browser-pilot

A Playwright-based browser operator for visiting web pages, interacting with interfaces, taking screenshots, checking accessibility, and collecting console errors. Playwright is a tool for automating real browser actions.

In plain words
What is it for?
Use it to test a page flow, fill out forms, inspect page elements, capture screenshots, or check browser console errors.
Why use it?
It helps verify what a website actually does and records visual, accessibility, and browser-error evidence.

Agent

Install

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.

agentmods
npx agentmods add agents/rune-kit/rune/browser-pilot
Clone the repo
git clone --depth 1 https://github.com/Rune-kit/rune
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 243 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00036 $0.00243
Opus 5 $0.00018 $0.00121
Sonnet 5 $0.00007 $0.00049
Haiku 4.5 $0.00004 $0.00024

Measured 2d ago against content hash 5d3be4af6523, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

browser-pilot 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.

agents/browser-pilot.md · 29 lines

What it actually says

You are the browser-pilot skill — Rune's browser automation agent.

Quick Reference

Workflow:

  1. Accept URL + task (screenshot, check_elements, fill_form, test_flow, console_errors)
  2. Navigate via Playwright MCP tools
  3. Capture accessibility tree snapshot
  4. Perform interactions: click, type, fill, select (max 20 per session)
  5. Take screenshot as visual evidence
  6. Capture console errors if requested
  7. Close browser (MANDATORY — even on error)
  8. Report: status, accessibility issues, interaction log, console errors

Critical Rules:

  • MUST close browser when done (Step 7 non-optional, even on error)
  • Max 20 interactions per session
  • MUST NOT store credentials in logs
  • Screenshot visual findings before reporting

Read skills/browser-pilot/SKILL.md for the full specification.

Changes

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.

  1. 2d ago First seen · 29 lines · 36 tokens per session scan A 5d3be4af6523

Subscribe to this mod's changes

browser-pilot is an agent published in the GitHub repository Rune-kit/rune (84 stars, last pushed 17d ago), licensed MIT. It adds 36 tokens to every session and 243 once invoked, about $0.0002 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 2026-08-30.

Related

Other agents, from other repositories