Spawn and manage Claude sub-agents for parallel or delegated tasks. WHEN: User needs parallel operations, multi-step autonomous research, or wants to delegate complex tasks to sub-agents. Use when task can be parallelized or requires independent exploration. WHEN NOT: Simple single-step operations, sequential dependencies, specific file reads (use fs_read_file), writing code directly (do it yourself).
/plugin marketplace add cyrup-ai/kodegen-claude-plugin/plugin install kg@kodegenThis skill inherits all available tools. When active, it can use any tool Claude has access to.
mcp__plugin_kg_kodegen__claude_agent spawns independent Claude sub-sessions that can execute tasks autonomously. Each agent has its own conversation context, can use tools, and returns a final report. Perfect for parallel research, independent code analysis, or complex multi-step delegations.
Create a new agent session with initial prompt.
Send additional prompt to existing agent.
Read current output from agent.
List all active agent sessions.
Terminate agent session and cleanup.
| Parameter | Type | Required | Description |
|---|---|---|---|
action | string | No | SPAWN (default), SEND, READ, LIST, KILL |
agent | number | No | Agent instance (0, 1, 2...), default: 0 |
prompt | string | SPAWN/SEND | Task for the agent to perform |
system_prompt | string | No | Custom system prompt for agent behavior |
await_completion_ms | number | No | Timeout in ms (default: 300000 = 5 min) |
max_turns | number | No | Max conversation turns (default: 10) |
allowed_tools | array | No | Tools agent CAN use (allowlist) |
disallowed_tools | array | No | Tools agent CANNOT use (blocklist) |
cwd | string | No | Working directory for agent |
add_dirs | array | No | Additional context directories |
{
"action": "SPAWN",
"prompt": "Research all error handling patterns in this codebase. Return a summary of patterns found with file locations.",
"max_turns": 15
}
// Agent 0: Research
{
"agent": 0,
"prompt": "Find all API endpoints and document their signatures"
}
// Agent 1: Analysis (concurrent)
{
"agent": 1,
"prompt": "Analyze test coverage and identify untested code paths"
}
{
"prompt": "Review this codebase for security vulnerabilities",
"allowed_tools": ["fs_read_file", "fs_search", "fs_list_directory"],
"disallowed_tools": ["terminal", "fs_write_file", "fs_delete_file"]
}
{
"prompt": "Deep dive into the authentication system architecture",
"await_completion_ms": 60000,
"max_turns": 20
}
{"action": "READ", "agent": 0}
{"action": "LIST"}
{"action": "KILL", "agent": 0}
| Scenario | Use Agent? | Why |
|---|---|---|
| Search for keyword in codebase | Yes | Agent explores autonomously |
| Read specific known file | No | Use fs_read_file directly |
| Parallel research tasks | Yes | Spawn multiple agents |
| Write code | No | Do it yourself |
| Complex multi-step analysis | Yes | Agent handles autonomously |
| Simple calculation | No | Overkill |
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.