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 Snowtumb/Karen --skill codex-reviewgit clone --depth 1 https://github.com/Snowtumb/KarenWrote 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/snowtumb/karen/codex-review)<a href="https://agentmods.dev/skills/snowtumb/karen/codex-review"><img src="https://agentmods.dev/badge/skills/snowtumb/karen/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/snowtumb/karen/codex-review"><img src="https://agentmods.dev/badge/skills/snowtumb/karen/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 | $0.00118 | $0.02610 |
| Opus 5 | $0.00059 | $0.01305 |
| Sonnet 5 | $0.00024 | $0.00522 |
| Haiku 4.5 | $0.00012 | $0.00261 |
Grade A, and why
codex-review scanned grade A with 1 finding 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.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- No `--model` flag — uses the default model from `~/.codex/config.toml` Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Review Skill
Invoke OpenAI Codex CLI as a second-opinion bug reviewer. Codex analyzes the PR diff with full codebase read access, then Claude Code evaluates each finding, filters false positives, and auto-fixes confirmed bugs. A verification re-pass ensures fixes didn't introduce new issues.
This skill is rigid — follow the phases in order. Do not skip the evaluation phase.
Prerequisites Check
Before anything else, verify the environment:
# 1. Codex CLI installed?
which codex || echo "MISSING"
# 2. Auth configured?
codex login status 2>/dev/null || echo "NO_AUTH"
# 3. Changes exist?
git diff $(git merge-base main HEAD)...HEAD --stat
If Codex not installed:
Codex CLI is not installed. Install it with:
npm install -g @openai/codexThen authenticate with:codex login(browser) or setCODEX_API_KEYenv var.
If no auth:
Codex is not authenticated. Run
codex loginto authenticate via browser.
If no diff:
No changes found against the base branch. Nothing to review.
Stop and inform the user if any prerequisite fails. Do not proceed.
Phase 1: Gather Context
Prepare the inputs for Codex:
-
Detect base branch:
# If a PR exists, use its base BASE_BRANCH=$(gh pr view --json baseRefName -q '.baseRefName' 2>/dev/null || echo "main") -
Generate diff:
MERGE_BASE=$(git merge-base $BASE_BRANCH HEAD) git diff $MERGE_BASE...HEAD > /tmp/codex-review-diff.patch -
List changed files:
git diff --name-only $MERGE_BASE...HEAD -
Get PR info (if available):
PR_TITLE=$(gh pr view --json title -q '.title' 2>/dev/null || echo "N/A") PR_DESC=$(gh pr view --json body -q '.body' 2>/dev/null || echo "N/A") BRANCH_NAME=$(git branch --show-current) -
Write project context for Codex: Use your existing knowledge of this project from the conversation to write a rich context block. You already know this project — you've been reading files, writing code, and talking with the user. Include:
- What the project is — language, framework, key technologies, architecture
- What was built in this PR — what changed and why (you know this from the conversation)
- Key conventions — anything from CLAUDE.md or patterns you've observed (multi-tenant scoping, validation approach, error handling patterns, etc.)
- What Codex should watch for — based on the stack and conventions, note specific patterns relevant to this project
What ships with it
2 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 · 285 lines · 118 tokens per session scan A 4d8787007cbf
codex-review is a skill published in the GitHub repository Snowtumb/Karen (4 stars, last pushed 5mo ago), licensed MIT. It adds 118 tokens to every session and 2,610 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). 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…