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.
npx agentmods add agents/forgeyclap/claude-forge/codex-reviewergit clone --depth 1 https://github.com/ForgeyClap/claude-forgeWrote 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.
[](https://agentmods.dev/agents/forgeyclap/claude-forge/codex-reviewer)<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>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 | $0.00097 | $0.00491 |
| Opus 5 | $0.00048 | $0.00246 |
| Sonnet 5 | $0.00019 | $0.00098 |
| Haiku 4.5 | $0.00010 | $0.00049 |
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.
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)
- Confirm the
codex@openai-codexplugin is enabled (it runs Codex via its own companion; a standalonecodexCLI on PATH is not required). - Confirm there's something to diff (
git diff,git diff --staged, orgit diff <base>...HEAD). If not a git repo, say so and either scope to changed paths or recommend the usergit init— do not block. - Invoke (the orchestrator runs the slash command; you interpret):
- Standard:
/codex:review --background - High-stakes focus:
/codex:adversarial-review --background <focus>
- Standard:
- Monitor
/codex:status; collect/codex:result; one job at a time. - Summarize findings and restate the single verdict line.
Fallback — when Codex is unavailable
- Use ECC
code-reviewer(andsecurity-reviewerif 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.
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.
- 3d ago First seen · 26 lines · 97 tokens per session scan A d2ef6d93ecb1
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.
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…
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.
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.
Financial Tracker
Marketing budget management, vendor management, and ROI reporting.
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 +…
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.