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 skills add AmElmo/proofshot --skill codexgit clone --depth 1 https://github.com/AmElmo/proofshotWrote 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/amelmo/proofshot/codex)<a href="https://agentmods.dev/skills/amelmo/proofshot/codex"><img src="https://agentmods.dev/badge/skills/amelmo/proofshot/codex/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/amelmo/proofshot/codex"><img src="https://agentmods.dev/badge/skills/amelmo/proofshot/codex.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00053 | $0.00645 |
| Opus 5.5 | $0.00021 | $0.00258 |
| Sonnet 5.5 | $0.00011 | $0.00129 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
proofshot 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 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.
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.
This is a copy
95% identical to proofshot — 1 line differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ProofShot — Visual Verification Workflow
ProofShot is an open-source, agent-agnostic CLI that lets you verify your own work in a real browser — video proof, screenshots, and error reports, no vendor lock-in.
When to use
Use ProofShot after:
- Building a new UI feature or page
- Modifying existing UI components
- Fixing a visual bug
- Any change that affects what the user sees
The workflow (always follow these 3 steps)
Step 1: Start the session
proofshot start --run "your-dev-command" --port PORT --description "what you are about to verify"
This opens a browser and begins recording. If the port is already in use, proofshot will kill the existing process automatically.
Always use --run to let proofshot start and capture your dev server output (server logs appear in the proof report).
Only omit --run if the server was explicitly started by the user or another process — without it, no server logs are captured.
If a previous session was not stopped cleanly, add --force to override it.
Step 2: Drive the browser and test
Use proofshot exec to navigate, interact, and verify:
proofshot exec snapshot -i # See interactive elements
proofshot exec open http://localhost:PORT/page # Navigate to a page
proofshot exec click @e3 # Click a button
proofshot exec fill @e2 "[email protected]" # Fill a form field
proofshot exec screenshot step-NAME.png # Capture key moments
Take screenshots at important moments — these become the visual proof. Verify what you expect to see by reading the snapshot output.
Step 3: Stop and bundle the proof
proofshot stop
This stops recording, collects console + server errors, and generates a SUMMARY.md with video, screenshots, and error report.
Step 4 (optional): Post proof to the PR
proofshot pr # Auto-detect PR from current branch
proofshot pr 42 # Target a specific PR number
What ships with it
1 file 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 · 75 lines · 53 tokens per session scan A ca1dbc7ba265
proofshot is a skill published in the GitHub repository AmElmo/proofshot (866 stars, last pushed 6mo ago), licensed MIT. It adds 53 tokens to every session and 645 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 95% identical to proofshot, differing in 1 line, and is treated as a copy.
Other skills, from other repositories
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…