qa-eval

qa-eval is a skill for Codex from ashermahonin/agentic-skills. It costs 80 tokens per session (417 once invoked), scanned A, original, MIT.

A guide for planning and running software checks across areas such as unit tests, browser tests, security, performance, accessibility, migrations, and release smoke tests. It connects each acceptance requirement to a way of verifying it.

In plain words
What is it for?
Use it before merging or releasing changes, after implementation, when test evidence is missing, or when you need a practical verification plan tied to acceptance criteria.
Why use it?
It helps teams test the risks that matter without relying on an arbitrary checklist. It also records what was tested, what passed or failed, and what could not be verified.

Skill for Codex

Written for Codex: agents/openai.yaml present.

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/ashermahonin/agentic-skills/qa-eval
Any agent
npx skills add ashermahonin/agentic-skills --skill qa-eval
Clone the repo
git clone --depth 1 https://github.com/ashermahonin/agentic-skills

Made for: 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.

agentmods badge for qa-eval

README.md
[![agentmods](https://agentmods.dev/badge/skills/ashermahonin/agentic-skills/qa-eval.svg)](https://agentmods.dev/skills/ashermahonin/agentic-skills/qa-eval)
Your own site
<a href="https://agentmods.dev/skills/ashermahonin/agentic-skills/qa-eval"><img src="https://agentmods.dev/badge/skills/ashermahonin/agentic-skills/qa-eval.svg" alt="Measured on agentmods" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 417 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 5.1 $0.00080 $0.00417
Opus 5 $0.00040 $0.00209
Sonnet 5 $0.00016 $0.00083
Haiku 4.5 $0.00008 $0.00042

Measured 6d ago against content hash 447865a7ff7c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

qa-eval 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.

agentic/skills/qa-eval/SKILL.md · 54 lines

What it actually says

QA and Eval

Purpose

Prove the important behavior works and the important risks are covered. Make verification practical, visible, and tied to acceptance criteria.

Change context

  • Collect requirements, acceptance criteria, changed files, and risk notes.
  • Identify the minimum test set that covers the behavior and highest risks.
  • Separate automated checks from manual smoke checks.
  • Decide what cannot be verified in this environment and how to report it honestly.

Change method

  1. Map each acceptance criterion to a validation method.
  2. Run existing tests before inventing new ones when that gives useful signal.
  3. Add focused tests when behavior changed and no existing test covers it.
  4. For UI work, verify real rendering and main workflows when possible.
  5. For migrations or data changes, verify rollback or safe failure behavior.
  6. Summarize pass/fail evidence with commands, scenarios, and residual risk.

Engineering constraints

  • Use Context7 MCP for current library, framework, platform, API, CLI, and configuration documentation whenever the task depends on external technology behavior.

Evidence

  • Validation plan
  • Commands run
  • Acceptance evidence
  • Bugs or regressions found
  • Release readiness recommendation

Ready when

  • Do not treat compilation as full QA.
  • Do not hide skipped checks.
  • Tie every critical risk to a test, smoke check, or explicit residual risk.
  • Keep bug reports reproducible.

Handoff

Hand off evidence, failures, skipped checks, and release recommendation to PR review or release docs.

References

  • references/eval-plan.md: Use this for test and eval planning.
Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 54 lines · 80 tokens per session scan A 447865a7ff7c

Subscribe to this mod's changes

qa-eval is a skill published in the GitHub repository ashermahonin/agentic-skills (10 stars, last pushed 12d ago), licensed MIT. It adds 80 tokens to every session and 417 once invoked, about $0.0004 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 skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens