Agent Task Mapping

Agent Task Mapping

• Leverage native parallel subagent dispatch and 200k+ context windows where available.

Activation Conditions

Use symptom -> action triggers: when one matches, apply this skill and verify with the protocol below.

Use this skill when:

• Determining which specialized agent to delegate a task to
• Reviewing agent capabilities and expertise areas
• Trying to match a specific task to an appropriate specialist
• Needing quick reference for available agents and their purposes

Available Agents

See Agent Details for comprehensive information about each agent:

• Description and specialization areas
• When to use each agent
• Typical tasks handled by each

Cross-Client Portability

This skill is written to stay usable across GitHub Copilot, Claude Code, and Codex.

• GitHub Copilot: keep the folder in a Copilot-visible skill path or wrap the workflow in project instructions when folder discovery is unavailable.
• Claude Code: keep the folder in a local skills directory or a compatible plugin source.
• Codex: install or sync the folder into $CODEX_HOME/skills/agent-task-mapping and restart Codex after major changes.

MCP Availability And Fallback

Preferred MCP Server: None required

• Fallback prompt: "Use the Agent Task Mapping skill without MCP. Rely on its local instructions, bundled resources, standard shell or editor tools, and direct verification. Show the evidence used before concluding."
• Do not claim an MCP operation was used when the active host does not expose it.
• Treat local files, tests, rendered outputs, logs, or screenshots as the fallback evidence path.

Anti-Patterns

• Delegating or evaluating without a scoped success condition: The output becomes hard to review and easy to overbuild.
• Skipping the evidence step: A workflow that cannot be re-checked quickly is not ready for handoff.
• Bundling unrelated subtasks together: It creates noisy prompts, weaker ownership, and avoidable integration risk.

Verification Protocol

Before claiming "skill applied successfully":

1. Pass/fail: The Agent Task Mapping workflow names the agent boundary, delegated scope, and expected return artifact.
2. Pass/fail: Context passed to helpers is minimal, task-local, and free of hidden expected answers.
3. Pass/fail: Results are integrated only after evidence, diffs, or citations are checked by the controller.
4. Pressure-test scenario: Run the workflow on two similar tasks that must not share assumptions or leaked context.
5. Success metric: Zero context leakage; every delegated output is independently reviewable.

Examples & Scripts

• Delegation Examples — Code examples for delegating to different agents
• Agent Discovery Script — Node.js script to discover available agents

Quick Reference

Decision Framework

When choosing an agent for delegation:

1. Identify task type: Is it documentation, testing, two-stage review (spec compliance first, then code quality), or development?
2. Match to specialization: Find agent whose description aligns with task
3. Check availability: Verify agent exists and has proper frontmatter configuration
4. Use specific agentName: Delegate using exact name from agent's frontmatter

Task Categories

Code Analysis & Documentation

• Use Code Explainer for analyzing existing code patterns
• Use Tech Writer for formal developer documentation
• Use Specification for generating feature specifications

Code Quality & Maintenance

• Use Universal Janitor for cleanup and tech debt remediation
• Use Critical Thinking for challenging assumptions

Development Work

• Use Next.js Expert for Next.js 15/16+ architecture and optimizations
• Use Expert React Frontend Engineer for React 19+ patterns

Testing

• Use Playwright Tester Mode for comprehensive web application testing

Planning & Requirements

• Use Plan for research and outlining multi-step plans
• Use Create PRD Chat Mode for generating Product Requirements Documents

Design

• Use UI Designer for UI/UX improvements and design implementations

Related Skills

• custom-agent-usage: Use it when the workflow also needs loading and invoking custom agent definitions safely.
• subagent-delegation: Use it when the workflow also needs safe, scoped delegation to helper agents.
• subagent-driven-development: Use it when the workflow also needs plan-driven implementation with reviewer loops.
• agentic-eval: Use it when the workflow also needs rubric-driven evaluation loops.