AG

agent-orchestration

Instructs AI to use sub-agents for complex multi-file tasks instead of performing them in the main chat context.

Install

mkdir -p .claude/skills/agent-orchestration && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/2193" && unzip -o skill.zip -d .claude/skills/agent-orchestration && rm skill.zip

Installs to .claude/skills/agent-orchestration

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Agent Orchestration Rules
25 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Spawn implementation agents for multi-file tasks
  • Offload plan execution to sub-agents
  • Preserve main conversation context
  • Summarize agent task results
  • Execute multi-file codebase refactoring

How it works

The skill orchestrates sub-agents to handle complex, multi-file implementation tasks, keeping the main conversation context focused and token-efficient.

Inputs & outputs

You give it
Implementation task or plan phase
You get back
Summary of files created and task status

When to use agent-orchestration

  • Implementing complex features from a plan
  • Multi-file codebase refactoring
  • Running tests after a code change

About this skill

Agent Orchestration Rules

When the user asks to implement something, use implementation agents to preserve main context.

The Pattern

Wrong - burns context:

Main: Read files → Understand → Make edits → Report
      (2000+ tokens consumed in main context)

Right - preserves context:

Main: Spawn agent("implement X per plan")
      ↓
Agent: Reads files → Understands → Edits → Tests
      ↓
Main: Gets summary (~200 tokens)

When to Use Agents

Task TypeUse Agent?Reason
Multi-file implementationYesAgent handles complexity internally
Following a plan phaseYesAgent reads plan, implements
New feature with testsYesAgent can run tests
Single-line fixNoFaster to do directly
Quick config changeNoOverhead not worth it

Key Insight

Agents read their own context. Don't read files in main chat just to understand what to pass to an agent - give them the task and they figure it out.

Example Prompt

Implement Phase 4: Outcome Marking Hook from the Artifact Index plan.

**Plan location:** thoughts/shared/plans/2025-12-24-artifact-index.md (search for "Phase 4")

**What to create:**
1. TypeScript hook
2. Shell wrapper
3. Python script
4. Register in settings.json

When done, provide a summary of files created and any issues.

Trigger Words

When user says these, consider using an agent:

  • "implement", "build", "create feature"
  • "follow the plan", "do phase X"
  • "use implementation agents"

When not to use it

  • For single-line code fixes
  • For quick configuration changes

Limitations

  • Overhead is not justified for simple tasks
  • Requires clear task definition for sub-agents

How it compares

It offloads complexity to specialized agents rather than performing all operations within the main chat context.

Compared to similar skills

agent-orchestration side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
agent-orchestration (this skill)37moNo flagsIntermediate
agent-factory89moReviewAdvanced
claude-opus-4-5-migration98moNo flagsBeginner
subagent-driven-development147moNo flagsAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry