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.
npx skills add Open-Agent-Tools/General-OAT-Skills --skill qagit clone --depth 1 https://github.com/Open-Agent-Tools/General-OAT-SkillsWrote 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/open-agent-tools/general-oat-skills/qa)<a href="https://agentmods.dev/skills/open-agent-tools/general-oat-skills/qa"><img src="https://agentmods.dev/badge/skills/open-agent-tools/general-oat-skills/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.
<a href="https://agentmods.dev/skills/open-agent-tools/general-oat-skills/qa"><img src="https://agentmods.dev/badge/skills/open-agent-tools/general-oat-skills/qa.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 | $0.00067 | $0.04092 |
| Opus 5 | $0.00034 | $0.02046 |
| Sonnet 5 | $0.00013 | $0.00818 |
| Haiku 4.5 | $0.00007 | $0.00409 |
Grade A, and why
qa scanned grade A with 1 finding 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 8d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
commands (`os.system`, `subprocess` with `shell=True`, `exec`, etc.). How it starts
The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Agent QA Audit
Run a comprehensive quality audit of the current project. Auto-detect the language(s), framework(s), and tooling, then launch all audit agents in parallel for maximum speed.
Scope
If $ARGUMENTS is provided, narrow the audit to that area (e.g. "tests" → only test coverage, "security" → only security audit, "docs" → only documentation accuracy). Otherwise audit the full project.
Step 0 — Project Detection
Before any audit work, detect the project stack by reading the project root. Identify:
- Languages — check for:
Cargo.toml(Rust),package.json(JS/TS),pyproject.toml/setup.py/requirements.txt(Python),go.mod(Go),pom.xml/build.gradle(Java/Kotlin),*.csproj/*.sln(C#/.NET),Gemfile(Ruby),mix.exs(Elixir),Package.swift(Swift),CMakeLists.txt/Makefile(C/C++). - Frameworks — check for framework indicators in config files and imports (React, Vue, Angular, Django, Flask, FastAPI, Rails, Spring, Next.js, Nuxt, SvelteKit, Tauri, Electron, etc.).
- Build/lint/test tooling — identify available commands (npm/yarn/pnpm, cargo, uv/pip/poetry, go, make, gradle/maven, dotnet, mix, etc.).
- CI system — check for
.github/workflows/,.gitlab-ci.yml,Jenkinsfile,.circleci/,bitbucket-pipelines.yml, etc. - Project conventions — read
CLAUDE.md,.editorconfig, linter configs, and any style guides present.
Store the detected stack context. All subsequent agents receive this context so they can tailor their checks to the actual languages and frameworks in use.
Step 1 — Build, Lint & Test (run first, blocking)
Based on the detected tooling, run the project's build, lint, and test commands in parallel using the Bash tool. Adapt to what exists — skip commands that don't apply. Examples by language:
| Language | Build | Lint | Test |
|---|---|---|---|
| Rust | cargo build |
cargo clippy -- -D warnings |
cargo test |
| TypeScript | npx tsc --noEmit |
npm run lint (if exists) |
npm test |
| Python | uv build or skip |
ruff check . or flake8 |
pytest |
| Go | go build ./... |
golangci-lint run |
go test ./... |
| Java | ./gradlew build |
./gradlew check |
./gradlew test |
| C#/.NET | dotnet build |
dotnet format --verify-no-changes |
dotnet test |
| Ruby | skip | rubocop |
bundle exec rspec |
| Elixir | mix compile |
mix credo |
mix test |
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.
- 8d ago First seen · 382 lines · 67 tokens per session scan A 5235e91038ec
qa is a skill published in the GitHub repository Open-Agent-Tools/General-OAT-Skills (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 67 tokens to every session and 4,092 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
solopi-ai
A command-line framework for testing Android apps and devices with SoloPi, including on-device or cloud AI decision models. It manages devices, test cases, recorded interactions, replays, performance history, and evidence.
ios-simulator
Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
performing-api-fuzzing-with-restler
Uses Microsoft RESTler to perform stateful REST API fuzzing by automatically generating and executing test sequences that exercise API endpoints, discover producer-consumer dependencies between requests, and find security and reliability bugs. The tester compiles an OpenAPI specification into a RESTler fuzzing…
smoke-test
Run smoke tests against a deployed or local app based on your git diff. Each test uses Skyvern browser tools (navigate, act, validate, screenshot) with Chrome DevTools MCP as fallback. Posts screenshot evidence as PR comments.