Skip to main content
skill CX Codex

create-subagents — Claude Code skill: setup and installation

create-subagents is a Claude Code skill for configuring subagents, their tools and prompts, and delegating work through Task. It supports splitting tasks across specialized agents.

MIT ★ 1,988 updated 2026-04-01

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add glittercowboy/taches-cc-resources
/plugin install taches-cc-resources@taches-cc-resources
Open on GitHub

What create-subagents does

This skill covers subagent setup: defining a focused role, choosing tool access, writing system instructions, and coordinating work through Task. It recommends organizing prompt content with XML tags for sections such as role, constraints, workflow, and output format, rather than using Markdown headings.

A subagent works in an isolated context and sends its final result back to the main conversation. It cannot ask the user questions or wait for input, so gather requirements in the main chat first. Create an agent with /agents and choose project scope in .claude/agents/ or user scope in ~/.claude/agents/. When names conflict, the project-level agent takes priority.

What it helps with

  • create a subagent for a specific code task
  • limit an agent to selected tools
  • configure automatic agent selection from its description
  • split research and code generation across agents

Example prompts for the agent

  • Help me create a code security subagent and choose its tools.
  • Set up a project subagent in .claude/agents/ to research an API and return a report.
  • Explain how to delegate research and code generation to separate subagents through Task.

How to install create-subagents

1Plugin marketplace

/plugin marketplace add glittercowboy/taches-cc-resources
/plugin install taches-cc-resources@taches-cc-resources

This installs the whole taches-cc-resources plugin with all its skills

2Skills CLI (Vercel)

npx skills add glittercowboy/taches-cc-resources --skill create-subagents -a claude-code

3Manually: put the files in place

~/.claude/skills/create-subagents/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/create-subagents/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about create-subagents

How do I install create-subagents in Claude Code?

Run these commands in order: /plugin marketplace add glittercowboy/taches-cc-resources, then /plugin install taches-cc-resources@taches-cc-resources.

What does the create-subagents skill do?

It guides you through defining Claude Code subagent roles, prompts, and tool access, then coordinating delegated work with Task.

Can a subagent ask the user questions?

No. A subagent cannot interact with the user; it returns its final output to the main conversation. Collect requirements and decisions in the main chat.

Source text

SKILL.md · MIT
---
name: create-subagents
description: Expert guidance for creating, building, and using Claude Code subagents and the Task tool. Use when working with subagents, setting up agent configurations, understanding how agents work, or using the Task tool to launch specialized agents.
---

<objective>
Subagents are specialized Claude instances that run in isolated contexts with focused roles and limited tool access. This skill teaches you how to create effective subagents, write strong system prompts, configure tool access, and orchestrate multi-agent workflows using the Task tool.

Subagents enable delegation of complex tasks to specialized agents that operate autonomously without user interaction, returning their final output to the main conversation.
</objective>

<quick_start>
<workflow>
1. Run `/agents` command
2. Select "Create New Agent"
3. Choose project-level (`.claude/agents/`) or user-level (`~/.claude/agents/`)
4. Define the subagent:
   - **name**: lowercase-with-hyphens
   - **description**: When should this subagent be used?
   - **tools**: Optional comma-separated list (inherits all if omitted)
   - **model**: Optional (`sonnet`, `opus`, `haiku`, or `inherit`)
5. Write the system prompt (the subagent's instructions)
</workflow>

<example>
```markdown
---
name: code-reviewer
description: Expert code reviewer. Use proactively after code changes to review for quality, security, and best practices.
tools: Read, Grep, Glob, Bash
model: sonnet
---

<role>
You are a senior code reviewer focused on quality, security, and best practices.
</role>

<focus_areas>
- Code quality and maintainability
- Security vulnerabilities
- Performance issues
- Best practices adherence
</focus_areas>

<output_format>
Provide specific, actionable feedback with file:line references.
</output_format>
```
</example>
</quick_start>

<file_structure>
| Type | Location | Scope | Priority |
|------|----------|-------|----------|
| **Project** | `.claude/agents/` | Current project only | Highest |
| **User** | `~/.claude/agents/` | All projects | Lower |
| **Plugin** | Plugin's `agents/` dir | All projects | Lowest |

Project-level subagents override user-level when names conflict.
</file_structure>

<configuration>
<field name="name">
- Lowercase letters and hyphens only
- Must be unique
</field>

<field name="description">
- Natural language description of purpose
- Include when Claude should invoke this subagent
- Used for automatic subagent selection
</field>

