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 TasiTech/tasi-harness --skill embedded-browser-operatorgit clone --depth 1 https://github.com/TasiTech/tasi-harnessWrote 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/tasitech/tasi-harness/embedded-browser-operator)<a href="https://agentmods.dev/skills/tasitech/tasi-harness/embedded-browser-operator"><img src="https://agentmods.dev/badge/skills/tasitech/tasi-harness/embedded-browser-operator/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/tasitech/tasi-harness/embedded-browser-operator"><img src="https://agentmods.dev/badge/skills/tasitech/tasi-harness/embedded-browser-operator.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 | $0.00033 | $0.00846 |
| Opus 5.5 | $0.00013 | $0.00338 |
| Sonnet 5.5 | $0.00007 | $0.00169 |
| Haiku 4.5 | $0.00003 | $0.00085 |
Grade A, and why
embedded-browser-operator 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Embedded Browser Operator
Use this skill when the user needs web actions through Tasi Harness browser automation.
Tooling
Use these browser tools:
browser_opento navigate to a URL.browser_snapshotto get the default accessibility/semantic tree with@erefs, roles, names, states, links, headings, images, and viewport data.browser_findto locate elements by role, text, label, placeholder, alt text, title, test id, or CSS and optionally act on the match.browser_click,browser_type,browser_hover,browser_select,browser_check, andbrowser_pressto interact with controls. Use@erefs frombrowser_snapshotwhen available.browser_waitto wait for selectors, visible/hidden/detached state, text, URL glob, load state, JavaScript condition, or a short delay after navigation.browser_scrollto load lazy content; it can scroll the page or a scrollable selector/ref.browser_extractto capture text, HTML, or structured JSON from the full page or a selector/ref.browser_screenshotandbrowser_pdfto save visual evidence or a printable copy inside the workspace.browser_storage,browser_cookies,browser_console, andbrowser_networkto inspect storage, cookies, console/page errors, and resource timing/network data.browser_evalfor bounded page-side JavaScript inspection when the dedicated tools do not expose the needed data.browser_viewportto resize the browser for responsive checks.browser_stateto verify current page location.browser_closeto reset the browser session.
Reliable Workflow
- Open with
browser_open. - Confirm state with
browser_stateif navigation is ambiguous. - Use
browser_snapshotto read the accessibility tree, identify controls, and collect@erefs. - Wait for critical selectors/text/URL/load state before clicking or typing.
- Prefer
browser_findor@erefs over brittle positional CSS selectors. - Extract structured content with
browser_extractand preferformat=jsonfor page data you want to normalize. - Use console/network/storage/cookie tools when debugging failed interactions, auth state, SPA/API behavior, or missing data.
- Keep extraction bounded with
max_charsand iterate if more detail is needed.
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 · 57 lines · 33 tokens per session scan A c0ee88f85313
embedded-browser-operator is a skill published in the GitHub repository TasiTech/tasi-harness (11 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 846 once invoked, about $0.0001 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
interactive-login
Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
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.
open-design-browser
Inspect and exercise local HTML design artifacts and library prototype previews with the existing agent-browser CLI, including screenshots, interaction checks, and rendered DOM snapshots. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser…
browser_cdp
A health check for Python code that produces a score, letter grade, and measures of issues such as complexity, duplication, dead code, dependencies, and architecture.