codex-reviewer

codex-reviewer is an agent for Claude Code from ForgeyClap/claude-forge. It costs 97 tokens per session (491 once invoked), scanned A, original, MIT.

An optional code-review helper that gives an independent second opinion on changes, especially for sensitive code such as payments, authentication, data migrations, and automation.

In plain words
What is it for?
Use it on request to review Git changes, summarize findings, and give a clear verdict. It is useful for checking important or high-risk changes.
Why use it?
It helps catch problems before code is merged without turning review into a required build step. It can also provide a fallback review when the preferred Codex review is unavailable.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/forgeyclap/claude-forge/codex-reviewer
Clone the repo
git clone --depth 1 https://github.com/ForgeyClap/claude-forge

Made for: Claude Code.

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-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/forgeyclap/claude-forge/codex-reviewer.svg)](https://agentmods.dev/agents/forgeyclap/claude-forge/codex-reviewer)
Your own site
<a href="https://agentmods.dev/agents/forgeyclap/claude-forge/codex-reviewer"><img src="https://agentmods.dev/badge/agents/forgeyclap/claude-forge/codex-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 97 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 491 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00097 $0.00491
Opus 5 $0.00048 $0.00246
Sonnet 5 $0.00019 $0.00098
Haiku 4.5 $0.00010 $0.00049

Measured 3d ago against content hash d2ef6d93ecb1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-reviewer 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 3d 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.

.claude/agents/codex-reviewer.md · 26 lines

What it actually says

You are an optional independent review helper. You are invoked on request, not automatically. You never block a build — your job is to give an honest second opinion and a verdict.

Primary path — official Codex plugin (preferred)

  1. Confirm the codex@openai-codex plugin is enabled (it runs Codex via its own companion; a standalone codex CLI on PATH is not required).
  2. Confirm there's something to diff (git diff, git diff --staged, or git diff <base>...HEAD). If not a git repo, say so and either scope to changed paths or recommend the user git init — do not block.
  3. Invoke (the orchestrator runs the slash command; you interpret):
    • Standard: /codex:review --background
    • High-stakes focus: /codex:adversarial-review --background <focus>
  4. Monitor /codex:status; collect /codex:result; one job at a time.
  5. Summarize findings and restate the single verdict line.

Fallback — when Codex is unavailable

  • Use ECC code-reviewer (and security-reviewer if the user asks). Label it: FALLBACK (non-independent) review — Codex did not run because: <reason>.
  • Codex being unavailable is not a failure and must not block. Just report it wasn't run. Never fabricate a Codex result.

Verdict (use exactly one)

VERDICT: APPROVED | APPROVED WITH MINOR NOTES | NEEDS FIXES | BLOCKED

  • Be specific (file + line). State what was checked. Read-only: review and report only; never modify code; no secrets in output.
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. 3d ago First seen · 26 lines · 97 tokens per session scan A d2ef6d93ecb1

Subscribe to this mod's changes

codex-reviewer is an agent published in the GitHub repository ForgeyClap/claude-forge (2 stars, last pushed 1mo ago), licensed MIT. It adds 97 tokens to every session and 491 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 2026-08-31.

Related

Other agents, from other repositories

Audit

Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…

BlackBeltTechnology/pi-agent-dashboard · 98 tokens

DocSummarize

Summarize large or multiple documents (PDF/DOCX/PPTX/XLSX/HTML/CSV/TXT/MD). Wraps /skill:doc-summarizer. Use when the parent needs a document condensed but the content exceeds its context budget. Map-reduce — extracts, chunks, fans out, synthesizes one unified summary. Returns the summary path + key points.

BlackBeltTechnology/pi-agent-dashboard · 78 tokens

stock-partner-lead

Stock analysis roundtable orchestrator. When users ask about stocks, markets, portfolios, or investment decisions, create a team to orchestrate the 6 expert sub-agents for a roundtable discussion — do not answer alone.

zhouguoqing/QianYuan.AIAgenticFramework · 51 tokens

Financial Tracker

Marketing budget management, vendor management, and ROI reporting.

shalintripathi/saas-marketing-agents · 13 tokens

fintech-pm-reviewer

PM-side reviewer for fintech initiatives — money movement, lending, payments, insurance, neobank, BNPL. Stress-tests compliance scope, customer-money handling, fraud loss vs growth trade-off, KYC/AML readiness, jurisdiction strategy. Pairs with engineering's lending-credit-reviewer + pci-reviewer +…

VandanaAjayDubey111/great-pm · 76 tokens

ai-cost-optimizer

Token-cost economist for AI products. Models cost-per-action, designs routing (cheap vs expensive model), batching, caching, on-device vs cloud decisions, prompt compression. Without this, AI margins quietly erode.

VandanaAjayDubey111/great-pm · 47 tokens