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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/platonai/Browser4npx agentmods add skills/platonai/browser4/maintenanceWrote 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/maintenance)<a href="https://agentmods.dev/skills/platonai/browser4/maintenance"><img src="https://agentmods.dev/badge/skills/platonai/browser4/maintenance.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 | $0.00051 | $0.02347 |
| Opus 5 | $0.00026 | $0.01174 |
| Sonnet 5 | $0.00010 | $0.00469 |
| Haiku 4.5 | $0.00005 | $0.00235 |
Grade A, and why
maintenance 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintenance
A config-driven, cross-platform maintenance system that periodically verifies
code quality, document correctness, and SKILL documentation AI-friendliness.
The orchestrator reads bin/maintenance/config.psd1, runs check scripts on a
schedule, persists results to shared state, and reports through multiple
formatters (console, JSON, markdown, GitHub annotations).
When to Use
- "run maintenance"
- "run CI checks" / "run nightly checks"
- "check code quality"
- "verify SKILL frontmatter"
- "audit documentation links"
- "check for dead code"
- "run coverage check"
- "clean up build artifacts"
- "add a new maintenance check"
- "force-run all maintenance tasks"
- "check the maintenance state"
How It Works
The orchestrator (bin/maintenance/orchestrator.ps1) is the central entry
point. It reads task definitions from config.psd1, checks the shared state
file to avoid redundant re-runs (unless -Force), executes each task with the
configured interval, collects result objects, and routes them through reporters.
Result object contract — every check script emits a PSCustomObject:
@{
CheckId = "A1"
Name = "Compilation Check"
Status = "passed" # passed | failed | skipped | error
DurationMs = 1234
ExitCode = 0
Details = "Maven + Cargo compile OK"
Results = @( @{ Item="..."; Status="passed"; Message="..." } )
Artifacts = @( "bin/maintenance/logs/A1-20260714.json" )
Timestamp = "2026-07-14T14:30:22Z"
}
Usage
All commands are run from the repository root.
Orchestrator (primary entry point)
# One pass (run pending tasks, skip if still within interval)
pwsh bin/maintenance/orchestrator.ps1 -Once
# Continuous loop (dev mode — warn only, never fails)
pwsh bin/maintenance/orchestrator.ps1
# Force all tasks regardless of last-run state
pwsh bin/maintenance/orchestrator.ps1 -Force -Once
# CI mode (strict — first failure exits 1)
MAINTENANCE_MODE=ci pwsh bin/maintenance/orchestrator.ps1 -Once
# Nightly mode (collects all failures, reports at end)
MAINTENANCE_MODE=nightly pwsh bin/maintenance/orchestrator.ps1 -Once
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 · 231 lines · 51 tokens per session scan A ae511daa6d49
maintenance is a skill published in the GitHub repository platonai/Browser4 (1,122 stars, last pushed today), licensed Apache-2.0. It adds 51 tokens to every session and 2,347 once invoked, about $0.0003 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
Run durable local Chrome automation with the installed Task Master CLI. Use when an Agent needs to create and execute a one-off browser task, follow its progress, or manage its Chrome Profile.
worker-integration
Worker-Agent integration for intelligent task dispatch and performance tracking.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.