<field name="tools">
- Comma-separated list: `Read, Write, Edit, Bash, Grep`
- If omitted: inherits all tools from main thread
- Use `/agents` interface to see all available tools
</field>

<field name="model">
- `sonnet`, `opus`, `haiku`, or `inherit`
- `inherit`: uses same model as main conversation
- If omitted: defaults to configured subagent model (usually sonnet)
</field>
</configuration>

<execution_model>
<critical_constraint>
**Subagents are black boxes that cannot interact with users.**

Subagents run in isolated contexts and return their final output to the main conversation. They:
- ✅ Can use tools like Read, Write, Edit, Bash, Grep, Glob
- ✅ Can access MCP servers and other non-interactive tools
- ❌ **Cannot use AskUserQuestion** or any tool requiring user interaction
- ❌ **Cannot present options or wait for user input**
- ❌ **User never sees subagent's intermediate steps**

The main conversation sees only the subagent's final report/output.
</critical_constraint>

<workflow_design>
**Designing workflows with subagents:**

Use **main chat** for:
- Gathering requirements from user (AskUserQuestion)
- Presenting options or decisions to user
- Any task requiring user confirmation/input
- Work where user needs visibility into progress

Use **subagents** for:
- Research tasks (API documentation lookup, code analysis)
- Code generation based on pre-defined requirements
- Analysis and reporting (security review, test coverage)
- Context-heavy operations that don't need user interaction

**Example workflow pattern:**
```
Main Chat: Ask user for requirements (AskUserQuestion)
  ↓
Subagent: Research API and create documentation (no user interaction)
  ↓
Main Chat: Review research with user, confirm approach
  ↓
Subagent: Generate code based on confirmed plan
  ↓
Main Chat: Present results, handle testing/deployment
```
</workflow_design>
</execution_model>

<system_prompt_guidelines>
<principle name="be_specific">
Clearly define the subagent's role, capabilities, and constraints.
</principle>

<principle name="use_pure_xml_structure">
Structure the system prompt with pure XML tags. Remove ALL markdown headings from the body.

```markdown
---
name: security-reviewer
description: Reviews code for security vulnerabilities
tools: Read, Grep, Glob, Bash
model: sonnet
---

<role>
You are a senior code reviewer specializing in security.
</role>

<focus_areas>
- SQL injection vulnerabilities
- XSS attack vectors
- Authentication/authorization issues
- Sensitive data exposure
</focus_areas>

<workflow>
1. Read the modified files
2. Identify security risks
3. Provide specific remediation steps
4. Rate severity (Critical/High/Medium/Low)
</workflow>
```
</principle>

<principle name="task_specific">
Tailor instructions to the specific task domain. Don't create generic "helper" subagents.

❌ Bad: "You are a helpful assistant that helps with code"
✅ Good: "You are a React component refactoring specialist. Analyze components for hooks best practices, performance anti-patterns, and accessibility issues."
</principle>
</system_prompt_guidelines>

<subagent_xml_structure>
Subagent.md files are system prompts consumed only by Claude. Like skills and slash commands, they should use pure XML structure for optimal parsing and token efficiency.

<recommended_tags>
Common tags for subagent structure:

- `<role>` - Who the subagent is and what it does
- `<constraints>` - Hard rules (NEVER/MUST/ALWAYS)
- `<focus_areas>` - What to prioritize
- `<workflow>` - Step-by-step process
- `<output_format>` - How to structure deliverables
- `<success_criteria>` - Completion criteria
- `<validation>` - How to verify work
</recommended_tags>

<intelligence_rules>
**Simple subagents** (single focused task):
- Use role + constraints + workflow minimum
- Example: code-reviewer, test-runner

**Medium subagents** (multi-step process):
- Add workflow steps, output_format, success_criteria
- Example: api-researcher, documentation-generator

**Complex subagents** (research + generation + validation):
- Add all tags as appropriate including validation, examples
- Example: mcp-api-researcher, comprehensive-auditor
</intelligence_rules>

<critical_rule>
**Remove ALL markdown headings (##, ###) from subagent body.** Use semantic XML tags instead.

Keep markdown formatting WITHIN content (bold, italic, lists, code blocks, links).

