codex-review-branch

codex-review-branch is a skill for Claude Code, Codex from sd0xdev/sd0x-harness. It costs 18 tokens per session (474 once invoked), scanned A, original, MIT.

An automated review of all changes on a feature branch, meaning a separate line of development, using Codex.

In plain words
What is it for?
Use it to review a whole branch against its base branch, with an optional second reviewer for releases, security-sensitive changes, or public interfaces.
Why use it?
It checks the complete branch before merging so problems across multiple commits are considered together.

Skill for Claude CodeCodex

Written for Claude Code and Codex: allowed-tools in frontmatter, but also runs codex exec. Also seen: mentions Codex.

Part of the sd0x-dev-flow plugin — 98 skills, 16 agents, 5 hooks shipped together

Good fit Use it to review a whole branch against its base branch, with an optional second reviewer for releases, security-sensitive changes, or public interfaces.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sd0xdev/sd0x-harness/codex-review-branch
Install

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.

Any agent
npx skills add sd0xdev/sd0x-harness --skill codex-review-branch
Clone the repo
git clone --depth 1 https://github.com/sd0xdev/sd0x-harness

Made for: Claude Code, Codex.

Or install sd0x-dev-flow, the plugin that ships this one along with the rest of its 98 skills, 16 agents, 5 hooks.

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-branch

README.md
[![agentmods](https://agentmods.dev/badge/skills/sd0xdev/sd0x-harness/codex-review-branch.svg)](https://agentmods.dev/skills/sd0xdev/sd0x-harness/codex-review-branch)
Your own site
<a href="https://agentmods.dev/skills/sd0xdev/sd0x-harness/codex-review-branch"><img src="https://agentmods.dev/badge/skills/sd0xdev/sd0x-harness/codex-review-branch.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 474 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 15
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
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 $0.00018 $0.00474
Opus 5 $0.00009 $0.00237
Sonnet 5 $0.00004 $0.00095
Haiku 4.5 $0.00002 $0.00047

Measured yesterday against content hash 17959facd22f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

codex-review-branch 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 yesterday.

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.

skills/codex-review-branch/SKILL.md · 44 lines

What it actually says

Codex Review Branch

Thin entry-point skill — routes to the parent skill for full workflow.

Parent Skill

This is the Branch variant of codex-code-review. Full workflow, prompt templates, and review logic are defined in the parent skill.

See @skills/codex-code-review/SKILL.md

Variant

Property Value
Scope Full branch (all commits since base)
Pre-checks None
Prompt template @skills/codex-code-review/references/codex-prompt-branch.md
Reviewers Codex alone. --dual adds a secondary reviewer — off unless the flag is passed
Tier thorough (this is the depth variant — P0/P1/P2 block, round cap 30)

Flags

Flag Default Effect
--dual off Adds a second reviewer in parallel (see parent skill Step 3). The merge happens in conversation — no state write, no mode field, and the next invocation starts single again unless the flag is passed again. A second opinion that can block this review's gate. Use for releases, security-sensitive changes, and public API surfaces.

--dual is the only code-review entry point where two reviewers run. /codex-review-fast and /codex-review-doc are single-reviewer by design and offer no such flag: the cost of the second opinion is only worth paying where the change warrants it, and this is that variant. /plan-review --dual is the plan-mode counterpart — same opt-in shape, same default of off, a different loop.

Trigger

  • Keywords: branch review, full branch, review branch, codex-review-branch

When NOT to Use

  • Quick diff-only review (use /codex-review-fast)
  • Full review with lint + build (use /codex-review)
  • Document review (use /codex-review-doc)
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. yesterday Changed 17959facd22f
  2. 2d ago Changed 5284e8291b3b
  3. 8d ago First seen · 44 lines · 18 tokens per session scan A 38a876b4e5e0

Subscribe to this mod's changes

codex-review-branch is a skill published in the GitHub repository sd0xdev/sd0x-harness (188 stars, last pushed 2d ago), licensed MIT. It adds 18 tokens to every session and 474 once invoked, about $0.0001 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 2026-08-30.

Related

Other skills, from other repositories

code-review

Two-mode skill: (1) adversarial review — spec compliance + code quality + security, confidence-scored findings with file:line evidence; (2) receiving review — verify-before- agreeing discipline for acting on external/human review feedback.

romiluz13/cc10x · 53 tokens

codebase-hygiene

Two-mode skill: (1) find semantic duplicates — functions doing the same thing under different names, invisible to copy-paste detectors; (2) deepen shallow modules — thin wrappers and pass-through layers that spread complexity. Advisory and read-only; changes route through BUILD with full gates.

romiluz13/cc10x · 67 tokens

evaluator-review-contract

Internal Auto-Harness evaluator skill for sprint contract review before implementation. Use only inside the Evaluator subagent during review mode.

redker56/auto-harness · 30 tokens

comet-verify

Comet Phase 4: Verify and Close. Invoke with /comet-verify. Verify implementation matches design, handle development branch.

rpamis/comet · 32 tokens

comet-review

A read-only review guide for checking the current Comet change, a managed software-change workflow. It focuses on correctness, security, and boundary problems without changing files or advancing the workflow.

rpamis/comet · 30 tokens

comet-github-pr-review

A read-only review process for pull requests in Comet's GitHub repositories. A pull request is a proposed code change; the review checks its current code, related issue, comments, merge status, and automated checks.

rpamis/comet · 69 tokens