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 LaStrada/claude --skill review-with-codexgit clone --depth 1 https://github.com/LaStrada/claudeWrote 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/lastrada/claude/review-with-codex)<a href="https://agentmods.dev/skills/lastrada/claude/review-with-codex"><img src="https://agentmods.dev/badge/skills/lastrada/claude/review-with-codex.svg" alt="Measured on agentmods" 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 | $0.00177 | $0.01060 |
| Opus 5 | $0.00088 | $0.00530 |
| Sonnet 5 | $0.00035 | $0.00212 |
| Haiku 4.5 | $0.00018 | $0.00106 |
Grade A, and why
review-with-codex 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 8d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
review-with-codex
Send a diff to OpenAI's Codex CLI for a second-opinion review, then relay findings.
Non-negotiable rules
- Public repos only. Run the gate (below) before anything. Any result other than
PUBLICis a hard refusal — no overrides, no "just this once." - Read-only sandbox. Always pass
-s read-onlytocodex exec. Never--full-auto,--sandbox workspace-write, or--dangerously-bypass-approvals-and-sandbox. - Confirm upload first. On the first call in a session, tell the user what will be sent (branch, file count, +X/-Y) and wait for confirmation.
- Relay, don't agree. Present as "Codex says:" with a one-line triage (genuine / off / needs-verify) after. The user decides.
- Non-interactive only.
codex execorcodex review. Never start an interactive session. - Refuse on sensitive paths even in a public repo. If the diff touches
secrets.properties,.env,*.p12,*.keystore,GoogleService-Info.plist,google-services.json, or anything matching*secret*/*credential*/*token*— refuse and warn. Their presence in a public repo is itself a problem.
Public-repo gate
Run this first, fail closed on any error:
VISIBILITY=$(gh repo view --json visibility --jq .visibility 2>&1) || VISIBILITY="ERROR: $VISIBILITY"
Accept exact PUBLIC only. Anything else (PRIVATE, INTERNAL, ERROR: …, empty) → refuse:
I can't run Codex on this repo — the public-repo gate failed (
<result>). Codex uploads the diff to OpenAI, and per your standing rule this skill only runs on public GitHub repos. Tryreview-with-geminiorreview/code-reviewinstead.
Default invocation
BRANCH=$(git rev-parse --abbrev-ref HEAD)
BASE=$(git remote show origin 2>/dev/null | awk '/HEAD branch/ {print $NF}')
BASE_SHA=$(git merge-base "$BASE" HEAD)
git diff --stat "$BASE_SHA..HEAD"
Tell the user: N files changed, +X/-Y lines. Branch <branch> vs <base>. OK to send to Codex?
Then:
codex exec -s read-only "Review the changes in this branch vs $BASE_SHA.
Focus on:
- Correctness bugs and logic errors
- Race conditions / concurrency issues
- Silent failures / swallowed errors
- Missing edge cases
- API misuse
Do NOT comment on formatting/naming/comments unless something is actually wrong.
Be terse. 'bug:' for confident, 'might:' for speculative. Under 500 words." 2>&1 | tail -200
What ships with it
4 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.
- 8d ago First seen · 80 lines · 177 tokens per session scan A e32a0edba4e9
review-with-codex is a skill published in the GitHub repository LaStrada/claude (2 stars, last pushed 2mo ago), licensed MIT. It adds 177 tokens to every session and 1,060 once invoked, about $0.0009 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.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
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.
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…