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 joao-aires/agent-skills-public --skill browser-extension-testinggit clone --depth 1 https://github.com/joao-aires/agent-skills-publicWrote 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/joao-aires/agent-skills-public/browser-extension-testing)<a href="https://agentmods.dev/skills/joao-aires/agent-skills-public/browser-extension-testing"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/browser-extension-testing/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/joao-aires/agent-skills-public/browser-extension-testing"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/browser-extension-testing.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 | $0.00042 | $0.00962 |
| Opus 5.5 | $0.00017 | $0.00385 |
| Sonnet 5.5 | $0.00008 | $0.00192 |
| Haiku 4.5 | $0.00004 | $0.00096 |
Grade A, and why
browser-extension-testing 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 2d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test the boundary the user depends on
Start with the changed behavior, supported Chrome versions, existing test runner and available execution target. Preserve Jest, Vitest, Playwright or Puppeteer where they already meet the need. A stack-specific example is not a reason to replace the application's suite. Build meaningful acceptance around observable effects, including denial and lifecycle behavior that the change can affect.
Separate evidence levels
| Level | What it can establish | What remains outside it |
|---|---|---|
| Unit/API mocks | Parsing, state transitions, permission/error handling and message construction | Browser grants, isolated worlds, actual worker termination or Chrome API behavior |
| Component/stories | Rendered states, keyboard interaction, shared tokens and overlays in that setup | Browser toolbar activation, popup dismissal and installed permissions |
| Loaded production extension | Integration of packaged manifest/resources and real extension contexts | Store acceptance, other browsers or a signed store-delivered update |
| Real surface/journey | Actual invocation, page effects, closure/reopening and relevant persisted outcomes | Untested OS/browser variants or external services replaced by fixtures |
Opening chrome-extension://.../popup.html in a normal tab is useful for component integration but does not reproduce the toolbar popup's destruction or an activeTab invocation grant. Check the actual surface when those behaviors matter. Do not convert a missing driver into a passing claim; complete independent checks and record the exact remaining boundary.
Prepare a compatible isolated browser
Read runtime drivers and lifecycle checks before writing browser tests. Use a disposable profile, local controlled pages/providers and the production build directory. Record driver/browser versions and artifact identity. Do not load into a personal browser profile, reuse account sessions or disable sandboxing by default.
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.
- 2d ago First seen · 53 lines · 42 tokens per session scan A cda8582c65f9
browser-extension-testing is a skill published in the GitHub repository joao-aires/agent-skills-public (2 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 962 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 2026-10-24.
Other skills, from other repositories
test-conversion-researcher
Researcher for converting unit tests to browser tests for Project Bedrock. Invoke this when the user needs to understand the current codebase behavior while removing complex Browser dependencies from tests.
06-test
Write and iterate developer-side tests until they pass, or validate a user journey end to end in the browser during implementation. Use when the user wants to add coverage, find what's untested, or walk a flow while building it. Do NOT use for independent acceptance QA or reviewer evidence, auditing test health, or…
aif-web-testing
Test web apps with Playwright, Vitest and k6: E2E, unit, integration, load, security, visual and a11y.
chrome-ext-testing
This skill should be used when writing or setting up tests for a Chrome extension. Trigger when: "test chrome extension", "extension unit test", "extension e2e test", "Vitest extension", "Playwright extension", "@webext-core/fake-browser", "test content script", "test service worker", "test messaging", "test storage"…
hs-test
Provide executable feedback on changed behavior with the smallest relevant white-box or black-box probe, then classify the result and report real evidence. Diagnose failures against accepted intent, domain rules, and current implementation before deciding whether code, tests, fixtures, or environment are wrong. Use…
webapp-testing
Write and run comprehensive web app tests — unit, integration, E2E with Playwright/Cypress, and visual regression.