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 Kripu77/software-factory --skill browser-usegit clone --depth 1 https://github.com/Kripu77/software-factoryWrote 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/kripu77/software-factory/browser-use)<a href="https://agentmods.dev/skills/kripu77/software-factory/browser-use"><img src="https://agentmods.dev/badge/skills/kripu77/software-factory/browser-use/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/kripu77/software-factory/browser-use"><img src="https://agentmods.dev/badge/skills/kripu77/software-factory/browser-use.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 | $0.00040 | $0.00387 |
| Opus 5.5 | $0.00016 | $0.00155 |
| Sonnet 5.5 | $0.00008 | $0.00077 |
| Haiku 4.5 | $0.00004 | $0.00039 |
Grade A, and why
browser-use 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.
What it actually says
Browser use
Trigger
Need to test a running web app by actually using it. No smoke suite, or the suite does not cover this flow.
Navigate, click, fill, screenshot, assert. Use the harness browser.
How to drive the browser
Pick the door the runner actually has, in this order:
- A first-party browser tool on this harness (Grok Bot browserUse, Grok Build browser, Claude computer use).
- Headed Playwright against the given URL, if Playwright is already in the checkout.
- Stop and say the harness has no browser.
Do not invent a headless stack. Do not scrape cookies out of a profile to skip login.
Workflow
- Resolve the target URL (dispatched, or local app for the repo). Confirm it is up before clicking.
- Walk the flow as a user. One path. Screenshot each meaningful step.
- Assert what the user would see: copy, state, error, navigation.
- If login or 2FA is required, stop and hand that step to a human. Never ask for a password in chat. Never read
.env. - Report. Repro, screenshots, what broke, what was fine.
Guardrails
- Report only. Do not patch product code.
- Prefer a real click over injecting JS.
- Deterministic waits for visible state, not sleep.
- Stay on the dispatched flow. Do not wander the whole site.
- Never merge.
Output
- Flow walked
- Screenshots of evidence
- Failures with repro steps
- Anything that could not be tested (auth wall, downed app)
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 · 46 lines · 40 tokens per session scan A 0802900f8bca
browser-use is a skill published in the GitHub repository Kripu77/software-factory (7 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 387 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 2026-08-31.
Other skills, from other repositories
test-site
Tests a deployed, activated Power Pages site at runtime using browser-based navigation, page crawling, and API request verification via Playwright. Use when the user wants to test, verify, or smoke-test their deployed site.
qa
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).
browser-check
Drive a real browser and come back with a MEASUREMENT rather than an impression - console errors and >=400 responses as counts, computed styles as JSON when appearance is disputed. Use when work touches UI, when a review must verify one, or when fidelity-gate asks for its measurement.
peekaboo-driver
Use this skill when driving native-UI AX-tree snapshots and screenshots via steipete/peekaboo (MIT, macOS-only). Dispatched by skills/test-runner/ to capture native-UI AX-tree snapshots + screenshots on macOS 15+ targets, and exits with deterministic JSON output the orchestrator can parse.
playwright-driver
Use this skill when executing web tests via the canonical playwright npm package (Microsoft, Apache-2.0). Dispatched by skills/test-runner/ to execute web tests against a target, captures token-frugal AX-tree snapshots + screenshots + console output under .orchestrator/metrics/test-runs/ /, and exits with…
browser-qa-report
Runs a read-only browser QA pass and returns evidence.