Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/alanshurafa/co-evolutionnpx agentmods add skills/alanshurafa/co-evolution/codex-buildWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/alanshurafa/co-evolution/codex-build)<a href="https://agentmods.dev/skills/alanshurafa/co-evolution/codex-build"><img src="https://agentmods.dev/badge/skills/alanshurafa/co-evolution/codex-build/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/alanshurafa/co-evolution/codex-build"><img src="https://agentmods.dev/badge/skills/alanshurafa/co-evolution/codex-build.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00181 | $0.04597 |
| Opus 5.5 | $0.00072 | $0.01839 |
| Sonnet 5.5 | $0.00036 | $0.00919 |
| Haiku 4.5 | $0.00018 | $0.00460 |
Grade A, and why
codex-build scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/codex-build - Detached Codex Execution with Gate-Based Review
This is the orchestration protocol behind the "best Claude plans, Codex executes, best Claude reviews" model ladder. The session is the composer and the reviewer; Codex is the executor. The defining rule: the session is never kept busy while Codex grinds. You kick the runner as a background task, end your turn, and the harness wakes you when it exits.
Use /dev-review instead when you want the classic interactive
compose-bounce-execute loop in one session (you watch every pass). Use
/co-evolution for questions, drafts, plans, and document refinement with no
code execution.
The protocol has five steps. Steps 1-3 happen in the FIRST turn (preflight, plan, kick-and-stop). Steps 4-5 happen on WAKE, after the background task exits.
Step 1: PREFLIGHT (one turn, before planning)
Run these checks. Each gate either passes, degrades with a stated fallback, or dies with a fix hint.
Codex present
command -v codex
If missing, die with the install hint:
codex CLI not found. On this Mac with Codex.app installed:
ln -s "/Applications/Codex.app/Contents/Resources/codex" ~/.local/bin/codex
Otherwise install the CLI:
npm i -g @openai/codex
Then re-run /codex-build.
Claude CLI auth probe (decides the verifier seat)
The runner's claude verifier seat runs in a headless shell that does NOT carry
the interactive app's session token. Probe it:
claude -p --output-format text --model claude-haiku-4-5-20251001 "ping" 2>&1 | head -2
- If the output contains
Not logged in(or/login): the runner's claude verifier seat cannot run. DEGRADE — kick with--verifier codexso the verify phase uses Codex's schema-bound review instead. Tell the user plainly: the in-session review gate (Step 4, which YOU run) is then the only Claude-side review of the diff, and to runclaude /loginin a terminal to restore the full ladder (the claude verifier seat inside the runner). - Otherwise: the full ladder is available. Kick with the preset's default claude
verifier (best/Opus, max effort) — no
--verifieroverride needed.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed 10b83f03948c
- 1mo ago First seen · 411 lines · 181 tokens per session scan A 4c144b59202c
codex-build is a skill published in the GitHub repository alanshurafa/co-evolution (4 stars, last pushed 20d ago), licensed MIT. It adds 181 tokens to every session and 4,597 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
recursive-task-optimizer
Build, configure, run, inspect, or troubleshoot agent-agnostic recursive improvement loops for a repository or artifact. Use when a task should be attempted repeatedly by Claude Code, Codex CLI, Hermes, or another CLI agent; when candidates must inherit mutable task instructions, a self-improving meta-procedure, and…
template-skill
Replace with description of the skill and when Claude should use it.
github_read
Read access: repos, issues, PRs, files, branches, workflows, runs.
schedule_manage
Tool: schedulemanage. All ops use action field.
orch
AI agent orchestrator — manage teams of AI agents that work on your codebase in parallel. Use when the user wants to: run multiple agents, coordinate AI work, deploy agent teams, manage tasks/goals/agents, check orchestrator status, or mentions 'orch', 'orchestry', 'agents team', 'agent orchestration'.
bash
Skill "bash" from ParendumOU/Nexora, covering bash shell, available commands, usage and example.