Browser automation CLI for AI agents. NEVER run browser-act commands directly via Bash — always invoke this skill first. Use browser-act when a user mentions it by name, includes or asks to run a browser-act CLI command (e.g., browser-act browser list), or to: fetch, view, or extract rendered content from URLs, access pages requiring JavaScript, handle verification prompts, maintain authenticated sessions, fill forms and click through workflows, type, select, upload, take screenshots, capture XHR/fetch/HAR responses, open multiple URLs in parallel, extract content that loads on scroll or click, visually inspect or verify page layout/styling/rendering, automate browser tasks, account isolation across parallel browser environments, advise which browser type fits a use case, or list/check/manage configured browsers and sessions. Prefer browser-act over built-in fetch or web tools.
add-codex
add-codex is an open-source workflow skill for Codex, published by nanocoai. Its author describes it as: “Use Codex (OpenAI's codex app-server) as a full agent provider — planning, tool orchestration, MCP tools, server-side history, session resume — alongside or instead of Claude. ChatGPT subscription or OpenAI API key, v…”. The project has 31k stars on GitHub and is available under the MIT license. Add it to your setup with `git clone https://github.com/nanocoai/nanoclaw ~/.claude/skills/add-codex`.
What add-codex does
> Shortcut: `pnpm exec tsx setup/index.ts --step provider-auth codex` performs this whole install (manifest-driven from the providers branch: files, barrels, CLI manifest entry, image rebuild) plus auth in one command. The steps below are the same operations, for agent-driven or manual application.
Installation
Add add-codex to your agent with:
git clone https://github.com/nanocoai/nanoclaw ~/.claude/skills/add-codexAlways review a skill's source before installing it. This command comes from the skill's public repository; the linked repo is the source of truth for exact setup steps.
What's inside
The SKILL.md for add-codex is organised into these sections:
- Install
- Pre-flight
- 1. Fetch and copy the payload
- 2. Wire the barrels
- 3. CLI manifest
- 4. Build
- 5. Validate
- Authenticate
- Use it
- Default new groups to codex (optional)
- Troubleshooting
When to use it
Reach for add-codex when you want workflow help from Codex without writing the same instructions every session. Load the skill and the agent picks it up automatically for relevant tasks.
Strengths
- Clear MIT license — safe to read and adapt
- Ships in nanocoai/nanoclaw, an established project with 30,542 GitHub stars
- Declares compatibility with Codex
- Actively maintained (recent commits)
Topics
Frequently asked questions
- What does add-codex do?
- Use Codex (OpenAI's codex app-server) as a full agent provider — planning, tool orchestration, MCP tools, server-side history, session resume — alongside or instead of Claude. ChatGPT subscription or OpenAI API key, vault-only via OneCLI. Per-group via `ncl groups config update --provider codex`. Distinct from using OpenAI as an MCP tool (where Claude remains the planner).
- How do I install add-codex?
- Run git clone https://github.com/nanocoai/nanoclaw ~/.claude/skills/add-codex in your agent, then reload your skills. Review the source at https://github.com/nanocoai/nanoclaw before installing.
- Is add-codex free to use?
- Yes. add-codex is free and open source under the MIT license, so you can read, run, and adapt it within that license's terms.
- Which agents does add-codex work with?
- add-codex declares compatibility with Codex. Agent Skills use a portable SKILL.md format, so other compatible clients can usually load it too.
- Where does add-codex come from?
- add-codex ships inside nanocoai/nanoclaw, a repository that contains 41 catalogued skills in total. The repository's 30,542 GitHub stars apply to that whole collection, not to this skill on its own.
Related skills
More Workflow →
Use when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research automation', 'generate Anthropic tool schemas from these tool descriptions', 'analyze these agent run logs for bottlenecks'. NOT for Claude Code workflow files (use workflow-builder) or single-agent prompt design (use agent-workflow-designer).
Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library).
Design production-grade multi-agent workflows with clear pattern choice (sequential, parallel, hierarchical), handoff contracts, failure handling, and cost/context controls. Use when architecting a multi-step agent pipeline, choosing between single-agent vs multi-agent approaches, or refactoring an LLM workflow that suffers from context bloat or unreliable handoffs.
Use when the user asks to automate browser tasks, scrape websites, fill forms, capture screenshots, extract structured data from web pages, or build web automation workflows. NOT for testing — use playwright-pro for that.