From superpowers
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
npx claudepluginhub ironbob/superpower_light --plugin superpowersThis skill uses the workspace's default tool permissions.
> **Environment note:** Concurrency is limited to 1. Agents run one at a time (sequentially). The value of this skill is **isolated context per problem domain**, not speed.
Verifies tests pass on completed feature branch, presents options to merge locally, create GitHub PR, keep as-is or discard; executes choice and cleans up worktree.
Guides root cause investigation for bugs, test failures, unexpected behavior, performance issues, and build failures before proposing fixes.
Writes implementation plans from specs for multi-step tasks, mapping files and breaking into TDD bite-sized steps before coding.
Environment note: Concurrency is limited to 1. Agents run one at a time (sequentially). The value of this skill is isolated context per problem domain, not speed.
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), mixing them in one agent causes context confusion. Each investigation is independent and benefits from a fresh, focused agent.
Core principle: One agent per independent problem domain, dispatched one at a time. Isolated context → fewer mistakes.
digraph when_to_use {
"Multiple failures?" [shape=diamond];
"Are they independent?" [shape=diamond];
"Single agent investigates all" [shape=box];
"Dispatch agents one at a time" [shape=box];
"Multiple failures?" -> "Are they independent?" [label="yes"];
"Are they independent?" -> "Single agent investigates all" [label="no - related"];
"Are they independent?" -> "Dispatch agents one at a time" [label="yes"];
}
Use when:
Don't use when:
Group failures by what's broken:
Each domain is independent - fixing tool approval doesn't affect abort tests.
Each agent gets:
Dispatch one agent, wait for result, then dispatch the next:
// concurrency=1: one at a time
[Agent 1] Fix agent-tool-abort.test.ts failures → wait → review result
[Agent 2] Fix batch-completion-behavior.test.ts failures → wait → review result
[Agent 3] Fix tool-approval-race-conditions.test.ts failures → wait → review result
Do NOT dispatch multiple agents at once — only one can run.
When agents return:
Good agent prompts are:
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.
❌ 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"
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)
Scenario: 6 test failures across 3 files after major refactoring
Failures:
Decision: Independent domains - abort logic separate from batch completion separate from race conditions
Dispatch (one at a time):
Agent 1 → Fix agent-tool-abort.test.ts → review
Agent 2 → Fix batch-completion-behavior.test.ts → review
Agent 3 → Fix tool-approval-race-conditions.test.ts → review
Results:
Integration: All fixes independent, no conflicts, full suite green
After agents return:
From debugging session (2025-10-03):