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 agentmods add skills/platonai/browser4/browser4-codingnpx skills add platonai/Browser4 --skill browser4-codinggit clone --depth 1 https://github.com/platonai/Browser4What 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 | $0.00088 | $0.03281 |
| Opus 5 | $0.00044 | $0.01640 |
| Sonnet 5 | $0.00018 | $0.00656 |
| Haiku 4.5 | $0.00009 | $0.00328 |
Grade A, and why
browser4-coding 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 yesterday.
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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
browser4-coding
Quick Start
Create and validate a plugin, or a skill:
coding.scaffold(type="plugin", pluginName="My Plugin", domain="media",
basePackage="ai.platon.pulsar.myplugin",
toolMethod="detectMedia", toolDescription="Detect media on the page")
coding.validate(type="plugin", path="browser4-plugins/browser4-myplugin")
coding.scaffold(type="skill", name="my-skill", description="What it does")
coding.validate(type="skill", path="skills/my-skill/SKILL.md")
For self-development work (modifying Browser4 itself), start with coding.scaffoldFlow — see Workflows below.
The programming-agent kernel for Browser4: sandboxed shell + filesystem, artifact scaffolding/validation (plugins, skills, browser JS, scripts), and a full self-development toolset for modifying Browser4's own code (live module graph, impact analysis, Maven builds with structured diagnostics, CDP pitfall awareness, high-level dev-task planning).
When to Use
- User wants to create a new Browser4 plugin, skill (SKILL.md), browser JS script, or build/deploy/run script
- User wants to validate any of the above
- User wants to modify Browser4's own code (Kotlin modules, Rust CLI, poms) — use the self-development tools below
- User wants to check repo governance (versions, module registration) or the CDP pitfalls before editing the browser driver
How It Works
The coding tools fall into three layers: artifact tools generate and validate plugins, skills, JS, and scripts (templates from real code so they never go stale); self-development tools inspect and modify Browser4 itself (live module graph, impact analysis, Maven builds, CDP trap checks); and shell/filesystem tools provide a sandboxed environment for anything else.
Patterns
1. Create and validate a new plugin
coding.scaffold(type="plugin", pluginName="...", domain="...", basePackage="...", toolMethod="...", toolDescription="...")
coding.validate(type="plugin", path="browser4-plugins/browser4-xxx")
coding.mvnBuild(module="browser4-plugins/browser4-xxx")
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.
- yesterday First seen · 210 lines · 88 tokens per session scan A faab6af06f5a
browser4-coding is a skill published in the GitHub repository platonai/Browser4 (1,114 stars, last pushed 2d ago), licensed Apache-2.0. It adds 88 tokens to every session and 3,281 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 2026-08-30.
Other skills, from other repositories
eric-task-master
Install, connect, and use Eric Task Master for durable Playwright browser jobs with persistent or ephemeral Profiles, live fast-auto-human behavior control, task queues, progress health, semantic diagnostics, recovery, artifacts, and composable Task Packs.
browserstack
../../../engineering-team/playwright-pro/skills/browserstack/SKILL.md.
analyze-performance-traces
Analyze Chrome, Chromium, Electron, React DevTools, or Perfetto-compatible JSON traces and audit user-reported profiling findings without loading large artifacts into context; prove trigger-to-render/layout chains, separate measured facts from source inference, find exact code choke points, classify forced layout and…
feature-demo-recording
Record a demo video of a web feature from a real browser. Two modes -- a NARRATED film where measured voiceover drives the timeline (designed slides, subtitles, punch-in camera, rendered from an HTML timeline), and a SILENT evidence clip for a PR or a QA pass. Use when the user asks to record a video, demo, or screen…
browser-recording
Record a browser flow as a video/GIF for evidence — animations, transitions, and multi-step interactions that a still screenshot cannot prove. Drives the project's own Playwright through a bundled runner, then converts to mp4 + GIF via ffmpeg. Use when the user asks to record a demo, capture a GIF or video of the UI…
web-verify
Look at your OWN front-end change before claiming it works -- navigate the loopback URL of a dev server or pod you started, screenshot the surface you changed, read the image to judge it, and embed it in chat. Three capture backends: playwright-cli (the session the dashboard Browser panel shows), the agent-browser CLI…