Browser4 is an AI-native browser engine that lets autonomous agents and people control real browsers, extract information from web pages, and automate tasks at scale. It combines browser interaction through a Rust CLI and MCP with deterministic selectors, machine-learning clustering, and language-model extraction. The catalogue entries provide skills and instructions for using Browser4.
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 platonai/Browser4 --skill browser4-fix-buggit clone --depth 1 https://github.com/platonai/Browser4Wrote 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/platonai/browser4/browser4-fix-bug)<a href="https://agentmods.dev/skills/platonai/browser4/browser4-fix-bug"><img src="https://agentmods.dev/badge/skills/platonai/browser4/browser4-fix-bug/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/platonai/browser4/browser4-fix-bug"><img src="https://agentmods.dev/badge/skills/platonai/browser4/browser4-fix-bug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00078 | $0.01568 |
| Opus 5.5 | $0.00031 | $0.00627 |
| Sonnet 5.5 | $0.00016 | $0.00314 |
| Haiku 4.5 | $0.00008 | $0.00157 |
Grade A, and why
browser4-fix-bug 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 1mo 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
browser4-fix-bug
Quick Start
coding.shell(command="mvn -pl <module> -am compile -DskipTests") # 1. reproduce the error
coding.readLines(path=<file>, startLine=<line-8>, endLine=<line+8>) # 2. read the failing code
coding.replace(path=<file>, old="...", new="...") # 3. smallest possible edit
coding.shell(command="mvn -pl <module> -am compile -DskipTests") # 4. re-verify until green
Drive a bug from "it fails" to "it passes" with a disciplined compile-test-fix loop. Never guess — read the actual error, make the smallest edit, and re-verify.
When to Use
- User reports a build/compile failure or a failing test
- A plugin, skill script, JS, or shell script errors at runtime
- User says "fix this error", "the build is broken", "tests fail", "it crashes"
- LSP diagnostics (
coding.diagnostics) report errors in a file
How It Works
The compile-test-fix loop is error-driven: reproduce the failure, read the exact error, locate the faulty lines with minimal context, make the smallest possible edit, and re-verify. Never guess — every iteration starts from the actual error output.
Patterns
1. Build/compile failure
coding.shell(command="mvn -pl <module> -am compile -DskipTests")
coding.readLines(path=<file>, startLine=<line-8>, endLine=<line+8>)
coding.replace(path=<file>, old="...", new="...")
coding.shell(command="mvn -pl <module> -am compile -DskipTests")
2. Failing test
coding.shell(command="mvn test -pl <module> -Dtest=<TestClass>")
coding.readLines(path=<test-file>, startLine=<line-8>, endLine=<line+8>)
coding.replace(path=<file>, old="...", new="...")
3. Runtime error in plugin/script
coding.diagnostics(path=<file>)
coding.readLines(path=<file>, startLine=<line-8>, endLine=<line+8>)
coding.replace(path=<file>, old="...", new="...")
Flags
coding tools take structured arguments, not CLI flags — see Workflow below for each tool's parameters.
Errors & Recovery
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.
- 1mo ago First seen · 143 lines · 78 tokens per session scan A 34f7088d7f07
browser4-fix-bug is a skill published in the GitHub repository platonai/Browser4 (1,161 stars, last pushed yesterday), licensed Apache-2.0. It adds 78 tokens to every session and 1,568 once invoked, about $0.0003 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
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
cvm-ai-doctor
A health-diagnosis workflow for servers, computers, virtual machines, and containers on Linux, macOS, or Windows.
rubber-duck
Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…
ios-simulator
Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.
hns-lsel-curator
Local Self-Evolution Loop (LSEL) curator — the CLUSTER + drain engine for the GOOS-local PROPOSE→APPLY seam closure (SPEC-LSEL-LOCAL-EVOLUTION-001). Companion-offset drain of .moai/lessons-inbox.jsonl with a drain-side severity filter that drops the 65% Bash-timeout/sandbox noise, eventkey clustering with a frequency…
ai-discover
Read-only discovery step of the auto-improvement loop. One bounded agent turn per cycle reads the focus files (Read/Grep/Glob only, no shell, no subagents) and replies with a JSON array of testable surfaces {file, line, symbol, rule, message, hypothesis}; the spine authors fixes and verifies them. Discovery only — no…