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 task-token-usagegit 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/task-token-usage)<a href="https://agentmods.dev/skills/platonai/browser4/task-token-usage"><img src="https://agentmods.dev/badge/skills/platonai/browser4/task-token-usage/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/task-token-usage"><img src="https://agentmods.dev/badge/skills/platonai/browser4/task-token-usage.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 | $0.00041 | $0.00718 |
| Opus 5.5 | $0.00016 | $0.00287 |
| Sonnet 5.5 | $0.00008 | $0.00144 |
| Haiku 4.5 | $0.00004 | $0.00072 |
Grade A, and why
task-token-usage 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Token Usage
Analyzes Claude Code conversation traces to report token consumption per task.
When to Use
- "list tasks with token usage"
- "show me token usage for each task"
- "how many tokens did task X use?"
- "what tasks ran in the last N hours?"
- "compare token usage across tasks"
How It Works
- Scans
~/.claude/projects/<project>/for JSONL session traces - Extracts
input_tokens,output_tokens,cache_read_input_tokensfrom each assistant message - Optionally matches sessions to draft task files in
coworker/tasks/issues/draft/ - Prints a summary table grouped by task
Usage
Run the bundled script:
python3 coworker/skills/task-token-usage/scripts/list-tasks.py [OPTIONS]
Options
| Flag | Description |
|---|---|
--recent N |
Only show sessions from last N hours (default: 24) |
-d, --detail |
Per-session breakdown instead of grouped summary |
-a, --all |
Show all sessions (no time filter) |
Examples
# Summary of last 12 hours
python3 coworker/skills/task-token-usage/scripts/list-tasks.py --recent 12
# Detailed per-session view for all time
python3 coworker/skills/task-token-usage/scripts/list-tasks.py --all --detail
# Default: last 24 hours, grouped summary
python3 coworker/skills/task-token-usage/scripts/list-tasks.py
Output Columns (Summary Mode)
| Column | Description |
|---|---|
| Task | Task name (matched from draft files or first step description) |
| Runs | Number of evaluation sessions for this task |
| In Tok | Total input tokens across all runs |
| Out Tok | Total output tokens across all runs |
| Cache | Total cache-read + cache-creation tokens |
| TOTAL | Sum of all tokens |
| Avg/run | Average total tokens per run |
Output Columns (Detail Mode)
| Column | Description |
|---|---|
| Time | When the session ended |
| Task | Matched task name |
| In | Input tokens |
| Out | Output tokens |
| CacheR | Cache-read tokens |
| TOTAL | Total tokens |
| Model | AI model used |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 91 lines · 41 tokens per session scan A 30be332fe6d8
task-token-usage is a skill published in the GitHub repository platonai/Browser4 (1,161 stars, last pushed yesterday), licensed Apache-2.0. It adds 41 tokens to every session and 718 once invoked, about $0.0002 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
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.
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.