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 ReinaMacCredy/maestro --skill maestro-bundlegit clone --depth 1 https://github.com/ReinaMacCredy/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/reinamaccredy/maestro/maestro-bundle)<a href="https://agentmods.dev/skills/reinamaccredy/maestro/maestro-bundle"><img src="https://agentmods.dev/badge/skills/reinamaccredy/maestro/maestro-bundle/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/reinamaccredy/maestro/maestro-bundle"><img src="https://agentmods.dev/badge/skills/reinamaccredy/maestro/maestro-bundle.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 | $0.00032 | $0.01997 |
| Opus 5 | $0.00016 | $0.00999 |
| Sonnet 5 | $0.00006 | $0.00399 |
| Haiku 4.5 | $0.00003 | $0.00200 |
Grade A, and why
maestro-bundle 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 4d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
maestro-bundle
Routing brain for maestro method work. Decide the tier first, then follow the matching skill; this skill owns the bundle lifecycle itself.
Tier rule
Decide the tier from the request alone, before any recon: no bundle files, no code reading, no store lookups until the tier is known.
- quickfix: the diff fits in one sentence and hits no Full trigger below. Do it
directly, verify inline (run the smallest check that can falsify it), no
skill, no record. If it grows past one sentence, stop,
maestro work add, and continue as Light. - Light: one session, one branch, and the acceptance fits in a sentence. Work
directly with
maestro work add|start|done(no bundle). The work item is the floor becausemaestro ready, attention, and the Supervisor's brief read the store, not a session task list. - Full: any trigger below. Open a bundle, in the
store whose checkout will change: a design walk run in the Hub room still
builds where the code lives. List Hub decisions in the SPEC as
hub:<id>(maestro bundle showrenders them) and note the bundle on the Hub map and the map on the bundle's work item.
Open a bundle when ANY trigger holds:
- the work spans multiple sessions or must survive a context reset
- multiple branches, worktrees, or agents touch the same scope
- the scope is high risk (schema change, wide refactor, irreversible step)
- a previous fix attempt for the same problem failed
- the user asks for one
Ceremony scales with tier. Quickfix and Light never demand a SPEC or a test; Red tests are a Full-tier instrument for the risks the SPEC names, and nothing beyond that list. Light work that hits a Full trigger mid-task opens the bundle then and backfills it from what is already done; finished work is evidence, never redone. During a production incident, fix and verify first, then backfill and close the bundle immediately after stabilizing.
maestro bundle open <id> --work <workId> # scaffold SPEC/NOTES/VERIFY, link work
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.
- 4d ago Changed · +6 lines ecc1fb16e83c
- 5d ago Changed · +86 lines 05b5d42042e3
- 11d ago First seen · 90 lines · 32 tokens per session scan A ffc9ca994062
maestro-bundle is a skill published in the GitHub repository ReinaMacCredy/maestro (231 stars, last pushed 4d ago), licensed MIT. It adds 32 tokens to every session and 1,997 once invoked, about $0.0002 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
pn-session-handoff
End a session with a structured handoff document and two reflection questions. Captures shipped work, dangling state, resume action, and blind spots. Use via /pn-handoff before closing a session. Pairs with pn-continual-learning for AGENTS.md updates.
pn-context-engineering
Curate what the agent sees and when — rules vs specs vs task files vs errors vs history. Use when starting a session, switching tasks, output quality drops, or the agent ignores project conventions.
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…
generate-run-commands
Generate or modify run commands for the current session. Use when the user wants to set up or update run commands that appear in the session's Run button.
get-search-view-results
Get the current search results from the Search view in VS Code.
post-build-flow
Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.