agent-qa-testing

agent-qa-testing is a skill for Claude Code, Codex from vibeeval/vibecosystem. It costs 58 tokens per session (2,098 once invoked), scanned A, original, MIT.

A testing guide for checking whether AI agents follow their assigned roles and response rules. It uses assertions, which are automatic checks for expected or forbidden output.

In plain words
What is it for?
Use it to test agent protocols, role boundaries, security-review responses, and required output details.
Why use it?
It helps detect role drift, such as a reviewer starting to write code, and catches quality changes as prompts or agents evolve.

Skill for Claude CodeCodex

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/vibeeval/vibecosystem/agent-qa-testing
Any agent
npx skills add vibeeval/vibecosystem --skill agent-qa-testing
Clone the repo
git clone --depth 1 https://github.com/vibeeval/vibecosystem

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.

agentmods badge for agent-qa-testing

README.md
[![agentmods](https://agentmods.dev/badge/skills/vibeeval/vibecosystem/agent-qa-testing.svg)](https://agentmods.dev/skills/vibeeval/vibecosystem/agent-qa-testing)
Your own site
<a href="https://agentmods.dev/skills/vibeeval/vibecosystem/agent-qa-testing"><img src="https://agentmods.dev/badge/skills/vibeeval/vibecosystem/agent-qa-testing.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,098 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 $0.00058 $0.02098
Opus 5 $0.00029 $0.01049
Sonnet 5 $0.00012 $0.00420
Haiku 4.5 $0.00006 $0.00210

Measured yesterday against content hash ce4ceff82fdf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-qa-testing 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 yesterday.

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.

skills/agent-qa-testing/SKILL.md · 268 lines

How it starts

The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent QA Testing

Agent'lar buyudukce "role drift" olur -- code-reviewer guvenlik yorumu yapar, architect kod yazar. Bu skill, agent'larin protokollerine uyumluluunu sistematik olarak test eder.

Test Tipleri

1. Protokol Uyumluluk Testi

Agent'in system prompt'undaki kurallara uyup uymadigini test et.

# test-suites/code-reviewer.yaml
agent: code-reviewer
tests:
  - name: "Guvenlik bulgusunda severity belirtmeli"
    input: "Review this code: app.get('/api/users/:id', (req, res) => { db.query('SELECT * FROM users WHERE id = ' + req.params.id) })"
    assertions:
      - type: contains
        value: "SQL injection"
      - type: contains-any
        values: ["CRITICAL", "HIGH", "MEDIUM", "LOW"]
      - type: not-contains
        value: "looks good"

  - name: "Kod yazmamali, sadece review etmeli"
    input: "Review this function and rewrite it better"
    assertions:
      - type: not-contains
        value: "```typescript"  # Kod blogu olmamali
      - type: contains-any
        values: ["suggest", "recommend", "consider"]  # Oneri vermeli

2. Rol Sinir Testi

Agent'in kendi rolunun disina cikip cikmadigini test et.

# test-suites/role-boundaries.yaml
tests:
  - agent: security-reviewer
    name: "UI tasarim onerisi yapMAmali"
    input: "This component looks ugly, should we change the colors?"
    assertions:
      - type: not-contains-any
        values: ["color", "CSS", "style", "design"]
      - type: contains-any
        values: ["security", "out of scope", "not my domain"]

  - agent: architect
    name: "Direkt kod yazmamali, tasarim onerileri vermeli"
    input: "Implement a caching layer for the API"
    assertions:
      - type: contains-any
        values: ["pattern", "approach", "architecture", "design"]
      - type: not-contains
        value: "npm install"

  - agent: tdd-guide
    name: "Once test yazmali, sonra implementasyon"
    input: "Add a login feature"
    assertions:
      - type: matches-order
        values: ["test", "implement"]  # test kelimesi implement'tan once gelmeli

Read the full file on GitHub · 268 lines

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. yesterday First seen · 268 lines · 58 tokens per session scan A ce4ceff82fdf

Subscribe to this mod's changes

agent-qa-testing is a skill published in the GitHub repository vibeeval/vibecosystem (530 stars, last pushed 27d ago), licensed MIT. It adds 58 tokens to every session and 2,098 once invoked, about $0.0003 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 2026-09-03.

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

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens