A browser-based checking procedure for a user-interface change. It uses a real browser and records screenshots, console messages, and network activity as evidence.

It is for checking front-end changes by performing the intended interaction and capturing visible results, browser errors, and network responses for a reviewer.

A screenshot alone shows that something appeared, but not that interactions worked or that the page had no related errors.

ui-proof — Skill for Claude Code and Codex by CassioRoos/godfly-skills

Install

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.

Any agent

npx skills add CassioRoos/godfly-skills --skill ui-proof

Clone the repo

git clone --depth 1 https://github.com/CassioRoos/godfly-skills

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/cassioroos/godfly-skills/ui-proof/github.svg)](https://agentmods.dev/skills/cassioroos/godfly-skills/ui-proof)

Your own site

<a href="https://agentmods.dev/skills/cassioroos/godfly-skills/ui-proof"><img src="https://agentmods.dev/badge/skills/cassioroos/godfly-skills/ui-proof/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/cassioroos/godfly-skills/ui-proof"><img src="https://agentmods.dev/badge/skills/cassioroos/godfly-skills/ui-proof.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 153 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,464 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00153	$0.02464
Opus 5.5	$0.00061	$0.00986
Sonnet 5.5	$0.00031	$0.00493
Haiku 4.5	$0.00015	$0.00246

Measured 15d ago against content hash ff18e4004ed2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ui-proof 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 15d 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.

archive/ui-proof/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UI Proof

Prove a UI change works by driving a real browser through it and capturing evidence a reviewer can trust — screenshots, console messages, and network activity. This is operational verification of the front-end, not unit testing. Everything you claim must trace to something you observed in the browser — a rendered screen, a clean console, a 200 response — not memory or inference.

This skill is the front-end sibling of pr-proof. Same discipline, different boundary: pr-proof exercises a deployed service through a port-forwarded API; ui-proof exercises the UI through a real browser.

Core principles

Evidence or it didn't happen. Every claim maps to a captured artifact: a screenshot, a console dump, a network entry. A clean-looking screenshot over a console full of errors and a failed XHR is a lie with a nice render. Capture console + network, not just pixels — see cookbook/evidence.md.
A screenshot proves it rendered, not that it works. Prove the interaction (clicked X → got Y), the before/after delta the change intended, and that nothing broke underneath (console clean, network clean).
Drive what's actually under test. A screenshot of the wrong build or the wrong branch silently proves nothing. Phase 0 resolves what you're testing and which running URL serves that code, and confirms the browser is pointed at it. See cookbook/environment.md.
Persistent profile, not a fresh browser. This skill assumes the Chrome MCP drives a persistent, already-logged-in profile (configured at the MCP-server level, not here — see Phase 0). The skill's job is to verify the expected logged-in state before testing and stop/ask if it's wrong — never to silently test a logged-out or wrong-account session.
Discover, don't assume. The dev URL, the changed surfaces, the auth state, and how the app is served all vary by repo. Find them (Phase 0/1). A guessed URL or stale build tests the wrong thing.
Ask before fixing. Verifying and fixing are different mandates. Document the bug with evidence first; don't push a fix unless the user opted in (Phase 6).
Doc hygiene. State the final content only — no revision markers, "NEW:", or changelog sections in PR descriptions or proof docs. Git and the PR timeline track history.

Read the full file on GitHub · 88 lines

Files

What ships with it

4 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.

Changes

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.

15d ago First seen · 88 lines · 153 tokens per session scan A ff18e4004ed2

Subscribe to this mod's changes

ui-proof is a skill published in the GitHub repository CassioRoos/godfly-skills (1 stars, last pushed yesterday), licensed MIT. It adds 153 tokens to every session and 2,464 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-10-23.

Browser automation Claude Code Code review Frontend adversarial-review agent-skills claude-skills codex-cli

ui-proof next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ui-proofCassioRoos/godfly-skills	Skill	1	yesterday	MIT	A	153	Claude Code, Codex
auto-test-codehuangwb8/skills	Skill	50	6d ago	MIT	A	56	Claude Code, Codex
git-pr-reviewhuangwb8/skills	Skill	50	6d ago	MIT	A	76	Claude Code, Codex
challenge-resolveBorda/AI-Rig	Skill	31	yesterday	Apache-2.0	A	74	Claude Code, Codex
code-reviewBorda/AI-Rig	Skill	31	yesterday	Apache-2.0	A	41	Claude Code, Codex
assessBorda/AI-Rig	Skill	31	yesterday	Apache-2.0	A	19	Claude Code, Codex
code-remediateBorda/AI-Rig	Skill	31	yesterday	Apache-2.0	A	39	Claude Code, Codex