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-councilgit 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-council)<a href="https://agentmods.dev/skills/reinamaccredy/maestro/maestro-council"><img src="https://agentmods.dev/badge/skills/reinamaccredy/maestro/maestro-council/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-council"><img src="https://agentmods.dev/badge/skills/reinamaccredy/maestro/maestro-council.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 | $0.00065 | $0.02575 |
| Opus 5 | $0.00032 | $0.01288 |
| Sonnet 5 | $0.00013 | $0.00515 |
| Haiku 4.5 | $0.00006 | $0.00258 |
Grade A, and why
maestro-council 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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
maestro-council
Use when maestro-design intake scores yes on every ROI question including
hard to reverse. The Lead is the final arbiter: it frames, seals, collects,
verifies, drafts, and decides. It never performs a seat's analysis itself and
never spawns another Lead. Council ends at a decision and a handoff contract;
seats never implement.
Lead-only guard
Proceed only as the Lead of a running team, or in a plain session outside a team. A Peer, Verifier, Auditor, or any other seat refuses in one line and returns to its own assignment. A seat never opens a council. No Observer seat exists (Hub d98); a council has exactly the seats its tier names.
The owner chooses the Lead's model and effort; do not second-guess it. Seat routing lives in the five seat profiles of bundle slp-profiles (independent, challenger, specialist, verifier, auditor); this skill carries no routing table.
Protocol at a glance
tier -> the smallest sufficient tier, in one sentence
brief -> neutral brief + case output contract + framing lint
sealed -> one bound work item per round 1 seat, read nothing until all return
collect -> seat audit, failure policy
model -> typed claims with statuses
verify -> premise verifier on unanimity, bounded verifiers on dispute
cross -> one challenge and one response per disputed unit
draft -> the Lead drafts alone
audit -> auditor by tier
verdict -> decision draft with dissent, handoff note on the work item
Re-anchor on this list when unsure which step is active. Announce each phase in one line.
Tier
lens: one Independent.debate(default): Independent + Challenger.debate-with-proof: Independent + Challenger, Verifiers as needed, audit by default.high-risk: Independent + Challenger at the high-risk profile, optionally one Specialist, Verifiers as needed, audit mandatory.
Pick the tier in one sentence. The design ROI score decides only whether a council happens; it never picks the tier.
What ships with it
2 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 First seen · 255 lines · 65 tokens per session scan A 573f7a9aa064
maestro-council is a skill published in the GitHub repository ReinaMacCredy/maestro (232 stars, last pushed 6d ago), licensed MIT. It adds 65 tokens to every session and 2,575 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 2026-09-06.
Other skills, from other repositories
trigger-authoring-tasks
Covers writing backend Trigger.dev tasks with @trigger.dev/sdk: defining task() and schemaTask(), the run function and its ctx, retries, waits, queues and concurrency, idempotency keys, run metadata, logging, triggering other tasks (and the Result shape), scheduled/cron tasks, and the essentials of trigger.config.ts.…
background
Use when the user wants to see, inspect, cancel, or prune background agents fired during prior chain runs. Read/manage .hyperflow/background/registry.json and the per-agent output buffers at .hyperflow/background/ .md. Standalone — never auto-invoked. Trigger with /hyperflow:background, "list background agents"…
atmos-auth
Authentication and identity management: providers (SSO/SAML/OIDC/GCP/Atmos Pro), identities, keyring, identity chaining, login/exec/shell/console, and github/sts for private GitHub access.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
atmos-cache
Atmos caching: CI cache configuration and commands, GitHub Actions cache integration, Terraform registry cache mirror/list/prune/stats/trust, and cache modernization guidance.