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 hugobowne/show-us-your-agent-skills --skill verified-frontendgit clone --depth 1 https://github.com/hugobowne/show-us-your-agent-skillsWrote 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/hugobowne/show-us-your-agent-skills/verified-frontend)<a href="https://agentmods.dev/skills/hugobowne/show-us-your-agent-skills/verified-frontend"><img src="https://agentmods.dev/badge/skills/hugobowne/show-us-your-agent-skills/verified-frontend/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/hugobowne/show-us-your-agent-skills/verified-frontend"><img src="https://agentmods.dev/badge/skills/hugobowne/show-us-your-agent-skills/verified-frontend.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 | $0.00050 | $0.00759 |
| Opus 5.5 | $0.00020 | $0.00304 |
| Sonnet 5.5 | $0.00010 | $0.00152 |
| Haiku 4.5 | $0.00005 | $0.00076 |
Grade A, and why
verified-frontend 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build a local verified frontend skill
This is the shape of a skill, not Chip Huyen's original skill and not a universal set of commands. Work with the human to build the version that fits their project. Do not pretend the example decisions below are already true in their environment.
Start with the project
Inspect the repository before asking questions. Find the frontend framework, start command, local URL, existing browser or end-to-end test tools, CI setup, contribution guidance, and any visual or accessibility standards already recorded.
Bring the human concrete findings and ask only for the decisions the repository cannot answer:
- Which interfaces, routes, and states need visual verification?
- Which environments do they use, such as a desktop agent, terminal, remote runner, or CI?
- Which browser tool should the agent use in each environment?
- Which viewport sizes or breakpoints matter?
- What should the agent look for beyond obvious breakage?
- Which screenshots should be returned, and where should they go?
Do not turn this into a generic questionnaire. Build the first version around one real frontend change and refine it with the human.
Make environment selection deterministic
If the browser mechanism changes by environment, encode that choice in a script or configuration the project can run reliably. Do not make every agent infer the environment from prose on every task.
The local version should name:
- How to identify each supported environment.
- How to start or connect to the application.
- How to open and control a browser there.
- What to do when the required browser is unavailable.
Keep credentials, machine-specific paths, and private URLs out of the skill.
Define the verification loop
For every task that changes a user-facing interface:
- Run the application in the appropriate environment.
- Open each affected route and state at the required viewports.
- Inspect the rendered result, including layout, spacing, type, color, overflow, clipping, loading, empty, error, and interactive states that the change affects.
- Fix visible problems in the implementation.
- Render and inspect the page again after each material fix.
- Capture the evidence agreed with the human.
- Run the project's normal code, test, and accessibility checks.
What ships with it
2 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.
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 · 71 lines · 50 tokens per session scan A 577653ef18c5
verified-frontend is a skill published in the GitHub repository hugobowne/show-us-your-agent-skills (70 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 759 once invoked, about $0.0002 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
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
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.
critique
Adversarial design critique of the current work. Render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.