Dispatching parallel agents

Splits independent problems between parallel subagents, each with one domain and a self-contained brief with scope, constraints and the report expected back, then checks their edits for conflicts and runs the full suite. Use when several unrelated things fail at once.

CodingPack: Superpowers167 linesdispatching-parallel-agents
Author
Source
obra/superpowers/skills/dispatching-parallel-agents @ 22f0b46
License
MIT · Copyright (c) 2025 Jesse Vincent

About this skill

What it does

The skill teaches the agent to split unrelated problems between concurrent subagents, once it has checked that the failures are independent and share no state. Each domain — one test file or one subsystem — gets its own subagent and a self-contained brief: a narrow scope, a goal, constraints such as "do not change production code" and the report expected back. All briefs go out in one response, which is what makes them run concurrently. Subagents never see the main session; the agent builds their context from scratch and keeps its own free for coordination. Afterwards it reads each summary, checks that no two subagents edited the same code, runs the full suite and spot-checks the fixes.

The folder holds only SKILL.md and the licence; it includes a sample brief and a worked case with six failures in three files.

When to use it, and when not

Use it for two or more independent tasks — typically several test files failing for different reasons after a refactor, or separate subsystems broken at once — where each can be understood on its own.

Skip it when the failures may share a cause, when you do not yet know what is broken, when the bug only makes sense with the whole system in view, or when subagents would edit the same files or share resources. It also needs an agent that can launch subagents.

How to run it

The install command below puts the folder in place. The agent picks the skill up by its description; to call it yourself:

  • Claude Code: /dispatching-parallel-agents, or ask for the skill by name.
  • Codex: $dispatching-parallel-agents.
  • Cursor: type / in the Agent chat and pick dispatching-parallel-agents.

Example: /dispatching-parallel-agents After the upgrade, the CSV export tests, the auth middleware tests and the email template snapshots all fail. Give each area its own agent, then show me one combined summary.

The skill does not hand off to other Superpowers skills.

How it differs from similar skills

subagent-driven-development also uses fresh subagents, but it follows a written plan one task at a time, reviews each task and forbids parallel implementation subagents because they conflict. This skill has no plan and no review stage: independent investigations run side by side, and the main agent merges the results. systematic-debugging covers how one investigation should go; this skill decides how to split several. Implement a spec also runs subagents in parallel, but as implementers of tracker tickets, each in its own worktree, following the blocking graph. None of our own skills delegates to subagents; Small steps builder is the opposite case — one change at a time in one context, for dependent steps.

Install

Run one command — it saves SKILL.md and the files it uses into your agent's skills folder. Claude Code and Codex pick up a new skill without a restart; if it does not show up, restart the agent.

Claude Code — macOS, Linux
curl -fsSL --create-dirs -o ~/.claude/skills/dispatching-parallel-agents/SKILL.md https://anymodel.org/en/skills/superpowers/dispatching-parallel-agents/SKILL.md -o ~/.claude/skills/dispatching-parallel-agents/LICENSE https://anymodel.org/en/skills/superpowers/dispatching-parallel-agents/LICENSE
Codex, Cursor — macOS, Linux
curl -fsSL --create-dirs -o ~/.agents/skills/dispatching-parallel-agents/SKILL.md https://anymodel.org/en/skills/superpowers/dispatching-parallel-agents/SKILL.md -o ~/.agents/skills/dispatching-parallel-agents/LICENSE https://anymodel.org/en/skills/superpowers/dispatching-parallel-agents/LICENSE
Claude Code — Windows PowerShell
foreach ($f in 'SKILL.md','LICENSE') { $p = Join-Path "$HOME\.claude\skills\dispatching-parallel-agents" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/superpowers/dispatching-parallel-agents/$f" -UseBasicParsing -OutFile $p }
Codex, Cursor — Windows PowerShell
foreach ($f in 'SKILL.md','LICENSE') { $p = Join-Path "$HOME\.agents\skills\dispatching-parallel-agents" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/superpowers/dispatching-parallel-agents/$f" -UseBasicParsing -OutFile $p }

Any other agent: save the file into its skills folder, or give it the link to the file: https://anymodel.org/en/skills/superpowers/dispatching-parallel-agents/SKILL.md

SKILL.md

Raw

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.

2. Create Focused Agent Tasks

Each agent gets:

  • Specific scope: One test file or subsystem
  • Clear goal: Make these tests pass
  • Constraints: Don't change other code
  • Expected output: Summary of what you found and fixed

3. Dispatch in Parallel

Issue all three subagent dispatches in the same response — they run in parallel:

Subagent (general-purpose): "Fix agent-tool-abort.test.ts failures"
Subagent (general-purpose): "Fix batch-completion-behavior.test.ts failures"
Subagent (general-purpose): "Fix tool-approval-race-conditions.test.ts failures"
# All three run concurrently.

Multiple dispatch calls in one response = parallel execution. One per response = sequential.

