Skills for Real Engineers. Straight from my .agents directory.
codex-advisor
Agent skill fromfcakyon/claude-codex-settings
This skill should be used when the user asks for a "GPT second opinion", wants a "cross-model review", needs to "check a plan before committing", wants another view after repeated failures, or explicitly invokes "codex-advisor".
How to install codex-advisor
npx skills add fcakyon/claude-codex-settings# or add only this skill to Claude Code: copy the folder
plugins/codex-advisor/skills/codex-advisor/
# into
~/.claude/skills/codex-advisor/ (all projects)
.claude/skills/codex-advisor/ (one project)
1# Codex Advisor23Get a focused second opinion from GPT-6 Astra through the Codex CLI, without handing the4work over to it.56## Route by tool781. In Claude Code, delegate to the native `codex-advisor` agent. It receives the9 recent conversation automatically, so do not paste the history yourself.102. Elsewhere, run this exact shape from this skill's directory so the request11 reaches standard input:1213 ```14 node scripts/ask_codex.mjs <<'REVIEW'15 the review request16 REVIEW17 ```1819State the decision, the evidence behind it, and any constraint that changes the20verdict. Name the paths that matter: the reviewer has read-only access and21checks load-bearing claims itself.2223Return the answer without rewriting it. If `codex` is missing or unauthenticated,24surface the error and ask the user to install it or sign in. Never review in its25place.2627## Reviewer2829Pinned to `gpt-6-astra` at medium reasoning effort.3031## Weighing the answer3233Give the verdict serious weight. If a step it recommends fails when tried, or a34file contradicts a specific claim, surface the conflict instead of following the35review blindly.
Excerpt shown under the repository's Apache-2.0 license.
More skills in claude-codex-settings
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
