repository myrtlepn/gran-maestro (24 stars, last pushed 20d ago), licensed MIT. It adds 72 tokens to every session and 3,311 once invoked, about $0.0004 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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…