codex-review-gate

codex-review-gate is a skill for Claude Code from verivus-oss/llm-cli-gateway. It costs 51 tokens per session (1,889 once invoked), scanned A, original, MIT.

A review process that sends finished coding work to Codex, OpenAI's coding agent, through a local gateway for a final decision. It requires a clear approval, a request for changes, or a statement that outside conditions prevent review.

In plain words
What is it for?
Use it after implementation and local tests, before merging code, or whenever a project requires Codex to sign off.
Why use it?
It gives completed work an evidence-based review before it is merged, instead of relying only on the original agent's checks.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex.

Part of the llm-gateway plugin — 24 skills, 4 commands, 2 MCP servers shipped together

Good fit Use it after implementation and local tests, before merging code, or whenever a project requires Codex to sign off.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/verivus-oss/llm-cli-gateway/codex-review-gate
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 verivus-oss/llm-cli-gateway --skill codex-review-gate
Clone the repo
git clone --depth 1 https://github.com/verivus-oss/llm-cli-gateway

Made for: Claude Code.

Or install llm-gateway, the plugin that ships this one along with the rest of its 24 skills, 4 commands, 2 MCP servers.

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-gate

README.md
[![agentmods](https://agentmods.dev/badge/skills/verivus-oss/llm-cli-gateway/codex-review-gate/github.svg)](https://agentmods.dev/skills/verivus-oss/llm-cli-gateway/codex-review-gate)
Your own site
<a href="https://agentmods.dev/skills/verivus-oss/llm-cli-gateway/codex-review-gate"><img src="https://agentmods.dev/badge/skills/verivus-oss/llm-cli-gateway/codex-review-gate/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-gate

Your own site · 80×15
<a href="https://agentmods.dev/skills/verivus-oss/llm-cli-gateway/codex-review-gate"><img src="https://agentmods.dev/badge/skills/verivus-oss/llm-cli-gateway/codex-review-gate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,889 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 pass 7 Sept 2026
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 $0.00051 $0.01889
Opus 5 $0.00026 $0.00945
Sonnet 5 $0.00010 $0.00378
Haiku 4.5 $0.00005 $0.00189

Measured 9d ago against content hash 315546eed1be, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

codex-review-gate 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 9d 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.

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-gate/SKILL.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Review Gate

Use this gate after implementation and local verification. Dispatch reviews only through the local gtwy stdio MCP server, never through a direct codex CLI command. In Codex the gateway tools normally have names such as mcp__gtwy__codex_request and mcp__gtwy__codex_request_async; some clients show their short names instead.

Non-Negotiable Review Rules

  1. Omit model unless the user selected one.
  2. Pass approvalStrategy: "legacy". Codex cannot use mcp_managed, and approvalPolicy has no effect for it.
  3. Use sandboxMode: "read-only" for an inspection-only review. Use sandboxMode: "workspace-write" only when the reviewer needs to create build or test artifacts. Do not use fullAuto; it is deprecated shorthand for workspace-write.
  4. Require this exact terminal JSON verdict: APPROVED_UNCONDITIONALLY, CHANGES_REQUIRED, or BLOCKED_EXTERNAL.
  5. Do not impose a review-round, turn, token, price, cost, or wallclock cap. Do not use a provider equivalent of those controls to shorten a mandatory review. The configured idle-timeout safeguard only detects a process that stops producing output.
  6. Accept only explicit, evidence-backed APPROVED_UNCONDITIONALLY. Conditional approval, residual findings, a malformed verdict, inability to verify, cancellation, timeout, or provider error does not pass the gate.

Keep fixing and re-reviewing until the required verdict arrives. Stop only on explicit user cancellation or a terminal external provider failure. A terminal failure is BLOCKED_EXTERNAL with its exact error, never permission to skip the gate.

Explicit user-authorized full-access override

The normal safe posture above does not apply when the user explicitly grants full provider permissions and native MCP access for this review. Build the target checkout and start node dist/index.js --transport=stdio from that checkout. Do not call a global or stale gtwy process. On a fresh Codex session use approvalStrategy:"legacy", sandboxMode:"danger-full-access", and dangerouslyBypassApprovalsAndSandbox:true.

Read the full file on GitHub · 178 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. 9d ago First seen · 178 lines · 51 tokens per session scan A 315546eed1be

Subscribe to this mod's changes

codex-review-gate is a skill published in the GitHub repository verivus-oss/llm-cli-gateway (15 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 1,889 once invoked, about $0.0003 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.