Borrowing it
Nothing to install: this file belongs to SafetyMP/Autonomous-EHS-Management. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/SafetyMP/Autonomous-EHS-Management/main/.cursor/skills/senior-qa-automation/SKILL.mdgit clone --depth 1 https://github.com/SafetyMP/Autonomous-EHS-ManagementWrote 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/safetymp/autonomous-ehs-management/senior-qa-automation)<a href="https://agentmods.dev/skills/safetymp/autonomous-ehs-management/senior-qa-automation"><img src="https://agentmods.dev/badge/skills/safetymp/autonomous-ehs-management/senior-qa-automation/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/safetymp/autonomous-ehs-management/senior-qa-automation"><img src="https://agentmods.dev/badge/skills/safetymp/autonomous-ehs-management/senior-qa-automation.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 | $0.00106 | $0.01138 |
| Opus 5 | $0.00053 | $0.00569 |
| Sonnet 5 | $0.00021 | $0.00228 |
| Haiku 4.5 | $0.00011 | $0.00114 |
Grade A, and why
senior-qa-automation 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Senior QA automation (SDET)
You are acting as Senior QA Automation / SDET for this codebase. Do not implement product features unless a test exposes a reproducible defect and fixing it is in scope—prefer mocks and narrowing tests before changing production logic.
Merge bar for this repo: AGENTS.md (npm run verify, optionally npm run verify:all).
Philosophy
- Assume malice and stupidity — Fuzz adjacent to boundaries: empty and huge strings, wrong types/surrogate Unicode, nonsense UUID-ish strings (respect Zod’s RFC variant bits),
-1, zeros, NaN/Infinities where numbers flow through pure math, malformed paths, stray control characters (\0,\t), missing or extra fields. - Isolation — No real Postgres, Neon, Redis/Upstash, or third-party APIs in deterministic suites. Stub rate limits unless explicitly testing limits. Prefer module
vi.mockfor side-effect imports (e.g. audit writes) after consulting existing patterns. - Branches over lines — Enumerate transitions, parity of allowed vs forbidden combinations, middleware vs handler vs validator order (e.g. UNAUTHORIZED before BAD_INPUT).
This repository’s layout
| Kind | Location |
|---|---|
| Unit + integration (Vitest) | tests/unit/**/*.test.ts, tests/integration/**/*.test.ts |
| Eval-style LLM shape tests | tests/evals/**/*.eval.test.ts |
| Smoke E2E | tests/e2e/smoke/ (see AGENTS.md) |
| Vitest env bootstrap | tests/vitest.setup.ts (SKIP_ENV_VALIDATION, Upstash vars cleared) |
| Drizzle chain fakes | tests/helpers/fake-db.ts |
server-only test alias |
tests/mocks/server-only.ts via vitest.config.ts |
tRPC / server procedures
- Build a synthetic
TRPCContextmatchingsrc/server/trpc/context.ts:{ session, db, ip }. Auth middleware expectssessionwith auser(seesrc/server/trpc/init.ts); do not placeuserat the top level of context. - Use
callTRPCProcedurefrom@trpc/serverwithrouter, dot-path (e.g.incident.list),ctx,type,getRawInput, plussignal(e.g.new AbortController().signal) andbatchIndex: 0sotscmatchesProcedureCallOptions. The main package entry does not re-exportcreateCallerFactoryin this stack. - Mutations use
protectedMutation(rate limit middleware). WithNODE_ENV=testand Upstash unset in setup, limiter is typically inert—do not rely on production Redis in tests. - See reference procedure tests:
tests/integration/trpc/incident-router.test.ts.
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.
- 9d ago First seen · 62 lines · 106 tokens per session scan A 6c39cef663a8
senior-qa-automation is a skill published in the GitHub repository SafetyMP/Autonomous-EHS-Management (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 106 tokens to every session and 1,138 once invoked, about $0.0005 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
test-harness
Generates pytest test suites with happy path, edge cases, error conditions, fixture scaffolding, mocks, async patterns. Triggers on: "generate tests", "write tests for", "test this function", "create test suite", "pytest for", "unit tests for", "mock strategy for".
Write Tests
Generate unit and integration tests.
test-coverage
Enforces a 90% line and branch coverage threshold and audits for meaningful integration, end-to-end, stress, and property-based tests beyond unit tests. Identifies critical paths that lack coverage, flags tests that pass without asserting, and in edit mode generates missing test scaffolds. Use when the user asks to…
api-testing
Testing patterns for MCP tool/resource handlers using createMockContext and Vitest. Covers mock context options, handler testing, McpError assertions, format testing, Vitest config setup, and test isolation conventions.
add-test
Scaffold a test file for an existing tool, resource, or service. Use when the user asks to add tests, improve coverage, or when a definition exists without a matching test file.
add-test
Scaffold a test file for an existing tool, resource, or service. Use when the user asks to add tests, improve coverage, or when a definition exists without a matching test file.