Dispatching Parallel Agents

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Security Scan

The skill is an instruction-only pattern for dispatching independent agents to work in parallel; its requirements and instructions are consistent with that purpose and do not request unrelated privileges or installs.

Purpose & Capability

The name/description (dispatch parallel agents for independent tasks) matches the SKILL.md instructions (how to identify independent domains, craft focused prompts, dispatch agents, review results). There are no unrelated environment variables, binaries, or installs requested. One implicit dependency is that the agent using this pattern will need access to the codebase/tests and a test runner to follow the examples — that assumption is reasonable for the stated purpose but is not explicitly declared.

Instruction Scope

Instructions remain within the stated purpose: create self-contained prompts, run separate agents, and review their outputs. The examples explicitly ask agents to read test files, run/modify tests, and make fixes — which is appropriate for debugging workflows but implies filesystem and repository access and the ability to edit code. This is expected but worth noting: the skill does not provide guardrails around concurrent edits or repository permissions, so callers must ensure agents have only the intended access and that changes are reviewed.

Install Mechanism

Instruction-only skill with no install spec, no code files, and no downloads — minimal surface area and no install-time risk.

Credentials

The skill requests no environment variables or credentials. That is proportionate for an instruction template. The SKILL.md does assume the operational environment will allow reading and editing tests and running the test suite; if those capabilities require credentials or tools in your environment, grant them deliberately.

Persistence & Privilege

always:false and default autonomous invocation are set (normal). The skill does not request persistent presence or claim to modify other skills or system-wide settings. However, because it encourages dispatching agents that may make commits/edits, consider reviewing change approvals and CI policies before allowing autonomous write actions.

Assessment

This is a coherent, low-risk instruction template for running independent agents in parallel. Before using it, ensure you intentionally grant the agent(s) access to the repository/test runner (read/write) only if you want them to modify code. Add guardrails: require human approval for commits or merges, run CI/full test suite after agent changes, and use locks or a coordinator to avoid conflicting concurrent edits. If you don't want agents to make changes autonomously, disable autonomous model actions or require explicit confirmation for any write operations.

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

// In Claude Code / AI environment
Task("Fix agent-tool-abort.test.ts failures")
Task("Fix batch-completion-behavior.test.ts failures")
Task("Fix tool-approval-race-conditions.test.ts failures")
// All three run concurrently

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

Time saved: 3 problems solved in parallel vs sequentially

Key Benefits

1. Parallelization - Multiple investigations happen simultaneously
2. Focus - Each agent has narrow scope, less context to track
3. Independence - Agents don't interfere with each other
4. Speed - 3 problems solved in time of 1

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

Real-World Impact

From debugging session (2025-10-03):

• 6 failures across 3 files
• 3 agents dispatched in parallel
• All investigations completed concurrently
• All fixes integrated successfully
• Zero conflicts between agent changes