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 forjd/agent-skills --skill browsegit clone --depth 1 https://github.com/forjd/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/forjd/agent-skills/browse)<a href="https://agentmods.dev/skills/forjd/agent-skills/browse"><img src="https://agentmods.dev/badge/skills/forjd/agent-skills/browse.svg" alt="Measured on agentmods" 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 | $0.00080 | $0.01598 |
| Opus 5 | $0.00040 | $0.00799 |
| Sonnet 5 | $0.00016 | $0.00320 |
| Haiku 4.5 | $0.00008 | $0.00160 |
Grade A, and why
browse 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 7d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browse — Browser Automation for Agents
Setup
Check if browse is installed:
browse version
If not installed, ask the user before installing. Prefer a pinned release artifact with a published checksum or signature. Do not pipe a mutable remote script directly into bash. If the user approves a convenience installer, download it to a temporary file, show the source URL, inspect or verify it where possible, then execute the local file.
How it works
browse is a CLI that wraps Playwright behind a persistent daemon on a Unix socket. The daemon cold-starts in ~3s on first use, then every command runs in sub-200ms. Session state (cookies, localStorage, auth tokens) persists across commands within a session.
All output is plain text. Objects are JSON-stringified. Commands return non-zero on failure with an error message.
Important constraints:
- Commands are sequential — do not run multiple
browsecommands in parallel. The daemon handles one command at a time. - Run
browse helpfor the full command list, orbrowse help <command>for detailed usage and flags.
The ref system — read this first
Refs (@e1, @e2, ...) are how you target elements. They replace CSS selectors for most interactions.
Rules:
- Always
browse snapshotbefore interacting. Refs only exist after a snapshot. - Refs are ephemeral. Every
snapshotcall regenerates them. Old refs are invalid. - Refs go stale after navigation. Any
gotoor click that changes the page invalidates refs. You'll get a clear error — justbrowse snapshotagain.
Core interaction loop:
browse snapshot # see what's on the page — get refs
browse fill @e3 "test" # fill the search field
browse click @e4 # click a button
browse snapshot # re-snapshot after the page changes
Workflow
The standard pattern for any browser task:
- Navigate:
browse goto <url> - Observe:
browse snapshotfor page structure (interactive elements with refs). Usebrowse snapshot -ito include structural elements (headings, text), or-ffor the full accessibility tree. - Check for errors:
browse console --level errorafter navigation. - Interact:
browse fill @eN "value",browse click @eN,browse hover @eN,browse press Tab,browse select @eN "option",browse scroll @eN(scroll into view).- Use
browse press <key>for keyboard navigation (Tab, Escape, Enter, ArrowDown, Shift+Tab, etc.). Multiple keys:browse press Tab Tab Tab. - Use
browse scroll down/upto page through content,browse scroll top/bottomto jump to extremes. - After clicks that trigger SPA navigation, use
browse wait url /path,browse wait text "Expected", orbrowse wait visible .selectorbefore snapshotting.
- Use
- Verify:
browse snapshotorbrowse screenshotafter each interaction to confirm the result. - Repeat: Move through pages and flows.
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.
- 7d ago First seen · 136 lines · 80 tokens per session scan A b3aa87978e89
browse is a skill published in the GitHub repository forjd/agent-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 80 tokens to every session and 1,598 once invoked, about $0.0004 per session on Opus 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
playwright-recording
Record browser interactions as video using Playwright. Use for capturing demo videos, app walkthroughs, and UI flows for Remotion videos. Triggers include recording a demo, capturing browser video, screen recording a website, or creating walkthrough footage.
unix_computer_use
Local and remote desktop observation/input tools with coordinate normalization (local macOS/Linux by default; optional OSWorld HTTP and SSH Mac backends).
memstack-development-webapp-testing
Use when the user says 'write browser tests', 'test this page', 'playwright test', 'e2e test', 'end to end test', 'browser test', 'test the UI', or needs Playwright-based browser testing for a web application. Do NOT use for unit tests, API tests, or non-browser testing.
ask-opencli
A helper for asking Grok or Gemini through OpenCLI, which uses an already signed-in Chrome browser session instead of a paid API.
browser-doctor
Read-only health check on browser-control setup. Verifies browser binary, Playwright MCP Bridge extension presence, token file mode/contents, AIWG MCP registration, provider config injection, and optional workspace allow-list. Outputs pass/fail per check with remediation commands.
e2e
Generate and run Playwright E2E tests traced to spec.md acceptance criteria, with an optional accessibility audit. Use when saying "e2e tests" or "a11y audit".