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 agentmods add skills/myths-labs/muse/dispatching-parallel-agentsnpx skills add myths-labs/muse --skill dispatching-parallel-agentsgit 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/dispatching-parallel-agents)<a href="https://agentmods.dev/skills/myths-labs/muse/dispatching-parallel-agents"><img src="https://agentmods.dev/badge/skills/myths-labs/muse/dispatching-parallel-agents.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00017 | $0.01484 |
| Opus 5 | $0.00009 | $0.00742 |
| Sonnet 5 | $0.00003 | $0.00297 |
| Haiku 4.5 | $0.00002 | $0.00148 |
Grade A, and why
dispatching-parallel-agents 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dispatching Parallel Agents
Overview
Pattern for dispatching multiple subagents to work on independent tasks simultaneously.
Core principle: Parallel execution of strictly independent implementation or investigation domains.
v3.0: Enhanced with Anthropic coordinator patterns — synthesis iron law, continue/spawn matrix, concurrency management.
The Pattern
1. Identify Independent Domains
Group tasks by what's independent:
- File A tests: Tool approval flow
- File B tests: Batch completion behavior
- File C tests: Abort functionality
Each domain is independent — fixing one doesn't affect the others.
2. Create Self-Contained Agent Tasks
Iron Law: Workers can't see your conversation. Every prompt must be self-contained with everything the worker needs.
Each agent gets:
- Specific scope: One test file or subsystem
- Full context: File paths, line numbers, error messages — not "based on earlier findings"
- Clear goal: Make these tests pass
- Purpose statement: Why this matters (helps worker calibrate depth)
- Constraints: Don't change other code
- Expected output: Summary of what you found and fixed
3. Dispatch with Concurrency Rules
// Read-only tasks (research) → parallel freely
Task("Research auth system — find token handling in src/auth/")
Task("Research session management — how are sessions stored?")
Task("Research test helpers for auth")
// Write tasks → one at a time per file area
Task("Fix auth validation in src/auth/validate.ts")
// Wait for completion before dispatching overlapping writes
Task("Fix session expiry in src/auth/session.ts")
Concurrency management:
| Task Type | Rule |
|---|---|
| Read-only (research) | Run in parallel freely |
| Write-heavy (implementation) | One at a time per set of files |
| Verification | Can run alongside implementation on different file areas |
4. Synthesize and Integrate
When agents return:
- Read each summary — Understand what changed (this is YOUR job, don't delegate)
- Synthesize findings — Write specific specs if follow-up work needed
- Check for conflicts — Did agents edit same code?
- Run full suite — Verify all fixes work together
- Decide continue vs spawn for next phase
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 First seen · 170 lines · 17 tokens per session scan A ca00fdde6908
dispatching-parallel-agents is a skill published in the GitHub repository myths-labs/muse (32 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 1,484 once invoked, about $0.0001 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
project-brain
Triggers (all require explicit user request — do NOT activate just because a brain/ folder exists): (1) The user wants to set up project-level memory ("set up project brain", "scaffold project context", "init project brain", "建项目脑"). (2) The user is in a directory containing brain/ AND explicitly asks to resume /…
mex-inbox
Prepare and manage governed MEX Inbox proposals for durable Spec-family knowledge. Use when the user clearly asks to capture, create, save, or draft a MEX product Spec, requirement, constraint, acceptance criterion, or durable product-spec decision for team review, or explicitly invokes /mex-inbox or $mex-inbox. Do…
mex-relay
Prepare and manage durable MEX team handoffs. Use when the user asks to hand work to a person or team, prepare an end-of-session handoff, save what the next engineer needs, create a MEX Relay, take or close a Relay, or explicitly invokes /mex-relay or $mex-relay. Treat Relay as a memory and context baton, not chat…
context-receipts
Emit privacy-safe receipts for context selection, deferral, hydration, compaction, pruning, delegation, usage attribution, and boundary handoffs.
engram
Local-first personal AI identity and memory layer for MCP-compatible coding tools (Claude Code, Codex, Cursor, and others). Use this skill when the user wants to continue from a previous session ("continue from last session", "pick up where we left off"), recall a past decision ("what did we decide", "what was our…
evidence-attestation
Emit privacy-safe evidence attestations for agent actions, reviews, memory answers, handoffs, scores, approvals, and tool dispatches.