4. Review and Integrate

When agents return:

  • Read each summary
  • Verify fixes don't conflict
  • Run full test suite
  • Integrate all changes

Agent Prompt Structure

Good agent prompts are:

  1. Focused - One clear problem domain
  2. Self-contained - All context needed to understand the problem
  3. Specific about output - What should the agent return?
Fix the 3 failing tests in src/agents/agent-tool-abort.test.ts:

1. "should abort tool with partial output capture" - expects 'interrupted at' in message
2. "should handle mixed completed and aborted tools" - fast tool aborted instead of completed
3. "should properly track pendingToolCount" - expects 3 results but gets 0

These are timing/race condition issues. Your task:

1. Read the test file and understand what each test verifies
2. Identify root cause - timing issues or actual bugs?
3. Fix by:
   - Replacing arbitrary timeouts with event-based waiting
   - Fixing bugs in abort implementation if found
   - Adjusting test expectations if testing changed behavior

Do NOT just increase timeouts - find the real issue.

Return: Summary of what you found and what you fixed.

Common Mistakes

❌ Too broad: "Fix all the tests" - agent gets lost ✅ Specific: "Fix agent-tool-abort.test.ts" - focused scope

❌ No context: "Fix the race condition" - agent doesn't know where ✅ Context: Paste the error messages and test names

❌ No constraints: Agent might refactor everything ✅ Constraints: "Do NOT change production code" or "Fix tests only"

❌ Vague output: "Fix it" - you don't know what changed ✅ Specific: "Return summary of root cause and changes"

When NOT to Use

Related failures: Fixing one might fix others - investigate together first Need full context: Understanding requires seeing entire system Exploratory debugging: You don't know what's broken yet Shared state: Agents would interfere (editing same files, using same resources)

Real Example from Session

Scenario: 6 test failures across 3 files after major refactoring

Failures:

  • agent-tool-abort.test.ts: 3 failures (timing issues)
  • batch-completion-behavior.test.ts: 2 failures (tools not executing)
  • tool-approval-race-conditions.test.ts: 1 failure (execution count = 0)

Decision: Independent domains - abort logic separate from batch completion separate from race conditions

Dispatch:

Agent 1 → Fix agent-tool-abort.test.ts
Agent 2 → Fix batch-completion-behavior.test.ts
Agent 3 → Fix tool-approval-race-conditions.test.ts

Results:

  • Agent 1: Replaced timeouts with event-based waiting
  • Agent 2: Fixed event structure bug (threadId in wrong place)
  • Agent 3: Added wait for async tool execution to complete

Integration: All fixes independent, no conflicts, full suite green

Verification

After agents return:

  1. Review each summary - Understand what changed
  2. Check for conflicts - Did agents edit same code?
  3. Run full suite - Verify all fixes work together
  4. Spot check - Agents can make systematic errors

Connect through AnyModel API

This skill runs on whatever model your agent uses. Point Claude Code, Codex or Cursor at AnyModel to run it on Claude, GPT, Gemini and more with one key — pay per token, no subscription.

More from the pack Superpowers

Brainstorming before you build

Finds out what you want to build and why: one question at a time, its understanding played back part by part, two or three approaches to pick from and a design doc, with no code until you approve it. Use for a new feature or change when the request leaves the essentials open.

Executing plans

Runs a plan from writing-plans in the current session with no subagent per task: tasks in order through TDD, a ledger of progress and rulings that survives context compaction, and one fresh review of the whole branch at the end. Use when per-task review is not needed or there are no subagents.

Finishing a development branch

Finishes a branch: runs the tests, offers to merge locally, open a pull request or keep it as is, reruns the tests after a merge and removes its own worktree, and discards work only after you type "discard". Use when the implementation is done.

Receiving code review

Checks each review comment against the code before changing anything, clears up every unclear item first, pushes back with technical reasons and never performs agreement. Use when working through review feedback without blind fixes.

Requesting code review

Hands finished work to a fresh reviewer subagent through a template: the commit range, the plan or requirements, findings by severity and a verdict on merging. Use when a task or feature is done and a merge to main is next.

Subagent-driven development

Executes a plan through subagents: a fresh implementer and reviewer for every task, checking spec compliance and code quality, up to five fix rounds and a final review of the whole branch. Use for a plan of independent tasks when each one needs a review.

Systematic debugging

Keeps the agent from guessing at fixes: reproduce the bug and find the root cause first, test one hypothesis at a time, fix with a failing test, and question the design after three failed fixes. Use for any bug, test failure or unexpected behavior.

Test-driven development, Superpowers style

Drives work test-first: a test seen failing, then the least code that passes and a run of the whole suite; code written before its test is deleted. Use for features and bug fixes when the agent tends to add tests after the code.

Using git worktrees

Moves feature work into an isolated git worktree: checks whether the agent is already isolated, prefers the harness's own worktree tool, keeps the folder git-ignored, installs dependencies and runs a baseline test. Use when the work must not land on the branch you have open.

Verification before completion

Stops the agent from saying "done" or "tests pass" until it has rerun the check and read the whole output. Use whenever the agent reports success, commits or opens a pull request.

Writing implementation plans

Turns a spec into a plan for an implementer new to the codebase: files, signatures, interfaces between tasks, tests with exact values and TDD steps with each command's expected output. Use for a multi-step task when the spec is ready and no code exists yet.

Writing skills

Writes and edits skills the TDD way: a subagent first does the task without the skill and its mistakes are written down, then the smallest text that answers them goes in and the loopholes get closed. Use for a skill that other agents will load.