codex-review-full

codex-review-full is a skill for Codex from KamakuraCrypto/claude-codex-review. It costs 85 tokens per session (4,172 once invoked), scanned A, original, MIT.

A codebase-backed checker for reviewing a written software plan before implementation. It asks two Codex models to inspect the repository, run checks, and compare their conclusions.

In plain words
What is it for?
Use it to verify a detailed implementation plan against a repository, follow imports, run tests, and investigate scripts or expected behavior.
Why use it?
It catches incorrect assumptions about files, functions, libraries, tests, and side effects before coding begins. This helps avoid approving a plan that does not match the actual code.

Skill for Codex

Written for Codex: runs codex exec. Also seen: names the AskUserQuestion tool; mentions Codex.

Good fit Use it to verify a detailed implementation plan against a repository, follow imports, run tests, and investigate scripts or expected behavior.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kamakuracrypto/claude-codex-review/codex-review-full
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.

Any agent
npx skills add KamakuraCrypto/claude-codex-review --skill codex-review-full
Clone the repo
git clone --depth 1 https://github.com/KamakuraCrypto/claude-codex-review

Made for: Codex.

Wrote 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.

agentmods badge for codex-review-full

README.md
[![agentmods](https://agentmods.dev/badge/skills/kamakuracrypto/claude-codex-review/codex-review-full/github.svg)](https://agentmods.dev/skills/kamakuracrypto/claude-codex-review/codex-review-full)
Your own site
<a href="https://agentmods.dev/skills/kamakuracrypto/claude-codex-review/codex-review-full"><img src="https://agentmods.dev/badge/skills/kamakuracrypto/claude-codex-review/codex-review-full/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.

agentmods 80×15 button for codex-review-full

Your own site · 80×15
<a href="https://agentmods.dev/skills/kamakuracrypto/claude-codex-review/codex-review-full"><img src="https://agentmods.dev/badge/skills/kamakuracrypto/claude-codex-review/codex-review-full.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,172 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00085 $0.04172
Opus 5 $0.00043 $0.02086
Sonnet 5 $0.00017 $0.00834
Haiku 4.5 $0.00009 $0.00417

Measured 10d ago against content hash caa1cae9e19b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

codex-review-full 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 10d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (install.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

codex-review-full/SKILL.md · 245 lines

How it starts

The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.

codex-review-full

A deeper sibling of /codex-review. Same dual-codex premortem loop, same convergence machinery — but codex runs with full shell access (read anything, run tests, follow imports, exercise scripts) bounded by a strict prompt-level rule against destroying work. Use this when verification against the actual codebase matters more than speed or determinism.

Sibling skill: /codex-review does the same loop with codex pinned to --sandbox read-only and the plan piped via stdin. Use that one when speed, reproducibility, or working with sensitive files matters more than ground-truth verification. The skills are exclusive — pick one per review run.

When to use this

The trigger is a plan that makes specific, checkable claims about the codebase — function names, file paths, library versions, expected test behavior, side effects of touching X. If the user wants codex to actually verify those claims (not just reason about the plan in isolation), this is the skill.

Phrasings that should fire it: "have codex check this against the code", "verify the plan against the repo", "deep review", "full check", "/codex-review-full".

Phrasings that should fire /codex-review instead: "premortem this", "have codex check this", "/codex-review" — those are the plan-only flow. When in doubt, default to /codex-review for speed and switch to this skill on follow-up if the review missed something verifiable.

Out of scope: open-ended chat with codex, code generation, anything that isn't a plan review. See Escape hatches for those.

The default flow: dual premortem

The premise is that one model's verdict has blind spots. Two different models, run in parallel on the same input, surface a wider failure-mode set than either alone. The loop ends when both agree.

Step 1 — assemble the input bundle

Build a stdin payload containing:

  1. The premortem framing prompt (template below, including the SHELL ACCESS RULES block).
  2. The full plan text.
  3. Optionally, a few anchor files — the ones the plan references most heavily — inlined under === FILE: <path> === markers. This is a hint, not a constraint; codex is expected to fetch the rest from disk itself. Don't try to inline the whole project.

Read the full file on GitHub · 245 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 245 lines · 85 tokens per session scan A caa1cae9e19b

Subscribe to this mod's changes

codex-review-full is a skill published in the GitHub repository KamakuraCrypto/claude-codex-review (5 stars, last pushed 4mo ago), licensed MIT. It adds 85 tokens to every session and 4,172 once invoked, about $0.0004 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 2026-08-31.