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-designgit 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-design)<a href="https://agentmods.dev/skills/reinamaccredy/maestro/maestro-design"><img src="https://agentmods.dev/badge/skills/reinamaccredy/maestro/maestro-design/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-design"><img src="https://agentmods.dev/badge/skills/reinamaccredy/maestro/maestro-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 30 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.
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 | $0.00062 | $0.01460 |
| Opus 5 | $0.00031 | $0.00730 |
| Sonnet 5 | $0.00012 | $0.00292 |
| Haiku 4.5 | $0.00006 | $0.00146 |
Grade A, and why
maestro-design 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 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.
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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
maestro-design
Use when the request, acceptance, authority, or implementation boundary is unsettled. Design is human-guided whenever a choice changes what will be built. Do not begin implementation until the relevant decisions are locked and the user has approved the resulting scope. Design is read-only toward production code and authorizes nothing.
Mode per unknown
Identify what kind of unknown blocks progress, then load only the reference that resolves it:
| The unknown | Mode | Reference |
|---|---|---|
| Decisions only the user can make, several and interdependent | grill | references/grilling.md |
| A decision owned by someone not in the conversation | route to maestro-questionnaire |
|
| A fact in docs, APIs, or source outside this repo | research | maestro-explore (research mode) |
| "Does this state model feel right?" or "What should it look like?" | prototype | maestro-explore (prototype mode) |
| Fuzzy terminology, or a hard-to-reverse choice worth recording | model | references/domain-modeling.md |
| The effort exceeds one session and is wrapped in fog, or the user does not know what to do next | wayfind | references/wayfinder.md |
Facts are yours to find; decisions are the user's. Never ask the user for anything you could look up. Modes compose: grill runs with the glossary in hand; wayfind dispatches grill, research, and prototype per child work item. Each design pass must close at least one fork; a pass that closes none surfaces the blocker to the user instead of looping.
Intake
Pin the problem before choosing a method:
For [who], reach [observable outcome] within [boundary], because [impact], without [excluded effect].
Route uncertainty to a lane:
| Current uncertainty | Lane |
|---|---|
| state unknown | scout, no-write |
| several architectures | two or three decision lanes |
| contract clear | delivery |
| candidate needs breaking | challenge |
| hard-to-reverse fork | council |
What ships with it
4 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.
- 5d ago Changed · -4 lines d2179acba634
- 6d ago Changed · +44 lines · +29 tokens per session c5e2ff87ad8f
- 11d ago First seen · 95 lines · 33 tokens per session scan A 725fbcc01176
maestro-design is a skill published in the GitHub repository ReinaMacCredy/maestro (232 stars, last pushed 5d ago), licensed MIT. It adds 62 tokens to every session and 1,460 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
qveris
Discover and call third-party API capabilities through QVeris, using inspect or probe only when their checks are needed, then generate production REST code. Use when task fit, data quality/freshness, provider comparison, fallback, or the user request favors QVeris.
deepseek-harness
Use when building AI agent applications with a plugin-based architecture — Web UI, CLI, Python SDK, Cordis plugin system, multi-model orchestration. DeepSeek Harness (dsh): open-source agent harness by DeepSeek AI where everything is a plugin, powered by Cordis for spatiotemporal composability.
ui5-typescript-conversion
A skill for converting UI5 (SAPUI5/OpenUI5) projects to TypeScript.
skill-creator
Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating…
sub-agent-creator
Create, edit, convert, or audit ChatLuna sub-agent markdown files. Use when adding a new sub-agent, refining a sub-agent prompt, choosing a sub-agent's goal and output contract, restricting tools, skills, MCP, or computer permissions, pinning or omitting a model, setting maxTurns, placing agents under local…
agentcli
Use this skill to inspect or change ChatLuna agent admin state — skills, sub-agents, tools, MCP servers, MCP tools, or permission rules. The skill edits a working copy of the agent config inside the sandbox; the user must run chatluna.agent.sync to write changes back to the host instance.