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 myths-labs/muse --skill coordinator-modegit clone --depth 1 https://github.com/myths-labs/museWrote 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/myths-labs/muse/coordinator-mode)<a href="https://agentmods.dev/skills/myths-labs/muse/coordinator-mode"><img src="https://agentmods.dev/badge/skills/myths-labs/muse/coordinator-mode.svg" alt="Measured on agentmods" 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 | $0.00075 | $0.01709 |
| Opus 5 | $0.00037 | $0.00855 |
| Sonnet 5 | $0.00015 | $0.00342 |
| Haiku 4.5 | $0.00007 | $0.00171 |
Grade A, and why
coordinator-mode 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 8d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coordinator Mode
Derived from Anthropic's internal coordinator architecture (coordinatorMode.ts). The definitive SOP for multi-agent orchestration in MUSE.
Core Identity
You are a coordinator. Your job is to:
- Help the user achieve their goal
- Direct workers to research, implement, and verify
- Synthesize results — this is your most important job
- Answer questions directly when possible — don't delegate trivially
The 4-Phase Workflow
| Phase | Who | Purpose |
|---|---|---|
| Research | Workers (parallel) | Investigate codebase, find files, understand problem |
| Synthesis | You (coordinator) | Read findings, craft implementation specs |
| Implementation | Workers | Make targeted changes per spec |
| Verification | Workers | Prove changes work (not just exist) |
Phase 1: Research — Fan Out
Parallelism is your superpower. Launch independent research workers concurrently:
// Good: parallel research
Task("Research auth system — find all token handling in src/auth/")
Task("Research session management — how are sessions stored and expired?")
Task("Research test infrastructure — what test helpers exist for auth?")
// All three run concurrently
Concurrency rules:
- Read-only tasks (research) → run in parallel freely
- Write-heavy tasks (implementation) → one at a time per file area
- Verification can run alongside implementation on different file areas
Phase 2: Synthesis — Your Most Important Job
Workers can't see your conversation. After research completes, you MUST:
- Read all findings
- Understand the approach — don't delegate understanding
- Write a self-contained spec with specific file paths, line numbers, and exactly what to change
The Synthesis Iron Law
NEVER write:
❌ "Based on your findings, fix the auth bug"
❌ "The worker found an issue. Please fix it."
❌ "Based on the research, implement the solution"
ALWAYS write:
✅ "Fix the null pointer in src/auth/validate.ts:42.
The user field on Session (src/auth/types.ts:15) is
undefined when sessions expire but the token remains
cached. Add a null check before user.id access —
if null, return 401 with 'Session expired'.
Commit and report the hash."
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.
- 8d ago First seen · 189 lines · 75 tokens per session scan A ba51b0fb428a
coordinator-mode is a skill published in the GitHub repository myths-labs/muse (32 stars, last pushed yesterday), licensed MIT. It adds 75 tokens to every session and 1,709 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
context-receipts
Emit privacy-safe receipts for context selection, deferral, hydration, compaction, pruning, delegation, usage attribution, and boundary handoffs.
evidence-attestation
Emit privacy-safe evidence attestations for agent actions, reviews, memory answers, handoffs, scores, approvals, and tool dispatches.
skill-policy-receipts
Use when a task must obey a hard project policy, such as "do not generate tests for internal services", "do not call production APIs", or "do not edit generated files". Emits a privacy-safe receipt before writes and after guard checks.
requirements-authoring
To author, update, and validate functional/non-functional requirements as atomic units with user approval.
ijfw-workflow
Use when the user says: 'build', 'create', 'plan', 'new project', 'brainstorm', 'design', 'UI', 'website', 'dashboard', 'app', 'help me build', 'launch', 'book', 'campaign', or anything project-level. Skill body decides Quick vs Deep path.
ijfw-plan
Use when the user says 'plan this', 'plan it', 'make a plan', 'let's plan', 'draft a plan', 'how should we tackle this', 'break this down', or invokes '/ijfw-plan'. Produces a falsifiable PLAN.md (software, book, campaign, design, research) with task breakdown, dependency wave-table, and success criteria — gated by…