Codex
Delegate a task or question to the OpenAI Codex CLI running as an isolated subagent, then relay its answer. Use when the user invokes /codex <prompt>, says "ask codex", "have codex look at / do X", or wants a second independent model to investigate a question or make a self-contained edit. Read-only by default; /codex --write lets Codex edit the working tree. Distinct from /codex-review, which is the structured JSON review gate — /codex is a general-purpose Codex delegate.
Install
npx skills add iamneilroberts/claude-skills --skill codexgit clone --depth 1 https://github.com/iamneilroberts/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/skills/codex ~/.claude/skills/codexPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# /codex — delegate to the Codex CLI via a subagent Runs the OpenAI Codex CLI (`codex exec`) on the user's prompt inside a **dispatched subagent**, so Codex's (possibly large) output stays out of the main context and you relay only its answer. Codex is a genuinely independent model — good for a second opinion, an adversarial read, or offloading a self-contained investigation or edit. Helper: `codex.sh` (this skill's dir) runs `codex exec`, captures only Codex's final message (`-o`), and falls back across models on failure. ## When to use - `/codex <prompt>` — hand any question or task to Codex against this repo. - "ask codex to …", "have codex look at …", "get codex to write / refactor …". - NOT the structured review gate — that's `/codex-review`. ## How to run 1. **Parse the invocation.** Everything after `/codex` is the PROMPT. Flags: - `--write` → Codex may edit the working tree (workspace-write sandbox). Default is read-only. - `-m <model>` → pin a Codex model. `--dir <path>` → working root (default: repo root). 2. **Dispatch ONE subagent** (Agent tool, `subagent_type: general-purpose`). Pin the model explicitly: `haiku` for a plain ask/relay; `sonnet` if Codex is making edits and you want the result sanity-checked. Give it this task (substitute `<SKILL_DIR>` = this skill's base directory, and `<PROMPT>`): > Run the Codex CLI and return its final answer VERBATIM — trim only banner/progress > noise, do not summarize or editorialize. Run:
Details
- Skill name
codex- Repository
- iamneilroberts/claude-skills
- Path
skills/codex/SKILL.md- Repo updated
- 21 August 2026
FAQ
What does the Codex skill do?
Delegate a task or question to the OpenAI Codex CLI running as an isolated subagent, then relay its answer. Use when the user invokes /codex <prompt>, says "ask codex", "have codex look at / do X", or wants a second independent model to investigate a question or make a self-contained edit. Read-only by default; /codex --write lets Codex edit the working tree. Distinct from /codex-review, which is the structured JSON review gate — /codex is a general-purpose Codex delegate.
How do I install the Codex skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add iamneilroberts/claude-skills --skill codex. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Codex popular?
It lives in iamneilroberts/claude-skills, which has 37 GitHub stars and 7 forks.
Related skills
Brag
37iamneilroberts/claude-skills
Memorialize something you just built by generating a self-contained "showcase" page for it — a persuasive, good-looking deep dive: what it is, why it's impressive, how it works — with a screenshot if one can be found or captured, and links to related showcase pages. This is the sales/hype-leaning counterpart to /write-post (which drafts a neutral, no-BS technical post); reach for /brag when you want it to sell. Fast by design, like /idea: ask only what's needed, build the page, don't turn it into a project. Triggers on `/brag <subject>`, "brag about this", "make a showcase page for X", "write
Branch
37iamneilroberts/claude-skills
Create an isolated git worktree for a task and log it to a shared work journal, so multiple Claude Code sessions run in parallel without racing on HEAD, uncommitted edits, or the index. Subcommands: `list`, `done <slug>`, `update` (heartbeat), `coord <message>` / `coord clear <slug>` (cross-session constraints). Triggers on `/branch`, "start in a worktree", "isolate this work", "parallel session", "heartbeat the journal".
Claude Code Best Practices
37iamneilroberts/claude-skills
Use when asked about Claude Code workflow, prompt caching cost, session economics, CLAUDE.md hygiene, context-window management, plan mode, permission modes, hooks, skills, subagents, checkpointing/rewind, parallel sessions, worktrees, headless/CI usage, the Agent SDK, slash commands, MCP configuration, or "what's the right way to use Claude Code for X". Also use proactively BEFORE suggesting /model, /compact, fast-mode toggle, or editing CLAUDE.md mid-session, since those bust the system cache.
Codex Review
37iamneilroberts/claude-skills
Get a second opinion on the current change or a plan from a different model (Codex), and enforce its verdict mechanically. Codex returns a structured JSON verdict — findings scored by priority (0 critical, 1 important, 2 minor, 3 nit) against sev.schema.json — and a gate script turns that into a pass/fail exit code, so a critical or important finding gets fixed or escalated rather than re-argued by the model that wrote the code. Infra failures (rate limit, model reject, empty output) are their own outcome and never count as a clean pass. Use after writing tests, before a deploy or merge, or to
Backend Patterns
32joneqian/claude-skills-suite
Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, NestJS, FastAPI, and Next.js API routes.
Comment Refactor
37iamneilroberts/claude-skills
Refactor the comments in AI-generated (or long-lived) code — strip the accumulation of fix-history narration, obsolete explanations, and code-restating noise while preserving load-bearing WHY/TODO/warning comments. Works over a path, glob, or the whole repo; skips dead/abandoned/unused and vendored/generated files; and stamps each cleaned file with a content-hash marker so re-runs skip files that haven't changed. Incorporates the /remove-comments and /deslop (humanizer) heuristics plus a used-code filter and incremental idempotency. Triggers on `/comment-refactor [path|glob]`, "refactor the co
Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.