Skip to content

open-gitagent/opengap / examples/gitagent-helper/skills/run-agent

run-agent

Unverified

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.

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

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

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

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

Adapters

AdapterFlagEnv Var RequiredInteractive
Claude-a claude(uses Claude Code auth)Yes
OpenAI-a openaiOPENAI_API_KEYNo
CrewAI-a crewai—No
OpenClaw-a openclawANTHROPIC_API_KEYNo (-p required)
Nanobot-a nanobotANTHROPIC_API_KEYYes
Lyzr-a lyzrLYZR_API_KEYNo (-p required)
GitHub-a githubGITHUB_TOKENNo (-p required)
Git-a git(auto-detects)Depends
Prompt-a prompt—Print only

Examples

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

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

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

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

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

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

Git Caching

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

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

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

# No cache (temp dir, deleted after)
opengap 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
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 463kUpdated Claude CodeCodexVerifiedInstall
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 463kUpdated Claude CodeCodexVerifiedInstall
discernment-nudgeanthropics/skillsAfter you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.Stars: 195kUpdated Claude CodeCodexVerifiedInstall
internal-commsanthropics/skillsA set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).Stars: 195kUpdated Claude CodeCodexVerifiedInstall