agent-coordination

AI Community

Repo stars 54,444
Author repo ruflo

Interpretation is structured for decision-making; original keeps the upstream SKILL.md unchanged.

Decide Fit First

Core job: > Spawn and coordinate agents for complex multi-agent tasks. npx claude-flow agent spawn --type coder --name my-coder npx claude…
Best fit: Use it when the task has reusable inputs, steps, and validation criteria rather than a one-off answer.
Avoid forcing it: If the source lacks commands, platform support, or external-service evidence, keep those fields unknown instead of guessing.

Design Intent

Structure: The skill is organized around “Purpose”, “Agent Types”, “Core Development”, “V3 Specialized”, showing how the author expects the agent to judge fit, collect context, and produce verifiable output.
Trigger evidence: Prioritize the author’s wording around when to use it, what context to collect, and what output shape to produce.
Evidence boundary: Author text states facts, repository files prove commands and paths, and Fluxly only adds fit, limits, and usage judgment.

How To Use It

Inputs: Provide target material, scope, expected result, forbidden changes, and validation method.
Invocation: Name agent-coordination directly; if the source includes slash commands, start with the command and then add task context.
Validation: Start small and check whether the result follows “Purpose / Agent Types / Core Development” before expanding.

Boundaries And Review

Dependencies: It usually needs no extra API key, so start with a small validation task.
Permissions: Declared permissions include read / write / shell-exec; ask the agent to state file, command, and rollback boundaries before acting.
Quality bar: A useful result names the deliverable, evidence, and next action. Generic prose means the task needs tighter context.

Agent Coordination Skill

Purpose

Spawn and coordinate agents for complex multi-agent tasks.

Agent Types

Core Development

coder, reviewer, tester, planner, researcher

V3 Specialized

security-architect, security-auditor, memory-specialist, performance-engineer

Swarm Coordination

hierarchical-coordinator, mesh-coordinator, adaptive-coordinator, collective-intelligence-coordinator

Consensus

byzantine-coordinator, raft-manager, gossip-coordinator, consensus-builder

GitHub

pr-manager, code-review-swarm, issue-tracker, release-manager

SPARC

sparc-coord, sparc-coder, specification, pseudocode, architecture, refinement

Commands

Spawn Agent

npx claude-flow agent spawn --type coder --name my-coder

List Agents

npx claude-flow agent list --filter active

Agent Status

npx claude-flow agent status --id agent-123

Agent Metrics

npx claude-flow agent metrics --id agent-123

Stop Agent

npx claude-flow agent stop --id agent-123

Pool Management

npx claude-flow agent pool --size 5 --type coder

Routing Codes

Code	Task	Agents
1	Bug Fix	coordinator, researcher, coder, tester
3	Feature	coordinator, architect, coder, tester, reviewer
5	Refactor	coordinator, architect, coder, reviewer
7	Performance	coordinator, perf-engineer, coder
9	Security	coordinator, security-architect, auditor

Best Practices

Use hierarchical topology for coordination
Keep agent count under 8 for tight coordination
Use specialized agents for specific tasks
Coordinate via memory, not direct communication

Fluxly profile Author and license come from source; runtime, permissions, and network are Fluxly detections or estimates

Fluxly category: AI
Author-declared agents: No explicit declaration found; this is not inferred or tested compatibility
Static check: 88 / 100 · heuristic scan, not runtime safety proof
Author / version / license: @ruvnet · no license declared
Fluxly token estimate: Lean
Fluxly setup estimate: Guided setup
External API key: No requirement detected
Detected OS requirements: macOS · Linux · Windows
Runtime requirements: Unspecified
Detected file/system behavior: Read-only
Write / modify
Shell exec
Detected network behavior: Local-only
Install commands: None (reference only)

Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.

Heads up: 未限定 allowed-tools，默认拥有全部工具权限。

Output preview agent-coordination.preview

The current SKILL.md does not define a fixed output example.

SKILL.md SKILL.md

# Agent Coordination Skill

## Purpose
Spawn and coordinate agents for complex multi-agent tasks.

## Agent Types

### Core Development
`coder`, `reviewer`, `tester`, `planner`, `researcher`

### V3 Specialized
`security-architect`, `security-auditor`, `memory-specialist`, `performance-engineer`

### Swarm Coordination
`hierarchical-coordinator`, `mesh-coordinator`, `adaptive-coordinator`, `collective-intelligence-coordinator`

### Consensus
`byzantine-coordinator`, `raft-manager`, `gossip-coordinator`, `consensus-builder`

### GitHub
`pr-manager`, `code-review-swarm`, `issue-tracker`, `release-manager`

### SPARC
`sparc-coord`, `sparc-coder`, `specification`, `pseudocode`, `architecture`, `refinement`

## Commands

### Spawn Agent
```bash
npx claude-flow agent spawn --type coder --name my-coder
```

### List Agents
```bash
npx claude-flow agent list --filter active
```

### Agent Status
```bash
npx claude-flow agent status --id agent-123
```

### Agent Metrics
```bash
npx claude-flow agent metrics --id agent-123
```

### Stop Agent
```bash
npx claude-flow agent stop --id agent-123
```

### Pool Management
```bash
npx claude-flow agent pool --size 5 --type coder
```

## Routing Codes

| Code | Task | Agents |
|------|------|--------|
| 1 | Bug Fix | coordinator, researcher, coder, tester |
| 3 | Feature | coordinator, architect, coder, tester, reviewer |
| 5 | Refactor | coordinator, architect, coder, reviewer |
| 7 | Performance | coordinator, perf-engineer, coder |
| 9 | Security | coordinator, security-architect, auditor |

## Best Practices
1. Use hierarchical topology for coordination
2. Keep agent count under 8 for tight coordination
3. Use specialized agents for specific tasks
4. Coordinate via memory, not direct communication

Evidence boundary and execution chain

Author text anchors workflow facts; Fluxly only indexes current sections, terms, files, and commands.

sections -> Purpose → Agent Types → Core Development → V3 Specialized → Swarm Coordination → Consensus
terms    -> no emphasized key terms
files/cmd -> coder · reviewer · tester · planner · researcher · security-architect · security-auditor · memory-specialist
body sha256 -> 671a37a5c987