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-workgit 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-work)<a href="https://agentmods.dev/skills/reinamaccredy/maestro/maestro-work"><img src="https://agentmods.dev/badge/skills/reinamaccredy/maestro/maestro-work/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-work"><img src="https://agentmods.dev/badge/skills/reinamaccredy/maestro/maestro-work.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 | $0.00034 | $0.02562 |
| Opus 5 | $0.00017 | $0.01281 |
| Sonnet 5 | $0.00007 | $0.00512 |
| Haiku 4.5 | $0.00003 | $0.00256 |
Grade A, and why
maestro-work 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 6d 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
maestro-work
Use for one accepted implementation unit. Keep the change inside the work
item's acceptance and authority. If the scope is unclear or must expand, stop
and return to maestro-design.
Tier first, recon second
Decide the tier from the request alone, before reading bundle files, the
store, or the rest of this skill (maestro-bundle tier rule):
- quickfix: a one-sentence diff with no Full trigger. Do it directly, verify inline with the smallest check that can falsify it, no work item, no test demanded, none of the machinery below.
- Light: one session, one branch, acceptance in a sentence.
maestro work add|start|doneis the whole record. Verify the changed surface inline; a regression test is written only for a real bug being fixed, never as ceremony: it reproduces the bug where it shows and lands with the fix, in the ordinary bugfix order, not through a red-green loop, and no TDD skill is loaded for it. No SPEC, no red list. - Full: an open bundle. Preconditions before any edit: the user's explicit
request to implement or fix this scope, and a SPEC whose Scope names this
work; its Red tests, when present, are the only tests written. A SPEC that predates the requested scope
(post-ship review findings, hardening follow-ups) counts as missing: return
to
maestro-designfirst. A throwaway prototype not yet approved to port ismaestro-explore's scope: fix it there without opening production work.
Before writing code, read any language-convention notes the user's setup provides for the language being edited. Repository conventions override them.
Dispatch
When work is handed to a lane (a Herdr pane in the room, or a sub-agent where no room exists), send this envelope:
Objective: <observable outcome>
Owned scope: <paths or responsibility>
Excluded scope: <explicit non-goals>
Mutation: <no-write | write-bounded: paths>
Stop condition: <done or blocked boundary>
Lane: scout | decision | delivery | challenge | shadow
Evidence required: <proof and layer>
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago Changed · +8 lines 1f439e910860
- 7d ago Changed · +85 lines · +6 tokens per session b0c84b92597a
- 12d ago First seen · 115 lines · 28 tokens per session scan A f59093e0f117
maestro-work is a skill published in the GitHub repository ReinaMacCredy/maestro (232 stars, last pushed 6d ago), licensed MIT. It adds 34 tokens to every session and 2,562 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
ts-library
Use when authoring TypeScript libraries or npm packages - covers project setup, package.json exports, build tooling (tsdown/unbuild), API design patterns, type inference tricks, testing, and publishing to npm. Use when bundling, configuring dual CJS/ESM output, or setting up release workflows.
Unit Test Scaffold (TypeScript)
Generate TypeScript unit test skeletons (Jest/Vitest) from specifications.
pn-writing-skills
Applies TDD to skill authoring: validation scenarios first, then SKILL.md. Use when creating new skills, editing existing skills, or verifying skills work before deployment.
pn-systematic-debugging
Root cause analysis with triage mode — Phase 0 feedback loop, investigate first, one question max, then isolate, hypothesize, confirm. Outputs TDD fix plan with RED-GREEN cycles; optional GitHub issue via GitHub MCP. Use when debugging a failure or bug.
pn-testing-strategy
Testing strategy and pyramid. Unit/integration/E2E ratio, Vitest vs Playwright vs MSW, contract testing, and test-environment setup. Use when defining or reviewing a project's testing approach.
pn-discipline-philosophy
Defines engineering discipline: test-first, root-cause before fix, minimal change, measure-before-optimize, review/second look, evidence over guess. Use when implementing features, debugging, planning, or establishing development practices. Aligns with TDD, systematic debugging, and RCA practices (current).