Agent skill

run-agent

Configures and runs agents with different adapters including Claude, OpenAI, CrewAI, Lyzr, and GitHub Models. Supports local execution, remote git repos, and one-shot prompts. Use when the user wants to run an agent, switch LLM providers, configure adapter settings, or launch agents from git repositories.

Stars 2,657
Forks 321

Install this agent skill to your Project

npx add-skill https://github.com/open-gitagent/gitagent/tree/main/examples/gitagent-helper/skills/run-agent

Metadata

Additional technical details for this skill

author
gitagent
version
1.0.0
category
execution

SKILL.md

Run Agents

When to Use

When a user wants to run an agent locally, from a git repo, or with a specific adapter/framework.

Troubleshooting

If you see authentication errors:

  • Claude: Ensure Claude Code is authenticated (claude auth status)
  • OpenAI: Verify OPENAI_API_KEY is set and valid
  • GitHub: Check GITHUB_TOKEN has correct permissions
  • Lyzr: Confirm LYZR_API_KEY is active

Basic Usage

bash
# Run local agent with Claude (default)
gitagent run -d ./my-agent

# Run from git repo
gitagent run -r https://github.com/user/agent

# Run with a prompt (one-shot mode)
gitagent run -d ./my-agent -p "Review my code"

Adapters

Adapter Flag Env Var Required Interactive
Claude -a claude (uses Claude Code auth) Yes
OpenAI -a openai OPENAI_API_KEY No
CrewAI -a crewai No
OpenClaw -a openclaw ANTHROPIC_API_KEY No (-p required)
Nanobot -a nanobot ANTHROPIC_API_KEY Yes
Lyzr -a lyzr LYZR_API_KEY No (-p required)
GitHub -a github GITHUB_TOKEN No (-p required)
Git -a git (auto-detects) Depends
Prompt -a prompt Print only

Examples

bash
# Claude (interactive)
gitagent run -d ./my-agent

# GitHub Models (one-shot, streaming)
export GITHUB_TOKEN="ghp_..."
gitagent run -d ./my-agent -a github -p "Explain this codebase"

# Lyzr (creates agent on Lyzr Studio + chats)
export LYZR_API_KEY="..."
gitagent run -r https://github.com/user/agent -a lyzr -p "Hello"

# Lyzr one-liner (clone + create + chat)
gitagent lyzr run -r https://github.com/user/agent -p "Hello"

# Auto-detect adapter from repo
gitagent run -r https://github.com/user/agent -a git -p "Hello"

# Just print the system prompt
gitagent run -d ./my-agent -a prompt

Git Caching

Repos cloned via -r are cached at ~/.gitagent/cache/:

bash
# Use cache (default)
gitagent run -r https://github.com/user/agent

# Force refresh
gitagent run -r https://github.com/user/agent --refresh

# No cache (temp dir, deleted after)
gitagent run -r https://github.com/user/agent --no-cache

Auto-Detection (-a git)

The git adapter detects the best runner from the repo:

  1. .gitagent_adapter file (explicit hint)
  2. Model name (claude-* → claude, gpt-* → openai)
  3. Framework files (CLAUDE.md, .cursorrules, crew.yaml, .lyzr_agent_id, .github_models)
  4. Default: claude

Expand your agent's capabilities with these related and highly-rated skills.

Didn't find tool you were looking for?

Be as detailed as possible for better results