Orchestrate baselayer subagents for complex tasks. Defines available agents, their skills, and workflows for multi-agent scenarios. Load when coordinating work across agents, delegating tasks, or deciding which agent handles what.
/plugin marketplace add outfitter-dev/agents/plugin install baselayer@outfitterThis skill inherits all available tools. When active, it can use any tool Claude has access to.
references/agent-skills.mdreferences/workflows.mdOrchestrate baselayer subagents by matching tasks to the right agent + skill combinations.
| Agent | Purpose | Primary Skills |
|---|---|---|
| developer | Build, implement, fix, refactor | software-engineering, test-driven-development, bun-dev, react-dev, hono-dev, ai-sdk |
| reviewer | Evaluate code, PRs, architecture | code-review, performance-engineering, software-architecture |
| analyst | Investigate, research, explore | codebase-analysis, research-and-report, pathfinding, report-findings |
| debugger | Diagnose issues, trace problems | debugging-and-diagnosis, codebase-analysis |
| tester | Validate, prove, verify behavior | scenario-testing, test-driven-development |
| skeptic | Challenge complexity, question assumptions | complexity-analysis |
| specialist | Infrastructure, CI/CD, domain expertise | (loads skills dynamically) |
| pattern-analyzer | Extract reusable patterns from work | pattern-analysis, patternify, conversation-analysis |
User request arrives
│
├─► "build/implement/fix/refactor" ──► developer
│
├─► "review/critique/audit" ──► reviewer
│
├─► "investigate/research/explore" ──► analyst
│
├─► "debug/diagnose/trace" ──► debugger
│
├─► "test/validate/prove" ──► tester
│
├─► "simplify/challenge/is this overkill" ──► skeptic
│
├─► "deploy/configure/CI" ──► specialist
│
└─► "capture this workflow/make reusable" ──► pattern-analyzer
One agent completes, passes to next:
analyst (investigate) → developer (implement) → reviewer (verify) → tester (validate)
Use when: Clear phases, each requires different expertise.
Multiple agents work simultaneously:
┌─► reviewer (code quality)
│
task ──┼─► analyst (impact analysis)
│
└─► tester (regression tests)
Use when: Independent concerns, time-sensitive, comprehensive coverage needed.
Build → challenge → refine:
developer (propose) ←→ skeptic (challenge) → developer (refine)
Use when: Complex architecture, preventing over-engineering, high-stakes decisions.
Narrow down, then fix:
analyst (scope) → debugger (root cause) → developer (fix) → tester (verify)
Use when: Bug reports, production issues, unclear symptoms.
| Task | Agent | Skills |
|---|---|---|
| New feature | developer | software-engineering, test-driven-development |
| Bug fix | debugger → developer | debugging-and-diagnosis, software-engineering |
| Refactor | developer + skeptic | software-engineering, complexity-analysis |
| API endpoint | developer | hono-dev, software-engineering |
| React component | developer | react-dev, software-engineering |
| AI feature | developer | ai-sdk, software-engineering |
| Task | Agent | Skills |
|---|---|---|
| PR review | reviewer | code-review |
| Architecture review | reviewer | software-architecture |
| Performance audit | reviewer | performance-engineering |
| Pre-merge check | reviewer + tester | code-review, scenario-testing |
| Task | Agent | Skills |
|---|---|---|
| Codebase exploration | analyst | codebase-analysis |
| Research question | analyst | research-and-report |
| Unclear requirements | analyst | pathfinding |
| Status report | analyst | status-reporting, report-findings |
| Task | Agent | Skills |
|---|---|---|
| Feature validation | tester | scenario-testing |
| TDD implementation | developer or tester | test-driven-development |
| Integration testing | tester | scenario-testing |
"I need to build X" → developer + software-engineering + test-driven-development
"Review this PR" → reviewer + code-review
"Why is this broken?" → debugger + debugging-and-diagnosis
"Is this approach overkill?" → skeptic + complexity-analysis
"Prove this works" → tester + scenario-testing
"What's the codebase doing?" → analyst + codebase-analysis
"Deploy to production" → specialist + (domain skills)
"Make this workflow reusable" → pattern-analyzer + patternify
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.