What is codex-review?

A Herdr skill that starts an independent Codex reviewer to examine changes, commits, files, or plans in read-only mode. Codex is an AI coding assistant, and Herdr is used here to coordinate that separate review session.

Use it when an Agent inside Herdr explicitly needs Codex to review a code change, commit, selected files, or an implementation plan.

It provides an independent review without allowing the reviewer to modify files or silently switch to a different collaboration method. The calling agent still checks the returned findings.

codex-review — Skill for Claude Code and Codex by bahayonghang

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 bahayonghang/my-ai-cli-toolkit --skill codex-review

Clone the repo

git clone --depth 1 https://github.com/bahayonghang/my-ai-cli-toolkit

Made for: Claude Code, 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/bahayonghang/my-ai-cli-toolkit/codex-review/github.svg)](https://agentmods.dev/skills/bahayonghang/my-ai-cli-toolkit/codex-review)

Your own site

<a href="https://agentmods.dev/skills/bahayonghang/my-ai-cli-toolkit/codex-review"><img src="https://agentmods.dev/badge/skills/bahayonghang/my-ai-cli-toolkit/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/bahayonghang/my-ai-cli-toolkit/codex-review"><img src="https://agentmods.dev/badge/skills/bahayonghang/my-ai-cli-toolkit/codex-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 999 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00097	$0.00999
Opus 5	$0.00048	$0.00500
Sonnet 5	$0.00019	$0.00200
Haiku 4.5	$0.00010	$0.00100

Measured today against content hash aab7b98ce667, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

codex-review 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 today.

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/development-workflows/codex-review/SKILL.md · 37 lines

What it actually says

Codex Review

在 Herdr 中发起一个独立、只读的 Codex reviewer，由调用者核验可定位的审查结论。

Router Rules

仅在明确要求 Herdr + Codex 审查，或本技能调用已有该任务上下文时使用。普通正确性审查交给现有 review 流程；可维护性问题沿用 code-quality-review；非 Herdr 的 Codex 协作不要走本技能。
若已被分配为 leaf reviewer，直接完成审查，不调用本技能、orchestra 或更多 Agent。讨论/研究这些技能不授权启动进程。
通过已加载的 herdr-orchestra 名称/实际路径读取其 references/delegation.md；它是唯一进程控制 owner。本包不分配 pane、不重复环境探测、不直接启动 Codex。缺少依赖时报告源路径 skills/developer-tools-integrations/herdr-orchestra/ 与未完成项，不绕过 Herdr。
核对当前加载的本包身份；同名第三方入口不等于此源。若仍加载含自动 CHANGELOG 的旧入口，报告不匹配，不修改安装、全局配置或 hooks。宿主加载边界见仓库 docs/harnesses.md。

Compact Workflow

按审查契约明确 cwd、用户标准与一个审查范围，捕获 HEAD/ref、diff 和相关输入内容。当前全部改动默认含 staged、unstaged、untracked；用户指定 staged-only 时保留该边界。
准备六字段文本 handoff 与完整 leaf prompt。以 Codex CLI 边界的交互 root 参数 --sandbox read-only --ask-for-approval never --no-alt-screen 请求一个新 kind=codex worker；实际执行时核验当前 help。用户指定模型则保留，否则继承配置。
交给 orchestra 一次派发与收集。prompt 是任务文本，不是 shell 命令或 /review UI 操作；启动失败不得切换到 exec review 或另一 reviewer。
对 receipt 核对身份、目标、生命周期与完整响应。截断时仅由 orchestra 向同一 ready worker 请求缺失的小段；只读 reviewer 不写 temp file、不扩大 sandbox。恢复未完成就保持 incomplete。
接受前复核输入与 finding anchors。目标变化则标记 scope drift；完整且范围一致才核验结论。输出已接受发现、被排除的重要误报与不确定性，不自动修复或递归复审。

Output Contract

返回实际 reviewed cwd/scope/input identity、worker identity/lifecycle、响应覆盖与完整性，以及调用者的范围复核结果。
发现按优先级列出路径/行、触发场景、影响、证据和验证缺口。证据不足归入 uncertainty；无可行动发现必须有完整审查依据。
将通过、失败、未运行检查与 missing evidence 分开。blocked、timeout、unknown、空响应、缺段和 scope drift 不得写成通过；遗留 worker 资源状态来自 orchestra receipt。
仅在调用者已有产物写权限内保存已捕获文本；不把审查授权扩展为修复、CHANGELOG、Git 写操作、安装、trust/config/hooks 变更或资源清理。

包内资源以本技能加载时公布的实际目录解析；<skill-dir> 表示该目录，不假定安装目录之间的相对位置。行为 fixtures 见 evals，独立词法输入见 trigger cases。创建交接汇总来源、实际检查和未验证边界；这些材料不证明新会话已加载本包。

Files

What ships with it

10 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.

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.

today Changed aab7b98ce667
2d ago First seen · 37 lines · 97 tokens per session scan A 830e4b03033e

Subscribe to this mod's changes

codex-review is a skill published in the GitHub repository bahayonghang/my-ai-cli-toolkit (16 stars, last pushed today), licensed MIT. It adds 97 tokens to every session and 999 once invoked, about $0.0005 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 2026-09-09.

Building agents Code review codex delegation development-workflows herdr read-only review

claude_code_delegation

Delegate coding, review, and refactor tasks to Claude Code CLI through Row-Bot's approval-gated shell workflow.

siddsachar/row-bot · 31 tokens

agent-review

Critically review a Stencila agent and suggest improvements. Use when asked to review, audit, critique, evaluate, or improve an agent directory or AGENT.md file. Covers frontmatter validation, system instruction quality, configuration correctness, and adherence to the Agent schema.

stencila/stencila · 57 tokens

review-work

Quality gate: verify each acceptance criterion of a completed task/work unit, run quality checks, and create follow-up tasks for gaps. Use before merging or to audit delivered work. Invoked as /agiflow:review-work . Uses getworkunit, gettask, updatetask, createtask, createtaskcomment.

hashgraph-online/awesome-codex-plugins · 72 tokens

codex-review