Best use case
copy-agent is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Copy an agent from Product Forge to user or project level
Teams using copy-agent should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/copy-agent/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How copy-agent Compares
| Feature / Agent | copy-agent | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Copy an agent from Product Forge to user or project level
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Copy Agent
Copy an agent from Product Forge plugins to your user-level (`~/.claude/`) or project-level (`.claude/`) directory.
## Usage
```bash
# List available agents
/copy-agent
# Copy to project (default)
/copy-agent product-design:product-architect
# Copy to user level
/copy-agent git-workflow:commit-expert --user
# Explicit project level
/copy-agent python-experts:django-expert --project
```
## Arguments
- `<plugin>:<agent-name>` - The agent to copy in `plugin:name` format
- `--user` - Copy to `~/.claude/{plugin}/agents/{name}.md`
- `--project` - Copy to `.claude/{plugin}/agents/{name}.md` (default)
## What Gets Copied
Agents are single markdown files (`.md`) containing:
- YAML frontmatter with name, description, tools, model, and color
- Agent capabilities and activation triggers
- Autonomous workflow definitions
## Directory Structure
```
# Project-level (default)
.claude/
└── git-workflow/
└── agents/
└── commit-expert.md
# User-level (--user)
~/.claude/
└── git-workflow/
└── agents/
└── commit-expert.md
```
## Execution Instructions
When the user runs this command:
### No Arguments - List Available Agents
1. **Scan Product Forge plugins cache** for all available agents:
```bash
ls ~/.claude/plugins/cache/product-forge-marketplace/*/agents/*.md 2>/dev/null
```
2. **For each plugin with agents**, list them with descriptions:
- Read agent file frontmatter to get `name`, `description`, and `model`
- Format as: `{plugin}:{agent-name} ({model}) - {description}`
3. **Display formatted list**:
```
Available agents from Product Forge:
product-design:
product-architect (sonnet) - Full product development guidance
prd-orchestrator (sonnet) - PRD lifecycle management
qa-tester (sonnet) - Manual QA test procedure creation
web-debugger (sonnet) - Web application debugging
...
git-workflow:
commit-expert (haiku) - Git commit specialist
rebase-expert (haiku) - Git rebase specialist
code-review-expert (sonnet) - Code review orchestrator
...
python-experts:
django-expert (sonnet) - Django web application specialist
fastapi-expert (sonnet) - FastAPI async REST API specialist
...
Usage: /copy-agent <plugin>:<agent-name> [--user | --project]
```
### With Arguments - Copy Agent
1. **Parse arguments**:
- Extract `plugin` and `agent-name` from `<plugin>:<agent-name>` format
- Determine destination: `--user` or `--project` (default)
2. **Locate source agent**:
```bash
SOURCE=~/.claude/plugins/cache/product-forge-marketplace/{plugin}/agents/{agent-name}.md
```
- If not found, show error with available agents from that plugin
3. **Determine destination path**:
- `--project`: `.claude/{plugin}/agents/{agent-name}.md`
- `--user`: `~/.claude/{plugin}/agents/{agent-name}.md`
4. **Check if destination exists**:
- If exists, use **AskUserQuestion** to prompt:
```
Agent '{agent-name}' already exists at {destination}.
Options:
- Overwrite: Replace existing agent
- Rename: Save as {agent-name}-copy.md
- Cancel: Abort operation
```
5. **Create destination directory structure**:
```bash
mkdir -p {destination_dir}
```
6. **Copy agent file**:
```bash
cp {source} {destination}
```
7. **Confirm success**:
```
Agent copied successfully!
Source: ~/.claude/plugins/cache/product-forge-marketplace/{plugin}/agents/{agent-name}.md
Destination: {destination}
The agent is now available in your {project|user} configuration.
```
## Error Handling
- **Plugin not found**: Show list of available plugins
- **Agent not found**: Show list of agents in that plugin
- **Invalid format**: Show usage example with correct format
- **Copy failed**: Show error and suggest checking permissionsRelated Skills
copy-command
Copy a command from Product Forge to user or project level
zod
Zod schema validation patterns and type inference. Auto-loads when validating schemas, parsing data, validating forms, checking types at runtime, or using z.object/z.string/z.infer in TypeScript.
typescript-import-style
Merge-friendly import formatting (one-per-line, alphabetical). Auto-loads when writing TypeScript/JavaScript imports to minimize merge conflicts in parallel development. Enforces consistent grouping and sorting.
setup-mcp-auth
Configure authentication for an existing FastMCP server
fastmcp
FastMCP TypeScript framework patterns for MCP servers. Auto-loads when building MCP servers, creating tools/resources/prompts, implementing authentication, configuring transports, or working with FastMCP in TypeScript.
add-mcp-tool
Add a new tool to an existing FastMCP server with guided configuration
add-mcp-resource
Add a new resource or resource template to an existing FastMCP server
plan-with-team
Validate plan file ownership
privacy-compliance
GDPR, CCPA, and privacy compliance guidance for data protection. Use when handling personal data, implementing consent management, or ensuring regulatory compliance across jurisdictions.
oauth
OAuth 2.0 and OpenID Connect implementation patterns. Use when implementing authentication, authorization flows, or integrating with OAuth providers like Google, GitHub, or custom identity providers.
mcp-security
Use when securing MCP servers, preventing prompt injection, implementing authorization, validating user input, or building secure multi-agent pipelines. Provides 5-layer defense architecture patterns.
rag-cag-security
Security patterns for RAG and CAG systems with multi-tenant isolation. Use when building retrieval-augmented or cache-augmented generation systems that require tenant isolation, access control, and secure data handling.