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.
npx skills add KamakuraCrypto/claude-codex-review --skill codex-review-fullgit clone --depth 1 https://github.com/KamakuraCrypto/claude-codex-reviewWrote 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/kamakuracrypto/claude-codex-review/codex-review-full)<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.
<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>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 | $0.00085 | $0.04172 |
| Opus 5 | $0.00043 | $0.02086 |
| Sonnet 5 | $0.00017 | $0.00834 |
| Haiku 4.5 | $0.00009 | $0.00417 |
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.
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 — 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-reviewdoes the same loop with codex pinned to--sandbox read-onlyand 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:
- The premortem framing prompt (template below, including the
SHELL ACCESS RULESblock). - The full plan text.
- 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.
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.
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.
- 10d ago First seen · 245 lines · 85 tokens per session scan A caa1cae9e19b
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…