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 shaharsha/claude-skills --skill codex-reviewgit clone --depth 1 https://github.com/shaharsha/claude-skillsWrote 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/shaharsha/claude-skills/codex-review)<a href="https://agentmods.dev/skills/shaharsha/claude-skills/codex-review"><img src="https://agentmods.dev/badge/skills/shaharsha/claude-skills/codex-review/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/shaharsha/claude-skills/codex-review"><img src="https://agentmods.dev/badge/skills/shaharsha/claude-skills/codex-review.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 | $0.00113 | $0.08045 |
| Opus 5 | $0.00056 | $0.04022 |
| Sonnet 5 | $0.00023 | $0.01609 |
| Haiku 4.5 | $0.00011 | $0.00805 |
Grade B, and why
codex-review scanned grade B with 2 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 12d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`sandbox_mode = "danger-full-access"` in `~/.codex/config.toml` is common and Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| Raw network — `curl`, `urllib`, `ping` | ❌ DNS resolution fails | How it starts
The opening of the file, as written. The whole thing — 578 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex review
Hand the work to a different model, in a clean context, with no write access, and get back a list of claims. Then check each claim against the source and decide which ones are real.
The second half is not optional. Codex produces claims, not verdicts — some are defects you missed, some are confident nonsense, and telling them apart by reading the actual code is the entire value of the exercise. A review relayed without adjudication is worse than no review, because it launders a guess into an authority.
When this is worth it
Worth it: a plan about to be implemented, a change about to be merged, anything touching money, auth, migrations, concurrency, permissions, or deletion, and anything where you notice you're reasoning about your own work in a way that feels a bit too comfortable.
Not worth it: work in flight and about to change again, a one-line fix, a change the test suite already covers, or exploration. A review costs a few minutes of wall clock and its output needs adjudicating — spend it where being wrong is expensive.
Pick the mode
| Situation | Mode | What Codex compares against |
|---|---|---|
| Plan or design doc, not yet implemented | plan |
the repository it will land in |
| Change written, ready to commit or merge | code |
the intent and constraints you give it |
| Change written from a plan | code-vs-plan |
the plan, requirement by requirement |
It is not only for code. The three modes name code because that is the common case, but nothing in the mechanism cares: any artifact you can render as text can be reviewed this way. Measured 2026-08-18 on a spreadsheet and a 40-document evidence set, where it found a hardcoded summary row that had silently drifted away from the live formulas feeding it.
Two things make that work, and both generalise:
- Hand it the outputs as well as the source. The reviewer cannot execute anything, so a formula, a template or a query is opaque to it. Give it both representations — the formulas and the evaluated values, the template and the rendered result — and it can compare them. That comparison is what catches drift; neither representation alone would have.
- Pre-extract anything binary. Read-only blocks the reviewer from running
pdftotextor an OCR pass itself, so do it first and stage the text beside the originals. Say in the prompt which files are extracted text and how reliable the extraction is, or it will treat OCR noise as evidence.
What ships with it
7 files 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.
- 12d ago First seen · 578 lines · 113 tokens per session scan B e93cc58406cd
codex-review is a skill published in the GitHub repository shaharsha/claude-skills (5 stars, last pushed 14d ago), licensed MIT. It adds 113 tokens to every session and 8,045 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). 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…