Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/SethGammon/Citadelnpx agentmods add skills/sethgammon/citadel/qaWrote 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/sethgammon/citadel/qa)<a href="https://agentmods.dev/skills/sethgammon/citadel/qa"><img src="https://agentmods.dev/badge/skills/sethgammon/citadel/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/sethgammon/citadel/qa"><img src="https://agentmods.dev/badge/skills/sethgammon/citadel/qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 194 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium MCP Rug Pull · line 32 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 38 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Excessive Agency · line 190 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00056 | $0.02002 |
| Opus 5.5 | $0.00022 | $0.00801 |
| Sonnet 5.5 | $0.00011 | $0.00400 |
| Haiku 4.5 | $0.00006 | $0.00200 |
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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. Check if a dev server is already running (try curl localhost:3000, 5173, 8080) How it starts
The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/qa — Browser QA Verification
Dependency: Playwright
/qa requires Playwright. It's an optional dependency.
If Playwright is installed: full browser QA works. If Playwright is NOT installed: the skill offers to install it, or falls back to /live-preview (screenshot-only verification).
Detection:
npx playwright --version 2>/dev/null
Installation (if user agrees):
npm install -D playwright
npx playwright install chromium
Only installs Chromium (smallest download, ~150MB). Not Firefox or WebKit unless the user asks for cross-browser testing.
/do setup integration: During setup, if the project is a web app (has React, Next.js, Vue, Svelte, or HTML files), offer to install Playwright: "I see this is a web project. Want to enable browser QA testing? This installs Playwright (~150MB) for interaction testing. (y/n)"
If they say no, /qa falls back to /live-preview. No pressure.
When to Use
- After building a feature (verify it actually works in a browser)
- As a phase end condition: "QA verification passes for [flow]"
- When /do routes "qa", "test the app", "does it work", "click through it"
- When /create-app campaigns reach the verification phase
- After /live-preview shows something renders but you need to verify interactions
Protocol
Step 1: DISCOVER
Before testing, understand what to test:
- Read the project's routes/pages (from file tree, router config, or package.json scripts)
- Read the PRD or campaign file (if exists) for expected user flows
- Identify testable flows:
- Page loads and renders (baseline)
- Navigation between pages
- Form submissions
- Button click handlers
- Auth flows (login, logout, protected routes)
- CRUD operations (create, read, update, delete)
- Error states (invalid input, network errors)
If no PRD or campaign exists, ask: "What should I test? Give me 1-3 user flows."
Step 2: START THE APP
Before testing, the app needs to be running:
- Check if a dev server is already running (try curl localhost:3000, 5173, 8080)
- If not running, check package.json for start/dev scripts
- Start it:
npm run devor equivalent, in background - Wait for the server to be ready (poll the health endpoint or main URL)
- If the app won't start, report the error and stop. Don't test a broken app.
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.
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 · 249 lines · 56 tokens per session scan A af87e204d608
qa is a skill published in the GitHub repository SethGammon/Citadel (925 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 2,002 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
browser-check
Drive a real browser and come back with a MEASUREMENT rather than an impression - console errors and >=400 responses as counts, computed styles as JSON when appearance is disputed. Use when work touches UI, when a review must verify one, or when fidelity-gate asks for its measurement.
playwright-driver
Use this skill when executing web tests via the canonical playwright npm package (Microsoft, Apache-2.0). Dispatched by skills/test-runner/ to execute web tests against a target, captures token-frugal AX-tree snapshots + screenshots + console output under .orchestrator/metrics/test-runs/ /, and exits with…
peekaboo-driver
Use this skill when driving native-UI AX-tree snapshots and screenshots via steipete/peekaboo (MIT, macOS-only). Dispatched by skills/test-runner/ to capture native-UI AX-tree snapshots + screenshots on macOS 15+ targets, and exits with deterministic JSON output the orchestrator can parse.
browser-testing
Test and debug browser code with Chrome DevTools MCP. Use when building or debugging browser UI, inspecting the DOM, capturing console errors, analyzing network requests, or verifying visual output.
browser-use
Drive a real browser to QA a running app. Screenshots, clicks, forms, evidence. Use when there is no Playwright suite, or when a human flow must be walked.
playwright
Browser automation and end-to-end testing with Playwright. Use when building/testing frontends, automating user workflows, taking screenshots, validating UI state, filling forms, testing across browsers, or mentions "playwright", "E2E test", "browser automation", "screenshot".