Borrowing it
Nothing to install: this file belongs to Netcracker/qubership-ai-packages. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Netcracker/qubership-ai-packages/main/.agents/skills/codex-review/SKILL.mdgit clone --depth 1 https://github.com/Netcracker/qubership-ai-packagesWrote 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/netcracker/qubership-ai-packages/codex-review)<a href="https://agentmods.dev/skills/netcracker/qubership-ai-packages/codex-review"><img src="https://agentmods.dev/badge/skills/netcracker/qubership-ai-packages/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/netcracker/qubership-ai-packages/codex-review"><img src="https://agentmods.dev/badge/skills/netcracker/qubership-ai-packages/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 | $0.00082 | $0.01274 |
| Opus 5 | $0.00041 | $0.00637 |
| Sonnet 5 | $0.00016 | $0.00255 |
| Haiku 4.5 | $0.00008 | $0.00127 |
Grade C, and why
codex-review scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$CODEX_REVIEW_DIR" How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex code review
Use the Codex CLI as a second reviewer: it reads a diff and reports findings, you decide which ones are real, fix those, and re-review until Codex comes back clean. The work that needs care is the judgement — classifying each finding and writing the fix — so the steps below are mostly about driving Codex and keeping a clear record of what was fixed and what was skipped.
Reply in the language the user writes in. Keep code identifiers, paths, and tool names as they are.
Prerequisites
The Codex CLI is installed and authenticated, with codex on
the PATH. If codex is missing, stop and report it — the rest of the skill depends on it.
Step 1. Pick the review target
Find out what to review. The target maps to one Codex scope flag:
--base <branch>— the diff against a branch (the common case).--uncommitted— the working-tree changes that are not yet committed.--commit <SHA>— one specific commit.
If the user already named a target, use it. Otherwise ask with AskUserQuestion. Hold the chosen
flag for the Codex calls below:
REVIEW_SCOPE="--base main" # or "--uncommitted", or "--commit <SHA>"
Step 2. Pick the review mode
Ask the user which mode to run (AskUserQuestion):
- Automatic — you classify every finding, then show a summary of what you will fix and what you will skip (with reasons) before touching any code.
- Interactive — for each finding, ask the user to fix it as suggested, skip it, or fix it a different way.
Step 3. Set up a scratch directory
Keep the intermediate files out of the repository so the review never shows up in the diff it is reviewing:
CODEX_REVIEW_DIR="$(mktemp -d "${TMPDIR:-${TEMP:-/tmp}}/codex-review-XXXXXX")"
echo "$CODEX_REVIEW_DIR"
Every later step reads and writes under $CODEX_REVIEW_DIR.
Step 4. Run the first review
codex exec review $REVIEW_SCOPE --json -o "$CODEX_REVIEW_DIR/review-output.md" 2>/dev/null
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 · 141 lines · 82 tokens per session scan C 2119ddab29ec
codex-review is a skill published in the GitHub repository Netcracker/qubership-ai-packages (4 stars, last pushed yesterday), licensed Apache-2.0. It adds 82 tokens to every session and 1,274 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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…