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 agentmods add skills/sethgammon/citadel/live-previewnpx skills add SethGammon/Citadel --skill live-previewgit clone --depth 1 https://github.com/SethGammon/CitadelWrote 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/live-preview)<a href="https://agentmods.dev/skills/sethgammon/citadel/live-preview"><img src="https://agentmods.dev/badge/skills/sethgammon/citadel/live-preview.svg" alt="Measured on agentmods" 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 | $0.00040 | $0.01558 |
| Opus 5 | $0.00020 | $0.00779 |
| Sonnet 5 | $0.00008 | $0.00312 |
| Haiku 4.5 | $0.00004 | $0.00156 |
Grade A, and why
live-preview 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 5d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/live-preview — Build-Verify-Fix Loop
Prerequisites
This skill requires a screenshot tool. Supported:
- Playwright (recommended):
npx playwright screenshot [url] [output.png] - Puppeteer: via a small script
- Any tool that takes a URL and produces a screenshot
If no screenshot tool is available, this skill will tell you what to install and exit.
When to Use
- Any time .tsx, .jsx, .vue, .svelte, or .html files are modified
- After component creation or replacement
- During visual redesign campaigns
- When Archon or Marshal delegate UI work
Protocol
Step 1: DETECT
Determine what needs visual verification:
- Check which files were modified in the current session/phase
- Filter to view-layer files (.tsx, .jsx, .vue, .svelte, .html, .css)
- If no view-layer files found: exit early with message "No view-layer files modified. Nothing to preview." Skip Steps 2-5. This is expected for non-UI repos (CLI tools, libraries, agent harnesses).
- Map each modified file to a route or URL where it renders:
- If the project has a route manifest or sitemap, use it
- If the project has a dev server, identify which routes render the modified components
- If you can't determine the route, ask the user
Step 2: CAPTURE
For each route/URL that needs verification:
- Ensure the dev server is running (start it if not)
- Take a screenshot:
npx playwright screenshot http://localhost:{port}/{route} .planning/screenshots/{route-slug}.png --full-page - If Playwright isn't available, try:
# Check for playwright npx playwright --version 2>/dev/null # If not found, inform the user: # "live-preview needs Playwright for screenshots. Install with: npm i -D playwright"
Step 3: VERIFY
For each screenshot:
- Read the screenshot (vision). Check:
- Does the component render? (not blank, not invisible)
- Does it show real data or placeholder/empty states?
- Are there obvious layout breaks (overlapping elements, overflow, missing sections)?
- Does it match the intended design direction?
- Record the result:
- PASS: renders correctly, matches expectations
- FAIL: describe what's wrong
- BLANK: nothing rendered (critical failure)
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.
- 5d ago First seen · 166 lines · 40 tokens per session scan A baed4aabf828
live-preview is a skill published in the GitHub repository SethGammon/Citadel (916 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 1,558 once invoked, about $0.0002 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 2026-08-30.
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.
ios-device-qa
Use when the user runs /ios-device-qa to drive a real iPhone over USB through a debug-bridge daemon and return a device QA report with verified interactions. Do not use for remote, credential, publish, deploy, or irreversible changes.
xcode-simulator-testing
Use when asked to run /xcode-simulator-testing with a scheme name or current to build and launch an iOS app in a simulator and capture per-surface evidence. Not for project regeneration — use xcode-project-sync.
possible-worlds-qa
Use when a product surface must be tested against extreme or hostile worlds rather than collect green checks. Completeness mode classifies every world against stated criteria and reports gaps; break mode names an expected break signal per world, captures proof artifacts, and escalates worlds that survive. Not for…
run-smoke-tests
Use when asked to run smoke tests or verify a local build. Applies minimal fixes that unblock a stable passing result and reports flake risk honestly. Not for iterative bug fixing — use fix.
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.