Agent Factory
Generates production-ready Claude Code agents and sub-agents with standardized frontmatter, tool scopes, and safe execution patterns.
Dev & CodingIntermediate★ 847⑂ 172AI score 8/10Last updated: Nov 12, 2025
What it does
Produces complete agent Markdown files you can drop straight into .claude/agents/.
- Four proven archetypes: Strategic (blue), Implementation (green), Quality (red), Coordination (purple)
- Enhanced YAML frontmatter:
name,description,tools,model,color,field,expertise,mcp_tools - Tool-scope guidance: least-privilege tool sets per agent type (strategic agents get Read/Write/Grep only)
- Execution safety rules: 4–5 strategic agents in parallel is fine; quality/testing agents must run sequentially
- MCP suggestions: mcp__github, mcp__playwright, mcp__context7 and custom servers
Who it's for
- Developers who want to freeze repeated workflows into dedicated sub-agents
- Tech leads standardizing team conventions (style, testing) as agents
- Builders assembling a whole agent suite / agentic framework
- Newcomers unsure how to pick tools, model tier, or expertise level
Examples
- API integration specialist — "Create api-integration-specialist, backend domain, OAuth + REST error handling, mcp__github" → full agent file with valid frontmatter.
- Feature pipeline — product-planner (requirements) → frontend-developer + backend-developer (parallel) → test-runner (sequential) → code-reviewer (sequential).
- Security auditor — generate a red Quality-type security-auditor whose file explicitly forbids running in parallel with other quality agents.
· · · Install guide · · ·
Try it now, no install
Paste this into Claude to use the skill without installing anything.
Read the instructions in this file and follow them to help me: https://raw.githubusercontent.com/alirezarezvani/claude-code-skill-factory/HEAD/generated-skills/agent-factory/SKILL.md What I want: (describe your task here)
If Claude can't open the link, open it yourself and paste the contents instead.
↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.
Install in the Claude app (no terminal)
- Download the ZIP with the button below.
- In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
- Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
Install in Claude Code
Let Claude do it — paste this into Claude Code
Install the skill I found on Claude Skill Mart. Copy the generated-skills/agent-factory folder from the GitHub repo alirezarezvani/claude-code-skill-factory into my ~/.claude/skills/agent-factory/. When it's done, tell me in one line what this skill can do.
Install with a command instead
git clone https://github.com/alirezarezvani/claude-code-skill-factory.git && mkdir -p ~/.claude/skills && cp -r claude-code-skill-factory/generated-skills/agent-factory ~/.claude/skills/⚠ This is a third-party skill. Check the source repository before installing.
- Open a terminal.
- Clone the repo:
git clone https://github.com/alirezarezvani/claude-code-skill-factory.git - Create the skills folder:
mkdir -p ~/.claude/skills - Copy the skill:
cp -r claude-code-skill-factory/generated-skills/agent-factory ~/.claude/skills/ - The skill links to
documentation/templates/AGENTS_FACTORY_PROMPT.md. Keep the cloned repo around, or copy that template into~/.claude/skills/agent-factory/so the reference resolves. - Restart Claude Code and run
/skillsto confirmagent-factoryis listed. - Ask something like "use agent-factory to build a backend domain agent", then save the generated file to
.claude/agents/(project) or~/.claude/agents/(personal). - Run a small task first to verify the new agent is discovered and invoked correctly.
View source on GitHub ↗License: MIT