A project-specific quality check for Codex Project Autopilot, a workflow that coordinates development work. It reviews the project before handoff and records what was and was not tested.

It checks the expected path and at least one failure case, reviews desktop, tablet, and mobile layouts at recorded viewport sizes, and writes findings, a scorecard, and updated project state.

It helps prevent a project being approved when important paths, screen sizes, security details, or handoff items were skipped.

qa-reviewer — Skill for Claude Code and Codex by hashgraph-online: A project-specific quality check for Codex Project Autopilot, a…

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 skills/hashgraph-online/awesome-codex-plugins/qa-reviewer

Any agent

npx skills add hashgraph-online/awesome-codex-plugins --skill qa-reviewer

Clone the repo

git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/hashgraph-online/awesome-codex-plugins/qa-reviewer.svg)](https://agentmods.dev/skills/hashgraph-online/awesome-codex-plugins/qa-reviewer)

Your own site

<a href="https://agentmods.dev/skills/hashgraph-online/awesome-codex-plugins/qa-reviewer"><img src="https://agentmods.dev/badge/skills/hashgraph-online/awesome-codex-plugins/qa-reviewer.svg" alt="Measured on agentmods" height="20"></a>

Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 519 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.

Model	Per session	Once invoked
Fable 5.1	$0.00039	$0.00519
Opus 5	$0.00019	$0.00260
Sonnet 5	$0.00008	$0.00104
Haiku 4.5	$0.00004	$0.00052

Measured 6d ago against content hash 1c758cd99168, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

qa-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 6d 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.

plugins/AlexMi64/codex-project-autopilot/skills/qa-reviewer/SKILL.md · 69 lines

What it actually says

QA-аналитик

Правило активации

Не включай этот skill автоматически для любого ревью-кейса. Вне автопилота действует обычный review-подход Codex.

Ты отвечаешь за правду перед финалом.

Вход

implementation-plan.md
execution-log.md
verification-report.md
state.json

Выход

findings
verification-report.md
scorecard.md
обновленный state.json

Обязан

сначала писать findings
проверять happy path
проверять хотя бы один плохой сценарий
отмечать, что не проверено
выставлять scorecard проекта
отдельно проверять desktop, tablet и mobile
проверять адаптив не только на “работает / не работает”, а на читаемость, плотность и отсутствие визуальных поломок
фиксировать конкретные viewport size, на которых проводилась проверка
если проект касается данных, auth, платежей или интеграций, отдельно проверять секреты, доступ и путь проверки зависимостей

QA-подход Morecil

Ты нужен не для формальной галочки, а чтобы остановить самообман команды.

Если что-то не проверено, это должно быть написано явно.

Запрещено

писать “всё ок”, если ничего толком не проверено
пропускать проблемы безопасности, handoff или UX
одобрять финал при шаблонных артефактах
одобрять UI, если на mobile есть вылезание текста, тесные блоки, случайные переносы или неудобные кнопки

Самопроверка

есть ли реальные findings или их правда нет?
хватит ли handoff новому человеку?
scorecard честный?
проверены ли хотя бы 1440, 768 и 375?
зафиксированы ли реальные UX-поломки mobile, если они есть?
отмечено ли, чем проверялась безопасность и зависимости?

Handoff деплою и оркестратору

Передай:

что реально подтверждено
что остаётся риском
какие ручные проверки должен повторить пользователь

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.

6d ago First seen · 69 lines · 39 tokens per session scan A 1c758cd99168

Subscribe to this mod's changes

qa-reviewer is a skill published in the GitHub repository hashgraph-online/awesome-codex-plugins (924 stars, last pushed today), licensed Apache-2.0. It adds 39 tokens to every session and 519 once invoked, about $0.0002 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.

Testing ai-coding awesome awesome-list codex codex-plugins openai

search

Search 2500+ curated ChatGPT and LLM open-source repositories. Use when the user asks to find tools, libraries, or repos related to ChatGPT, LLMs, RAG, agents, langchain, NLP, AI development, or any open-source AI tooling.

taishi-i/awesome-ChatGPT-repositories · 57 tokens

similar-resources

Given a Japanese NLP GitHub repo or Hugging Face model/dataset (URL / owner/repo / tool name), find repositories or models/datasets that do the same or related processing. Mines the bundled dataset for content-similar items, then expands via web research across both GitHub and Hugging Face, then merges and re-ranks.

taishi-i/awesome-japanese-nlp-resources · 70 tokens

sprr

Single PR reviewer for awesome-quant. Use when the user asks to review, validate, comment on, label, close, or merge one specific pull request that adds README.md entries. Triggers include "sprr", "review PR", "check PR", and "validate contribution".

wilsonfreitas/awesome-quant · 60 tokens

bprr

Bulk PR reviewer for awesome-quant. Use when the user asks to review all open PRs, review unreviewed PRs, bulk review, or mentions "bprr". Reviews open PRs lacking the reviewed label and presents a summary before any merge/comment/label action.

wilsonfreitas/awesome-quant · 61 tokens

reverse-engineering-android-malware-with-jadx

Reverse engineers malicious Android APK files using JADX decompiler to analyze Java/Kotlin source code, identify malicious functionality including data theft, C2 communication, privilege escalation, and overlay attacks. Examines manifest permissions, receivers, services, and native libraries. Activates for requests…

adriannoes/awesome-agentic-ai · 82 tokens

implementing-code-signing-for-artifacts

This skill covers implementing code signing for build artifacts to ensure integrity and authenticity throughout the software supply chain. It addresses signing binaries, packages, and containers using GPG, Sigstore, and platform-specific signing tools, establishing trust chains, and verifying signatures in deployment…

adriannoes/awesome-agentic-ai · 62 tokens