run-agent
Launch agents with flexible LLM provider selection across Claude, OpenAI, CrewAI, Lyzr, GitHub Models, and other adapters. Supports local directories, remote git repositories, and one-shot prompts for immediate execution. Auto-detection identifies the best adapter from your repo's configuration.
run-agent executes local or remote agents with your choice of LLM adapter, from Claude to GitHub Models.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-02
run-agent executes local or remote agents with your choice of LLM adapter, from Claude to GitHub Models. Launch agents with flexible LLM provider selection across Claude, OpenAI, CrewAI, Lyzr, GitHub Models, and other adapters. Supports local directories, remote git repositories, and one-shot prompts for immediate execution. Auto-detection identifies the best adapter from your repo's configuration.
Use it when
- Yes.
- run-agent supports launching agents directly from remote git repositories.
Verify before relying
Read SKILL.md below before installing (1 file). Open directory: indexed for reading, not audited.
Install
open-gitagent/opengap/run-agent · repository language: TypeScript
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How to run an agent locally with run-agent?
run-agent launches agents from your local directory by auto-detecting the best LLM adapter from your repository's configuration. Simply point it to your agent folder, and it identifies whether you're using Claude, OpenAI, CrewAI, Lyzr, GitHub Models, or another supported framework, then executes it with the appropriate adapter settings.
Can I execute an agent with a specific LLM adapter?
Yes. run-agent lets you specify which LLM adapter to use—Claude, OpenAI, CrewAI, Lyzr, GitHub Models, and others are supported. You can configure your preferred adapter in the agent's settings, and run-agent will execute using that exact framework for consistent behavior across runs.
How do I run an agent from a GitHub repository?
run-agent supports launching agents directly from remote git repositories. Provide the repository URL, and run-agent clones and configures the agent from that source. This works for both local setup and immediate execution, letting you run agents hosted anywhere without manual cloning.
What's the best way to switch LLM providers for agent execution?
run-agent makes provider switching seamless by letting you select different LLM adapters—Claude, OpenAI, CrewAI, Lyzr, GitHub Models, and more. Change your adapter configuration or specify it at runtime, and run-agent handles the switch automatically without rewriting your agent code.
Can run-agent execute an agent with just one prompt?
Yes. run-agent supports one-shot mode, letting you execute agents with a single prompt for immediate results. This is ideal for quick testing, prototyping, or running agents without complex multi-turn setup—just provide your prompt and run-agent handles the rest.
How does run-agent auto-detect the right adapter?
run-agent scans your repository's configuration files to identify which framework and LLM adapter your agent uses. It recognizes Claude, OpenAI, CrewAI, Lyzr, GitHub Models, and other supported adapters, then automatically applies the correct settings for seamless execution without manual configuration.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
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
| Adapter | Flag | Env Var Required | Interactive
(truncated - see the full file via the links below)
File tree — 1 file
examples/gitagent-helper/skills/run-agent/SKILL.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Run or execute an agent with a specific LLM adapter or framework”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Translate agent configurations across multiple frameworks with a single command. Export to Claude Code, OpenAI, CrewAI, Lyzr, GitHub Models, and other formats, or import from existing Claude, Cursor, and CrewAI projects to standardize your automation setup.
This skill guides you through installing the gitagent CLI and creating your first agent from a template. You'll customize core files like agent.yaml and SOUL.md, validate your setup, and run your agent locally or from a git repository.
This skill tackles research by decomposing topics into 3-5 key subtopics, then gathering and reasoning through factual information for each. It synthesizes findings into a coherent summary while flagging areas of uncertainty or debate, and suggests related questions worth exploring next.
Packet Factory enforces a gatekeeper model where every task with side effects requires an APPROVED packet before running. Create packets in DRAFT status, review them for approval or rejection, then dispatch only approved work. Once approved, scope is locked to prevent creep—expansions spawn new packets instead.
Web Search taps into live web content to surface recent news, articles, and current data on any topic. It returns up to 5 results per query in a structured format with source URLs for easy citation, making it ideal when you need information beyond your existing knowledge base.
Build agents from scratch by generating agent.yaml configuration files, defining agent personality in SOUL.md, and organizing skills, tools, and knowledge directories. Includes templates for model settings, runtime constraints, and sub-agent delegation.
More skills paper-search (MIT) · regulatory-analysis (MIT) · document-review (MIT) · gmail-email (MIT) · knowledge-retrieval (MIT) · ollama (Apache-2.0) · Cli Anything (unlicensed) · anthropic-sdk-upgrader (MIT)