For XML structure principles and token efficiency details, see @skills/create-agent-skills/references/use-xml-tags.md - the same principles apply to subagents.
</critical_rule>
</subagent_xml_structure>

<invocation>
<automatic>
Claude automatically selects subagents based on the `description` field when it matches the current task.
</automatic>

<explicit>
You can explicitly invoke a subagent:

```
> Use the code-reviewer subagent to check my recent changes
```

```
> Have the test-writer subagent create tests for the new API endpoints
```
</explicit>
</invocation>

<management>
<using_agents_command>
Run `/agents` for an interactive interface to:
- View all available subagents
- Create new subagents
- Edit existing subagents
- Delete custom subagents
</using_agents_command>

<manual_editing>
You can also edit subagent files directly:
- Project: `.claude/agents/subagent-name.md`
- User: `~/.claude/agents/subagent-name.md`
</manual_editing>
</management>

<reference>
**Core references**:

**Subagent usage and configuration**: [references/subagents.md](references/subagents.md)
- File format and configuration
- Model selection (Sonnet 4.5 + Haiku 4.5 orchestration)
- Tool security and least privilege
- Prompt caching optimization
- Complete examples

**Writing effective prompts**: [references/writing-subagent-prompts.md](references/writing-subagent-prompts.md)
- Core principles and XML structure
- Description field optimization for routing
- Extended thinking for complex reasoning
- Security constraints and strong modal verbs
- Success criteria definition

**Advanced topics**:

**Evaluation and testing**: [references/evaluation-and-testing.md](references/evaluation-and-testing.md)
- Evaluation metrics (task completion, tool correctness, robustness)
- Testing strategies (offline, simulation, online monitoring)
- Evaluation-driven development
- G-Eval for custom criteria

**Error handling and recovery**: [references/error-handling-and-recovery.md](references/error-handling-and-recovery.md)
- Common failure modes and causes
- Recovery strategies (graceful degradation, retry, circuit breakers)
- Structured communication and observability
- Anti-patterns to avoid

**Context management**: [references/context-management.md](references/context-management.md)
- Memory architecture (STM, LTM, working memory)
- Context strategies (summarization, sliding window, scratchpads)
- Managing long-running tasks
- Prompt caching interaction

**Orchestration patterns**: [references/orchestration-patterns.md](references/orchestration-patterns.md)
- Sequential, parallel, hierarchical, coordinator patterns
- Sonnet + Haiku orchestration for cost/performance
- Multi-agent coordination
- Pattern selection guidance

**Debugging and troubleshooting**: [references/debugging-agents.md](references/debugging-agents.md)
- Logging, tracing, and correlation IDs
- Common failure types (hallucinations, format errors, tool misuse)
- Diagnostic procedures
- Continuous monitoring
</reference>

<success_criteria>
A well-configured subagent has:

- Valid YAML frontmatter (name matches file, description includes triggers)
- Clear role definition in system prompt
- Appropriate tool restrictions (least privilege)
- XML-structured system prompt with role, approach, and constraints
- Description field optimized for automatic routing
- Successfully tested on representative tasks
- Model selection appropriate for task complexity (Sonnet for reasoning, Haiku for simple tasks)
</success_criteria>

© Lex Christopherson · MIT · glittercowboy/taches-cc-resources

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set48

The whole set →
create-mcp-servers create-mcp-servers guides development of Model Context Protocol servers in Python and TypeScript for Claude Code, covering architecture, secrets isolation, and debugging. CX Codex +1 ★ 1,988repo stars slash-command-auditor slash-command-auditor audits Claude Code slash-command .md files for structure, arguments, context loading, tool scope, and security issues. CX Codex ★ 1,988repo stars create-hooks The create-hooks skill explains how Claude Code hooks work and gives ready configs for blocking dangerous commands, logging, and auto-formatting. CX Codex +1 ★ 1,988repo stars subagent-auditor subagent-auditor audits Claude Code subagent configurations against structured best practices. Catches malformed XML, unneeded tool permissions, and weak boundary constraints. CX Codex ★ 1,988repo stars debug-like-expert debug-like-expert activates a structured debugging protocol for complex issues when standard troubleshooting fails. Gathers evidence, tests hypotheses, and finds root causes instead of applying quick fixes. CX Codex +1 ★ 1,988repo stars skill-auditor skill-auditor audits SKILL.md files against Claude Code standards. It checks XML formatting, YAML frontmatter, and progressive disclosure rules. CX Codex ★ 1,988repo stars create-slash-commands create-slash-commands — a Claude Code skill for writing slash commands with YAML frontmatter and XML tags. Handy for standardizing repeatable operations across a project or for yourself. CX Codex +1 ★ 1,988repo stars create-prompt create-prompt — a command that builds executable prompts for other Claude instances. Asks clarifying questions about your task, then saves a structured prompt to your project. CX Codex +1 ★ 1,988repo stars

Project sponsors

Companies that keep this analytics open