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 skills add ZachArticulateV/designer-pro-and-seo --skill route-codex-reviewgit clone --depth 1 https://github.com/ZachArticulateV/designer-pro-and-seoWrote 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/skills/zacharticulatev/designer-pro-and-seo/route-codex-review)<a href="https://agentmods.dev/skills/zacharticulatev/designer-pro-and-seo/route-codex-review"><img src="https://agentmods.dev/badge/skills/zacharticulatev/designer-pro-and-seo/route-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.
<a href="https://agentmods.dev/skills/zacharticulatev/designer-pro-and-seo/route-codex-review"><img src="https://agentmods.dev/badge/skills/zacharticulatev/designer-pro-and-seo/route-codex-review.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00093 | $0.00699 |
| Opus 5 | $0.00046 | $0.00349 |
| Sonnet 5 | $0.00019 | $0.00140 |
| Haiku 4.5 | $0.00009 | $0.00070 |
Grade A, and why
route-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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
route-codex-review
Family: routing Status: Stable
Purpose
The execution arm of the no-self-review rule. Hands Claude's output to Codex for an independent, adversarial pass — bugs, security risks, missing edge cases/tests, broken invariants, unclear logic. Mandatory for substantial output heading to a client or production, or whenever the user asks to verify Claude's work.
Triggers
- "review the code you wrote" / "review what you just did"
- "check your work" / "look over what you wrote" / "give it a once-over"
- "second opinion" / "sanity-check what you wrote" / "double-check this"
- "adversarial review" / "have codex review" / "is this right"
Scoped to Claude's own output. Bare "audit this" / "audit my site" belongs to the SEO/QA families, not here (see
references/ENGINE-CONTRACTS.md§3).
Inputs
- The output to review (diff, files, content, or plan)
- Review focus (bugs / security / correctness / completeness / all)
Steps
- Check Codex is available:
codex --version. If absent, tell the user it's off until installed and offer a structured manual review from a different lens (never a same-model self-review). - Bundle the context — the diff or the specific files, plus what was tried and the relevant constraints.
- Invoke Codex:
For untracked code, pipe the file(s) instead ofgit diff | codex exec --skip-git-repo-check "Review this diff. Find bugs, security risks, missing tests, edge cases. Be specific and adversarial."git diff. For a harder pass:...codex exec ... "Adversarial review. Challenge the design. Prove what's broken." - Parse Codex's findings into severity-tagged items (Critical → nits).
- Integrate, don't rubber-stamp. For each finding decide fix / defer / dismiss (with a reason). Apply the fixes, then re-verify.
Outputs
- A severity-tagged findings list from Codex
- The integrated outcome: what was fixed, deferred, or dismissed (with reasons)
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.
- 12d ago First seen · 65 lines · 93 tokens per session scan A a36bfff63053
route-codex-review is a skill published in the GitHub repository ZachArticulateV/designer-pro-and-seo (8 stars, last pushed 2mo ago), licensed MIT. It adds 93 tokens to every session and 699 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 skills, from other repositories
component-api-validator
Audit component APIs for consistency, breaking changes, TypeScript coverage, and contract compliance across a component library. Trigger when someone says: component prop review, verify component types are exported, component API audit, check our component interfaces, are our props consistent, API consistency check…
wp-audit-standards
Audit criteria, severity definitions, report JSON schema, and quality thresholds for wp-audit agents.
river-review-frontend
A frontend review skill that checks user-interface changes for accessibility, design-system consistency, styling issues, UI states, and framework boundaries in React and Next.js.
Component Variants / States Documentation コンポーネント状態の文書化
A code review check for new reusable interface components and the variations and states they support, such as hover, focus, disabled, loading, and error states.
Design Source-of-Truth Conformance デザイン定義準拠
A code review check that compares new interface values—such as colors, spacing, font sizes, rounded corners, and shadows—with the project's documented design rules or token files. It only runs when those design definitions exist.
Design System Component Reuse Guard
A code review check that spots new buttons, inputs, modals, cards, and similar interface pieces built from scratch when reusable design-system components already exist. It also suggests importing the existing component.