Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add LeeJuOh/claude-code-zero/plugin install codex-advisorWrote 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/leejuoh/claude-code-zero/codex-verify)<a href="https://agentmods.dev/skills/leejuoh/claude-code-zero/codex-verify"><img src="https://agentmods.dev/badge/skills/leejuoh/claude-code-zero/codex-verify/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/leejuoh/claude-code-zero/codex-verify"><img src="https://agentmods.dev/badge/skills/leejuoh/claude-code-zero/codex-verify.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 | $0.00042 | $0.04331 |
| Opus 5.5 | $0.00017 | $0.01732 |
| Sonnet 5.5 | $0.00008 | $0.00866 |
| Haiku 4.5 | $0.00004 | $0.00433 |
Grade A, and why
codex-verify scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 396 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Document Verification + Double-Check
You are a translator + executor. The user wants an independent review of a plan or document. Your first job is to hand the document to Codex without ever loading it into your own context. Your second job is to hand what Codex returns to a fresh Verifier subagent and report the verdict it reaches. The judging is deliberately not yours — if you drafted the document in this session, a blind payload cannot erase that memory, and a fresh reader has no such stake (ADR 0012).
For code review use /codex-review. For research use /codex-research.
Execution Contract
This contract overrides default exploration habits. Read it before Phase 1.
| Phase | Allowed | Forbidden |
|---|---|---|
| 1 ANALYZE | codex-task.sh check-doc, new-run, prompt (the document goes in by file redirect, never to stdout), apply-codex-config.py |
cat "$DOC" to stdout, head, tail, Read, Grep, Glob |
| 2 INVOKE | codex-task.sh launch (prompt via stdin pipe) |
All source / document reads to stdout |
| 3 WAIT | codex-task.sh wait loop (≤6 calls, ≤24 min), result written to a file |
All reads, manual polling, ps/kill |
| 4 VERIFY | codex-task.sh payload --mode doc, then Agent (codex-advisor:verifier) |
Reading the document or the Codex result; judging any finding yourself |
| 5 REPORT + SAVE | codex-report.sh save, codex-report.sh clean |
Write tool for the report |
Why the document stays out of context: the Verifier judges against the
document, and it can only do that honestly if it comes to the document fresh.
Your copy would add nothing and cost the independence. codex-task.sh prompt --document appends the document to the prompt file by redirect, not to stdout,
so your context stays clean; Phase 4 passes paths, not text, for the same reason.
codex-task.sh launch refuses any argument that is not a known task flag, so a stray word stops the launch instead of landing in the prompt. Phase 1 still decides what is a flag and what is document text.
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.
- 9d ago Changed · -50 lines f20ac10a0fd2
- 22d ago Changed · +2 lines d942b8be1866
- 26d ago Changed · +81 lines c106a3eb508a
- 1mo ago First seen · 363 lines · 42 tokens per session scan A de3ccfba0c34
codex-verify is a skill published in the GitHub repository LeeJuOh/claude-code-zero (52 stars, last pushed 3d ago), licensed MIT. It adds 42 tokens to every session and 4,331 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
cpp-coding-standards
C++ coding standards based on the C++ Core Guidelines (isocpp.github.io). Use when writing, reviewing, or refactoring C++ code to enforce modern, safe, and idiomatic practices.
simplify-code
Parallel 4-agent cleanup of recent code changes.
coding-standards
Baseline cross-project coding conventions for naming, readability, immutability, and code-quality review. Use detailed frontend or backend skills for framework-specific patterns. Use when reviewing code quality or naming with no framework-specific skill that applies.
pr-lens
Draw code changes as animated architecture/data-flow SVGs.
opencode
Delegate coding to OpenCode CLI (features, PR review).
requesting-code-review
Pre-commit review: security scan, quality gates, auto-fix.