codex-verify

A review workflow that sends a plan or document to Codex for an independent PASS or FAIL verdict, then checks the result.

In plain words
What is it for?
It is for double-checking plans and documents. It is not intended for code review or research.
Why use it?
It helps catch problems without forming an early opinion from reading the document first.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/leejuoh/claude-code-zero/codex-verify
Any agent
npx skills add LeeJuOh/claude-code-zero --skill codex-verify
Clone the repo
git clone --depth 1 https://github.com/LeeJuOh/claude-code-zero

Made for: Claude Code, Codex.

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,502 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00042 $0.03502
Opus 5 $0.00021 $0.01751
Sonnet 5 $0.00008 $0.00700
Haiku 4.5 $0.00004 $0.00350

Measured 2d ago against content hash de3ccfba0c34, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

plugins/codex-advisor/skills/codex-verify/SKILL.md · 363 lines

How it starts

The opening of the file, as written. The whole thing — 363 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 + double-checker. The user wants an independent review of a plan or document. Your job is to hand the document to Codex without ever loading it into your own context, so your follow-up evaluation is genuinely independent.

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 test -f/-s, wc -l/-c, file, echo, printf, cat "$DOC" >> "$PROMPT_FILE" (file-redirect, no stdout) cat "$DOC" to stdout, head, tail, Read, Grep, Glob
2 INVOKE Bash for companion launch via stdin pipe All source / document reads to stdout
3 WAIT status --wait loop (≤6 iterations, ≤24 min) All reads, manual polling, ps/kill
4 DOUBLE-CHECK Read the document (now — not before) to verify Codex's findings n/a
5 REPORT + SAVE Write report file n/a

Why the document stays out of context in Phase 1-3: if you read the document upfront, you form opinions before seeing Codex's. The double-check is then biased — you'll rationalize away valid catches. The blind-payload pattern (cat "$DOC" >> "$PROMPT_FILE") redirects to a file, not stdout, so your context stays clean.

Unknown flags silently become task prompt content (readTaskPrompt :613-619). Phase 1 is the only safety net.


Phase 1: Analyze + assemble blind payload

Parse $ARGUMENTS

Whitelist for this skill: --model <slug>, --effort <level> (skill-level, route through apply-codex-config.py — never reach the companion). The document path is another skill input, not a companion flag.

Rules:

  • A single path → treat as the document to verify.
  • resume [follow-up] → pass --resume-last to the companion; the follow-up becomes the new prompt body.
  • Multiple pathsAskUserQuestion which one.
  • Meta-instructions addressed to YOU (e.g. "evaluate in Korean", "be strict" — often typed in the user's own language) → obey for your own behavior, never include in the prompt.
  • No argsAskUserQuestion: "What document should I verify?"
  • Unknown flags (e.g., --base, --write, --foo) → AskUserQuestion. verify has no companion flags to forward. --model/--effort are skill-level and route through apply-codex-config.py.
  • --no-preview → skip Phase 1.5 draft review. Power users who trust the translation.

Read the full file on GitHub · 363 lines

Changes

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.

  1. 2d ago First seen · 363 lines · 42 tokens per session scan A de3ccfba0c34

Subscribe to this mod's changes

codex-verify is a skill published in the GitHub repository LeeJuOh/claude-code-zero (51 stars, last pushed 2d ago), licensed MIT. It adds 42 tokens to every session and 3,502 once invoked, about $0.0002 per session on Opus 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens