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 the selected gateway. Per-group via `ncl groups config update --provider codex`. Distinct from using OpenAI as an MCP tool (where Claude remains the planner).
81%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required runtime path feeds inbound group chat messages (the initial prompt and follow-ups pushed via `query.push`) straight into Codex `turn/start` and `turn/steer` without the agent selecting an item, so outsider-authored chat text reaches the model.
nanocoai/nanoclaw
dad1aad
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.