Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/alexei-led/cc-thingznpx agentmods add skills/alexei-led/cc-thingz/browser-automationWrote 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/alexei-led/cc-thingz/browser-automation)<a href="https://agentmods.dev/skills/alexei-led/cc-thingz/browser-automation"><img src="https://agentmods.dev/badge/skills/alexei-led/cc-thingz/browser-automation/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/alexei-led/cc-thingz/browser-automation"><img src="https://agentmods.dev/badge/skills/alexei-led/cc-thingz/browser-automation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 35 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00083 | $0.00872 |
| Opus 5 | $0.00042 | $0.00436 |
| Sonnet 5 | $0.00017 | $0.00174 |
| Haiku 4.5 | $0.00008 | $0.00087 |
Grade A, and why
browser-automation scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
tests where curl, unit tests, or JSDOM is cheaper.' How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Automation
Use a real browser only when rendered behavior matters: UI state, navigation, forms, auth, screenshots, recordings, accessibility, visual checks, or end-to-end flows.
Keep automation temporary unless the user asks for permanent tests. Do not use a browser for plain HTTP API checks or pure logic tests.
Runtime Selection
- Prefer a platform built-in browser tool when available in the active tool
list. See
references/platform-browser-tools.md. - Use the project's configured browser runner when it exists.
- Use
playwright-skillonly as the bundled fallback/runtime reference. - If no runtime is available, report blocked with the missing tool/package.
Use the cheapest runtime that proves the claim.
Workflow
- Define the goal: explore, validate, screenshot, record, debug, or test.
- Read needed local context: start scripts, browser config, routes, fixtures, seed/reset docs, and auth notes.
- Detect or start the dev server. Reuse a reachable server.
- Use deterministic data: seeded users, fixed dates, stable IDs, reset state, and mocked external services.
- Drive with semantic targets first: role, label, text, test id; CSS last.
- Capture artifacts needed to support the result: screenshot, trace, console errors, network failures, accessibility snapshot, manifest, or report.
- Prefer screenshot/manifest evidence for visual checks in headless harnesses.
- Report pass, fail, or blocked. Do not imply success if the check did not run.
Playwright Fallback
Use Playwright when no built-in browser tool exists, the project already uses Playwright, or a repeatable script/test is the best artifact.
If using the bundled helper, load playwright-skill for exact setup and
invocation. Use its turnkey screenshot helpers before writing custom batch
scripts:
node scripts/screenshot-url.js --url <url> --selector <ready-selector> --json
node scripts/screenshot-sequence.js --url-template '<url/{n}>' --from 1 --to 10 --json
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.
- 9d ago First seen · 94 lines · 83 tokens per session scan A ae698e8d13da
browser-automation is a skill published in the GitHub repository alexei-led/cc-thingz (35 stars, last pushed today), licensed MIT. It adds 83 tokens to every session and 872 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ring:visualizing
Generating self-contained, Lerian-branded HTML artifacts — D2 diagrams, comparison tables/matrices, code diffs, dashboards, slide decks, and plan/diff/recap reviews — from mandatory templates, then opening them in the browser. Use for architecture overviews, any table with 4+ rows or 3+ columns, slide presentations…
ui-control
Verify graphical browser, desktop, or Electron behavior through the actual interface. Use when screenshot, accessibility, console, network, trace, or browser-driven evidence is required; exclude terminal-hosted interfaces.
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.