dispatching-parallel-agents
/dispatching-parallel-agents
Dzieli co najmniej dwa niezależne zadania, które nie mają wspólnego stanu ani zależności kolejnościowych, na równolegle pracujących subagentów.
- Autor
- cloudfieldcz ↗
- Repozytorium
- cf-powers ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 15.10.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 1
- Skrypty
- 0
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 15.10.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
Co robi i kiedy
Dzieli co najmniej dwa niezależne zadania, które nie mają wspólnego stanu ani zależności kolejnościowych, na równolegle pracujących subagentów.
Oryginalny opis (EN)
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Jak działa
- Overview
- When to Use
- Model Selection
- The Pattern
- Agent Prompt Structure
- Common Mistakes
- When NOT to Use
- Real Example from Session
- Verification
Podgląd SKILL.md
---
name: dispatching-parallel-agents
description: Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
---
# Dispatching Parallel Agents
**Runtime:** Follow project instructions. Use native skill loading and ordinary
project reads directly. Before dispatch, resume, model selection, or shared plugin
resource resolution, read [runtime operations](../using-superpowers/references/runtime.md)
and the active-host reference once per context. Keep workflow decisions and child runtime constraints unchanged.
## 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
```dot
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
## Model Selection
**REQUIRED SUB-SKILL:** cf-powers:choosing-subagent-models. Set `model`
explicitly on every dispatch — parallel dispatch multiplies the cost of
defaulting to the session's model, since you pay it N times at once.
The usual split here: mechanical sweeps across a file list on the mechanical tier, focused
single-domain fixes with a clear symptom on the implementation tier, unknown
root causes and every reviewer on the judgment tier.
## 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
```typescript
// 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?
```markdown
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
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · cloudfieldcz/cf-powers | 100 | MIT |
| jjuraszek/pi-gauntlet | 100 | MIT |
| osmontero/opencode-skills | 100 | MIT |
| coco-research/coco | 100 | MIT |
| FrancoStino/opencode-skills-collection | 100 | MIT |
| seaworld008/commonly-used-high-value-skills | 100 | MIT |
| rootcastleco/rei-skills | 100 | MIT |
| nikospavlopoulos/devops-mutant-powers | 100 | MIT |
| Richicinschi/studio-os | 100 | MIT |
Migawka bazy z 13.11.2026 · wersja paczki 9d7d58a7655d (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 100parallel
Prowadzi pracę nad co najmniej dwoma niezależnymi zadaniami, które nie mają wspólnego stanu ani zależności sekwencyjnych, uruchamiając je równolegle. - 100sr-dispatching-parallel-agents
Dzieli dwa lub więcej niezależnych zadań między równoległych agentów, gdy nie dzielą stanu i nie zależą od siebie.