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/roarista/awesome-harness/ui-console-debugnpx skills add roarista/awesome-harness --skill ui-console-debuggit clone --depth 1 https://github.com/roarista/awesome-harnessWrote 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/roarista/awesome-harness/ui-console-debug)<a href="https://agentmods.dev/skills/roarista/awesome-harness/ui-console-debug"><img src="https://agentmods.dev/badge/skills/roarista/awesome-harness/ui-console-debug.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 5.1 | $0.00050 | $0.00665 |
| Opus 5 | $0.00025 | $0.00332 |
| Sonnet 5 | $0.00010 | $0.00133 |
| Haiku 4.5 | $0.00005 | $0.00067 |
Grade A, and why
ui-console-debug 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI Console Debug Loop
Debug a web page the way a human does with F12, but automated through the claude-in-chrome MCP tools. Never guess at a UI bug from source alone — read the browser's own error first.
Preconditions
- Load tools in ONE ToolSearch call:
select:mcp__claude-in-chrome__tabs_context_mcp,mcp__claude-in-chrome__navigate,mcp__claude-in-chrome__read_console_messages,mcp__claude-in-chrome__computer,mcp__claude-in-chrome__read_network_requests - Call
tabs_context_mcpfirst (createIfEmpty: true). Never reuse tab IDs from old sessions.
The loop
- Navigate to the page URL (or reuse the tab if Ro is already on it).
- Read console:
read_console_messageswith a pattern likeerror|Error|declared|undefined|failed|404. NOTE: tracking starts at first call — if messages look stale (old timestamps) or empty, hard-reload withcomputerkeycmd+shift+r, wait 2-3s, read again. - Screenshot (
computeraction screenshot) — visual state is a second, independent signal; a page can be error-free and still visually wrong. - Diagnose from the REAL error text, not from expectations. Classic traps:
- Two classic
<script>files declaring the same top-levelconst→ "Identifier X has already been declared" → wrap each file in an IIFE. - Stale cache → always hard reload (cmd+shift+r), never plain reload.
- Two classic
- Fix the source,
node --checkany edited JS, hard-reload, re-read console. Repeat until console shows zero errors. - Verify visually with a final screenshot (save_to_disk: true so Ro gets
the absolute path). If interaction matters (zoom, drag), actually perform
it via
computer(scroll/click/drag) and screenshot the result. - For network issues (404 assets, CORS):
read_network_requests.
Rules
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 · 49 lines · 50 tokens per session scan A 70f7cd17048d
ui-console-debug is a skill published in the GitHub repository roarista/awesome-harness (1 stars, last pushed 10d ago), licensed MIT. It adds 50 tokens to every session and 665 once invoked, about $0.0003 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
runtime-debug
Debug and verification workflow for runtime-bundle and module-resolution regressions. Use when diagnosing unexpected module inclusions, bundle size regressions, or CI failures related to NEXTSKIPISOLATE, nft.json traces, or runtime bundle selection (module.compiled.js). Covers CI env mirroring, full stack traces via…
chrome-devtools-cli
Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.
agent-browser-electron
Use when Codex needs to inspect, debug, or automate an Electron app through agent-browser and Chrome DevTools Protocol, especially when the app has multiple BrowserWindow instances, lazy-created windows, duplicate URLs, or misleading agent-browser tab list output. Covers mapping Electron windows to raw CDP targets…
a11y-debugging
Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.
chrome-devtools
Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to --slim mode (MCP configuration).
nullaway
Guide for resolving NullAway static analysis errors. Best practices for: Passing ObservableSupplier/Supplier Dereferencing potentially @Nullable values Adding @NullMarked to Java code.