Borrowing it
Nothing to install: this file belongs to warpdotdev-demos/cloud-factory-demo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/warpdotdev-demos/cloud-factory-demo/main/.agents/skills/verify-behavior/SKILL.mdgit clone --depth 1 https://github.com/warpdotdev-demos/cloud-factory-demoWrote 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/warpdotdev-demos/cloud-factory-demo/verify-behavior)<a href="https://agentmods.dev/skills/warpdotdev-demos/cloud-factory-demo/verify-behavior"><img src="https://agentmods.dev/badge/skills/warpdotdev-demos/cloud-factory-demo/verify-behavior/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/warpdotdev-demos/cloud-factory-demo/verify-behavior"><img src="https://agentmods.dev/badge/skills/warpdotdev-demos/cloud-factory-demo/verify-behavior.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00069 | $0.01942 |
| Opus 5.5 | $0.00028 | $0.00777 |
| Sonnet 5.5 | $0.00014 | $0.00388 |
| Haiku 4.5 | $0.00007 | $0.00194 |
Grade A, and why
verify-behavior 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 2mo 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify behavior
Prove or disprove visible product behavior for bugs and greenfield features. Parents (triage, implementation, review) invoke this instead of driving the UI themselves.
Modes
reproduce— does the reported bug still happen on baseline? (usually default branch; triage)verify— does the implemented change match expected behavior? (features and fixes; implementation/review)
Infer if unnamed: issue-only → reproduce; implementation/PR branch → verify.
Platform contract (do not invent alternatives)
Oz computer use is a dedicated capability, not a generic remote child and not a set of parent-callable capture APIs.
| Layer | What happens |
|---|---|
| Outer Oz cloud run | Must already have computer use enabled (computer_use: true / --computer-use / computer_use_enabled: true). Factory implement workflows set this on the parent run. |
| Parent / orchestrator | Delegates GUI work through the platform computer_use capability with a concrete task and expected evidence. |
| Permission | request_computer_use is emitted automatically when the computer-use subagent starts. Parents must not call it, simulate it, or document fake tool calls for it. |
| Computer-use subagent | Native prompt already covers GUI actions, proactive start_recording / stop_recording, report_screenshot, and forbids ffmpeg / screen-capture CLIs. Do not re-teach capture plumbing or shell out to recorders. |
Never:
- Call or invent direct
request_computer_use,start_recording, orstop_recordingfrom the parent LLM - Launch generic
run_agentsremote children as a substitute forcomputer_use - Build custom recorder pipelines (ffmpeg, x11grab, avfoundation, Playwright video, etc.)
- Claim
gh ... --attachcan upload Oz videos to GitHub (it cannot reliably attach native Oz recordings)
When to use / skip
Use for UI, browser, desktop, mobile, or other interactive behavior where visual proof helps.
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.
- 2mo ago First seen · 135 lines · 69 tokens per session scan A f37aa2cd7628
verify-behavior is a skill published in the GitHub repository warpdotdev-demos/cloud-factory-demo (405 stars, last pushed 2mo ago), licensed MIT. It adds 69 tokens to every session and 1,942 once invoked, about $0.0003 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 2026-08-30.
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".
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.
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.
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…