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/suyoumo/clawprobench/web-ui-testnpx skills add suyoumo/ClawProBench --skill web-ui-testgit clone --depth 1 https://github.com/suyoumo/ClawProBenchWrote 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/suyoumo/clawprobench/web-ui-test)<a href="https://agentmods.dev/skills/suyoumo/clawprobench/web-ui-test"><img src="https://agentmods.dev/badge/skills/suyoumo/clawprobench/web-ui-test.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 | $0.00019 | $0.00825 |
| Opus 5 | $0.00010 | $0.00413 |
| Sonnet 5 | $0.00004 | $0.00165 |
| Haiku 4.5 | $0.00002 | $0.00082 |
Grade C, and why
web-ui-test scanned grade C 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 4d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf ~/.ironclaw/installed_skills/<skill-name> How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web UI Testing with Claude for Chrome
Use this skill when manually testing the IronClaw web gateway UI via the Claude for Chrome browser extension.
Prerequisites
- IronClaw must be running with
GATEWAY_ENABLED=true - Note the gateway URL (default:
http://127.0.0.1:3000/) and auth token - The Claude for Chrome extension must be installed and connected
Starting the Server
CLI_ENABLED=false GATEWAY_AUTH_TOKEN=<your-token> cargo run
Wait for "Agent ironclaw ready and listening" in the logs before proceeding.
Test Checklist
1. Connection
- Navigate to
http://127.0.0.1:3000/?token=<token> - Verify "Connected" indicator in the top-right corner
- Verify all tabs are visible: Chat, Memory, Jobs, Routines, Extensions, Skills
2. Chat Tab
- Send a simple message (e.g., "Hello, what tools do you have?")
- Verify the LLM responds without errors
- If you see "Invalid schema for function" errors, the tool schema fix (PR #301) may not be merged yet
3. Skills Tab
- Click the Skills tab
- Verify "No skills installed" or a list of installed skills (no "Skills system not enabled" error)
- Search for "markdown" in the ClawHub search box
- Verify results appear with: name, version, description, relevance score, "updated X ago"
- Verify skill names are clickable links to clawhub.ai
- If search returns empty with a yellow warning banner, the registry may be unreachable
4. Skill Install (from search)
- Search for a skill (e.g., "markdown")
- Click "Install" on a result
- Confirm the install dialog
- Verify success toast appears
- Verify the skill appears in "Installed Skills" section
5. Skill Install (by URL)
- Scroll to "Install Skill by URL"
- Enter a skill name and a ClawHub download URL:
- Name:
markdown-viewer - URL:
https://wry-manatee-359.convex.site/api/v1/download?slug=markdown-viewer
- Name:
- Click Install
- Verify success toast and skill appears in installed list
6. Skill Remove
- Find an installed skill
- Click "Remove"
- Confirm removal
- Verify the skill disappears from the installed list
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.
- 4d ago First seen · 107 lines · 19 tokens per session scan C c684807a8ac8
web-ui-test is a skill published in the GitHub repository suyoumo/ClawProBench (823 stars, last pushed 9d ago), licensed Apache-2.0. It adds 19 tokens to every session and 825 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
penguin-harness-manual-test
Use when standing PenguinHarness up to try a change by hand — launching the Web App, the desktop shell, the landing page or the docs site to click through it, screenshot it, or reproduce a report. Covers the four dev entry points and their ports, which data root each writes to, and the four ways a healthy setup looks…
browser-test
Validate a feature works by driving a real browser with Playwright MCP. No test files — just interactive verification.
firecrawl
Search the web and scrape pages into clean markdown with the Firecrawl API — query-based discovery, single-URL extraction including public PDFs, driven by curl with a vault-stored API key.
browser-qa
Drive a real headless browser against a locally-served web UI and capture screenshot evidence, reporting step-level PASS/FAIL/BLOCKED with extracted DOM text and console errors. Use when a phase on the docker QA image must exercise a rendered UI and attach screenshots — it complements the text-evidence verify/qa-test…
webqa
Use WebQA to test websites, web pages, URLs, login flows, search flows, forms, navigation, and core user journeys with an AI browser QA agent.
Evaluation
Frames model, prompt, and system evaluation as a reproducible experiment with baselines, datasets, and explicit metrics.