dispatching-parallel-agents

A guide for assigning two or more independent tasks to separate coding agents. The tasks must not depend on the same changing state or on one another's results.

In plain words
What is it for?
Use it to split separate test failures, bugs, or subsystem investigations into focused parallel assignments, then coordinate their results.
Why use it?
It reduces waiting when unrelated bugs or work items can be investigated at the same time.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/obra/superpowers/dispatching-parallel-agents
Any agent
npx skills add obra/superpowers --skill dispatching-parallel-agents
Clone the repo
git clone --depth 1 https://github.com/obra/superpowers

Made for: Claude Code, Codex.

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,363 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00026 $0.01363
Opus 5 $0.00013 $0.00681
Sonnet 5 $0.00005 $0.00273
Haiku 4.5 $0.00003 $0.00136

Measured 2d ago against content hash 1968923066f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

Origin

Copies of this mod

8 near-identical copies found in the catalogue:

skills/dispatching-parallel-agents/SKILL.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dispatching Parallel Agents

Overview

You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for coordination work.

When you have multiple unrelated failures (different test files, different subsystems, different bugs), investigating them sequentially wastes time. Each investigation is independent and can happen in parallel.

Core principle: Dispatch one agent per independent problem domain. Let them work concurrently.

When to Use

digraph when_to_use {
    "Multiple failures?" [shape=diamond];
    "Are they independent?" [shape=diamond];
    "Single agent investigates all" [shape=box];
    "One agent per problem domain" [shape=box];
    "Can they work in parallel?" [shape=diamond];
    "Sequential agents" [shape=box];
    "Parallel dispatch" [shape=box];

    "Multiple failures?" -> "Are they independent?" [label="yes"];
    "Are they independent?" -> "Single agent investigates all" [label="no - related"];
    "Are they independent?" -> "Can they work in parallel?" [label="yes"];
    "Can they work in parallel?" -> "Parallel dispatch" [label="yes"];
    "Can they work in parallel?" -> "Sequential agents" [label="no - shared state"];
}

Use when:

  • 3+ test files failing with different root causes
  • Multiple subsystems broken independently
  • Each problem can be understood without context from others
  • No shared state between investigations

Don't use when:

  • Failures are related (fix one might fix others)
  • Need to understand full system state
  • Agents would interfere with each other

The Pattern

1. Identify Independent Domains

Group failures by what's broken:

  • File A tests: Tool approval flow
  • File B tests: Batch completion behavior
  • File C tests: Abort functionality

Each domain is independent - fixing tool approval doesn't affect abort tests.

Read the full file on GitHub · 168 lines

Changes

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.

  1. 2d ago First seen · 168 lines · 26 tokens per session scan A 1968923066f3

Subscribe to this mod's changes

dispatching-parallel-agents is a skill published in the GitHub repository obra/superpowers (280,216 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 1,363 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.

Related

Other skills, from other repositories

skill-creator

Create, improve, evaluate, benchmark skills. Use when authoring a new skill, updating an existing one, running evals, or optimizing a skill's description for triggering. Don't use for invoking skills, writing prose, or scaffolding Python projects.

luongnv89/asm · 54 tokens

find-me-skills

Find Agent Skills for a goal the user cannot name yet, then export an installable bundle. Use when they ask which skills fit a project. Don't use for installing named skills, authoring skills, or catalog maintenance.

luongnv89/asm · 49 tokens

skill-auto-improver

Improve an external, legacy, or drifted SKILL.md to the skill-creator standard — hard validation gates plus an advisory predictability audit. Don't use for authoring from scratch (skill-creator output is already standard), bulk eval, or prose edits.

luongnv89/asm · 58 tokens

skill-index-updater

Add GitHub skill repos to the ASM index: clone, audit, eval, regenerate index, rebuild catalog, open PR. Use when given GitHub URLs to onboard. Don't use for authoring (skill-creator), improving (skill-auto-improver), or install (asm install).

luongnv89/asm · 63 tokens

refresh-index

Re-ingest every already-enabled repo in data/skill-index-resources.json: sync the working tree, run preindex, rebuild the catalog for verification, summarize updated/unchanged/failed/skipped, then gate commit + PR behind explicit confirmation. Use when asked to refresh the index, re-ingest indexed repos, or…

luongnv89/asm · 119 tokens

skill-install-improved

Install an improved variant of one named skill: resolve it by local path, repo, or name, run skill-auto-improver on a throwaway copy, then install the improved result. Don't use for improving in place, upstream PRs, or plain asm install.

luongnv89/asm · 59 tokens