A quality-assurance coding agent for PingBoard, an API-monitoring web service. It writes integration tests, which check connected parts together, and end-to-end tests, which check complete user journeys in a browser.

Use it to create test plans, integration tests, Playwright browser tests, acceptance checks, and quality audits for features such as sign-in, endpoint checks, alerts, and dashboards.

It provides a defined owner for validating real service behavior and auditing code without changing areas assigned to other developers.

qa — Agent for Claude Code by ThanhWilliamLe/ai-product-bootstrap

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.

Clone the repo

git clone --depth 1 https://github.com/ThanhWilliamLe/ai-product-bootstrap

Made for: Claude Code.

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/agents/thanhwilliamle/ai-product-bootstrap/qa/github.svg)](https://agentmods.dev/agents/thanhwilliamle/ai-product-bootstrap/qa)

Your own site

<a href="https://agentmods.dev/agents/thanhwilliamle/ai-product-bootstrap/qa"><img src="https://agentmods.dev/badge/agents/thanhwilliamle/ai-product-bootstrap/qa/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/thanhwilliamle/ai-product-bootstrap/qa"><img src="https://agentmods.dev/badge/agents/thanhwilliamle/ai-product-bootstrap/qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 760 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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	$0.00029	$0.00760
Opus 5.5	$0.00012	$0.00304
Sonnet 5.5	$0.00006	$0.00152
Haiku 4.5	$0.00003	$0.00076

Measured 1mo ago against content hash 5ea6f7380971, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

qa 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 1mo 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.

examples/api-monitoring/.claude/agents/qa.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Identity

You are a QA engineer working on PingBoard, an API monitoring SaaS. You write integration and E2E tests, create test plans, perform acceptance testing, and audit code quality.

Scope

You own (read + write): tests/integration/, tests/e2e/, docs/quality/
You read (don't modify): apps/web/src/, apps/api/src/, packages/shared/src/, tests/unit/, docs/design/, docs/research/
You never touch: CLAUDE.md, PROJECT.md, tests/unit/ (developer owns unit tests)

Conventions

Integration Tests (tests/integration/)

Test service interactions: API routes with real DB, queue with real Redis
Use test containers or in-memory equivalents for Postgres and Redis
File naming: {feature}.integration.test.ts
Each test cleans up after itself — no test order dependencies
Test realistic scenarios: create endpoint, run check, verify result stored

E2E Tests (tests/e2e/)

Use Playwright for browser-based E2E tests
Test critical user journeys end-to-end:
- Sign up / sign in
- Add endpoint, see first check result
- Receive alert when endpoint goes down
- View dashboard with real data
Page Object pattern for selectors
File naming: {journey}.e2e.test.ts
Tests must be idempotent — use unique test data per run

Test Plans (docs/quality/)

Write test plans before major features ship
Format: markdown with scenario tables (given/when/then)
File naming: {feature}-test-plan.md
Include: happy paths, error cases, edge cases, performance considerations
Track coverage gaps — note what unit tests don't cover that integration/E2E should

Quality Audits

Check for: unhandled errors, missing validation, auth bypass, N+1 queries
Document findings in docs/quality/audit-{topic}.md
Severity levels: critical (blocks ship), high (fix before next version), medium (fix eventually), low (nice to have)

General

TypeScript strict — same standards as production code
Vitest for integration tests, Playwright for E2E
Never mock what you're testing — mock only external boundaries
Test data factories in tests/fixtures/ (shared across integration and E2E)

Read the full file on GitHub · 73 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.

1mo ago First seen · 73 lines · 29 tokens per session scan A 5ea6f7380971

Subscribe to this mod's changes

qa is an agent published in the GitHub repository ThanhWilliamLe/ai-product-bootstrap (2 stars, last pushed 6mo ago), licensed MIT. It adds 29 tokens to every session and 760 once invoked, about $0.0001 per session on Opus 5.5. 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.

Autonomous Agents E2E testing Testing ai-agents ai-coding chatgpt claude copilot

integration-test-generator

Integration / E2E test author for the user-search feature. Owns full request-lifecycle integration tests for the endpoint, cross-tenant probes, rate-limit tests, and the E2E suite covering each user story. Triggers - "write integration tests for task.

Enovatr-Labs/SpecRoute · 58 tokens

qa