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 anhnguyen0905/codex-mcp --skill review-qualitygit clone --depth 1 https://github.com/anhnguyen0905/codex-mcpWrote 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/anhnguyen0905/codex-mcp/review-quality)<a href="https://agentmods.dev/skills/anhnguyen0905/codex-mcp/review-quality"><img src="https://agentmods.dev/badge/skills/anhnguyen0905/codex-mcp/review-quality/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/anhnguyen0905/codex-mcp/review-quality"><img src="https://agentmods.dev/badge/skills/anhnguyen0905/codex-mcp/review-quality.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 | $0.00027 | $0.00367 |
| Opus 5 | $0.00014 | $0.00183 |
| Sonnet 5 | $0.00005 | $0.00073 |
| Haiku 4.5 | $0.00003 | $0.00037 |
Grade A, and why
review-quality 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.
What it actually says
Quality Review (second pass, after conformance)
Correctness hazards (highest value per minute)
- Silent failures: swallowed exceptions, empty catch blocks, errors logged-then-ignored, fallback values masking real failures. Trace every error path to a visible outcome.
- Edge cases: empty/null input, zero/one/many, boundary values, unicode, concurrent access. Does the code (and its tests) handle the edges the interview identified?
- Async/concurrency: unawaited promises, race conditions on shared state, missing cancellation/cleanup, resource leaks (handles, listeners, timers).
- State mutation: in-place mutation of parameters, props, or shared structures.
Test quality (not just presence)
- Tests assert behavior, not implementation; failure paths tested, not only happy paths.
- Would the tests catch a realistic regression? A test that can't fail is a finding.
- Coverage of NEW code specifically — global % can hide an untested new module.
Structure & maintainability
- Function > 50 lines, file > 800, nesting > 4 → split (early returns).
- Duplication of logic that exists elsewhere in the repo (Codex can't see the whole repo — you can).
- Dead code, debug prints, commented-out blocks, unused imports left behind.
- Naming that lies (function does more/less than its name says).
- Comments that narrate instead of explaining constraints.
Calibration
Report findings that change behavior, risk, or maintenance cost. Style nitpicks the project's linter doesn't enforce are LOW at most — don't spend review rounds on them.
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 · 32 lines · 27 tokens per session scan A ed07eeef5a76
review-quality is a skill published in the GitHub repository anhnguyen0905/codex-mcp (3 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 367 once invoked, about $0.0001 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…