meta-agent-creator — Claude Code skill for creating subagents
The meta-agent-creator Claude Code skill helps define custom subagents and configure their settings. Use it to shape task delegation and control which tools an agent can access.
MIT 104 installs ★ 29 updated 2026-08-17
npx skills add oakoss/agent-skills --skill meta-agent-creator -a claude-codeWhat meta-agent-creator does
The skill guides the creation of specialized subagents in Markdown files with YAML fields. It covers agent scope, tool access, model choice, and permission modes. It also explains skill preloading and lifecycle hooks.
An agent can have restricted tools and permissions, while its description can specify when a task should be routed to it. The guidance covers project and user files, CLI settings, and plugins. Nested delegation is unsupported: a subagent cannot start another subagent.
What it helps with
- create a focused subagent for a specific task
- restrict an agent’s access to tools
- choose a model and permission mode
- define when tasks go to a subagent
Example prompts for the agent
- Create a test-checking subagent and define its settings.
- Set up a read-only agent to review files.
- How should the main conversation delegate tasks to an agent?
How to install meta-agent-creator
1Skills CLI (Vercel)
npx skills add oakoss/agent-skills --skill meta-agent-creator -a claude-code2Manually: put the files in place
~/.claude/skills/meta-agent-creator/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/meta-agent-creator/
1Skills CLI (Vercel)
npx skills add oakoss/agent-skills --skill meta-agent-creator -a codex2Manually: put the files in place
.agents/skills/meta-agent-creator/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add oakoss/agent-skills --skill meta-agent-creator -a cursor2Manually: put the files in place
.cursor/skills/meta-agent-creator/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install oakoss/agent-skills skills/meta-agent-creator2Manually: put the files in place
.github/skills/meta-agent-creator/SKILL.md1Skills CLI (Vercel)
npx skills add oakoss/agent-skills --skill meta-agent-creator -a gemini-cli2Platform CLI
gemini skills install https://github.com/oakoss/agent-skills --path skills/meta-agent-creatorManually: put the files in place
.devin/skills/meta-agent-creator/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add oakoss/agent-skills --skill meta-agent-creator -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about meta-agent-creator
How do I install meta-agent-creator in Claude Code?
Run npx skills add oakoss/agent-skills --skill meta-agent-creator -a claude-code. The skill file is at ~/.claude/skills/meta-agent-creator/SKILL.md.
What does meta-agent-creator do?
It guides the setup of custom subagents in Markdown files, including their tools, model, permissions, skills, and hooks.
Can subagents start other subagents?
No. Nested delegation is unsupported; tasks are delegated from the main conversation.
Source text
SKILL.md · MIT
---
name: meta-agent-creator
description: |
Creates custom subagents for Claude Code with YAML frontmatter configuration in Markdown files. Covers agent scoping (project, user, CLI, plugin), tool access control, model selection, permission modes, skill preloading, and lifecycle hooks.
Use when building specialized subagents, configuring tool access, selecting models, setting permission modes, or designing delegation patterns. Use for agent creation, subagent configuration, custom agent setup.
license: MIT
metadata:
author: oakoss
version: '1.0'
source: https://code.claude.com/docs/en/sub-agents
disable-model-invocation: true
---
# Custom Agent Creator
## Overview
Subagents are specialized AI assistants defined as Markdown files with YAML frontmatter. Each subagent runs in its own context window with a custom system prompt, specific tool access, and independent permissions. When a task matches a subagent's description, the parent conversation delegates to it automatically, preserving main context while enforcing constraints.
**When to use:** Isolating high-volume operations (tests, logs), enforcing read-only access for reviewers, routing simple tasks to cheaper models, running parallel research, creating reusable team workflows.
**When NOT to use:** Tasks requiring frequent back-and-forth, quick targeted changes, workflows needing nested delegation (subagents cannot spawn subagents), latency-sensitive operations where fresh context gathering is costly.
## Quick Reference
| Pattern | Configuration | Key Points |
| ----------------------- | ------------------------------ | ------------------------------------------------------- |
| File location (project) | `.claude/agents/name.md` | Shared via version control, priority 2 |
| File location (user) | `~/.claude/agents/name.md` | Available across all projects, priority 3 |
| Required fields | `name`, `description` | Only two fields are mandatory |
| Tool restriction | `tools: Read, Grep, Glob` | Allowlist; inherits all if omitted |
| Tool denial | `disallowedTools: Write, Edit` | Denylist; removed from inherited set |
| Model selection | `model: haiku` | Options: `sonnet`, `opus`, `haiku`, `inherit` (default) |
| Permission mode | `permissionMode: dontAsk` | Controls permission prompt behavior |
| Skill preloading | `skills: [auth, api-patterns]` | Injected at startup; no inheritance from parent |
| Lifecycle hooks | `hooks: { PreToolUse: [...] }` | Validate or block tool usage conditionally |
| CLI-defined agent | `claude --agents '{...}'` | Session-only, highest priority, JSON format |
| Interactive creation | `/agents` command | Guided setup with Claude generation |
| Proactive triggers | `"Use proactively after..."` | Include in description for auto-delegation |
## Common Mistakes
| Mistake | Correct Pattern |
| ----------------------------------------------- | ---------------------------------------------------------------- |
| Using opus for simple checklist reviews | Use haiku for read-only reviews and style checks |
| Omitting output format in system prompt | Include structured output template for consistent results |
| Listing tools explicitly when all are needed | Omit `tools` field to inherit all tools including MCP |
| Expecting skills from parent conversation | Explicitly list skills in the `skills` field |
| Generic description without triggers | Include specific trigger phrases like "Use proactively when..." |
| Giving a single agent too many responsibilities | Design focused agents with one clear purpose each |
| Using `bypassPermissions` without caution | Prefer `acceptEdits` or `dontAsk` for safer automation |
| Creating deeply nested agent workflows | Chain subagents from main conversation; nesting is not supported |
## Delegation
- **Agent pattern discovery**: Use `Explore` agent to find existing agents in `.claude/agents/`
- **Interactive creation**: Use `/agents` command for guided setup with Claude generation
- **Code review of agent files**: Use `Task` agent to validate system prompts and configuration
## References
- [Agent configuration: YAML fields, file locations, and priority order](references/agent-configuration.md)
- [Tool selection: access patterns, common combinations, and model guide](references/tool-selection.md)
- [Templates: ready-to-use agent patterns for common workflows](references/templates.md)
© oakoss · MIT · oakoss/agent-skills