qubership-ai-packages: Skill for Codex

.agents/skills/codex-review/SKILL.md

codex-review is a skill for Codex from Netcracker/qubership-ai-packages. It costs 82 tokens per session (1,274 once invoked), scanned C, original, Apache-2.0.

A process for using the Codex command-line tool as a second reviewer, then checking its findings, fixing real issues, and reviewing again.

In plain words
What is it for?
Use it to review a branch diff, uncommitted changes, or a specific commit, apply valid fixes, and repeat the review until no real findings remain.
Why use it?
It adds an independent review pass while leaving the final judgment about false positives and fixes with the developer.

Skill for Codex

Written for Codex: runs codex exec. Also seen: names the AskUserQuestion tool; installed under .agents/ (shared by several agents); mentions Codex.

This is Netcracker/qubership-ai-packages's own configuration. It tells Codex how to work on qubership-ai-packages itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything qubership-ai-packages configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/Netcracker/qubership-ai-packages/main/.agents/skills/codex-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Netcracker/qubership-ai-packages

Made for: Codex.

Wrote 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.

agentmods badge for codex-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/netcracker/qubership-ai-packages/codex-review/github.svg)](https://agentmods.dev/skills/netcracker/qubership-ai-packages/codex-review)
Your own site
<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.

agentmods 80×15 button for codex-review

Your own site · 80×15
<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>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,274 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 10d ago against content hash 2119ddab29ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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"
.agents/skills/codex-review/SKILL.md · 141 lines

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

Read the full file on GitHub · 141 lines

Changes

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.

  1. 10d ago First seen · 141 lines · 82 tokens per session scan C 2119ddab29ec

Subscribe to this mod's changes

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.