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/lexmount/browseruse-agent-bench/create-prnpx skills add lexmount/browseruse-agent-bench --skill create-prgit clone --depth 1 https://github.com/lexmount/browseruse-agent-benchWhat 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 | $0.00026 | $0.00564 |
| Opus 5 | $0.00013 | $0.00282 |
| Sonnet 5 | $0.00005 | $0.00113 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
create-pr scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Create Pull Request
Create a draft GitHub pull request for this repository using gh.
Prerequisites
ghis installed and authenticated.- Your branch is pushed to origin.
- You are in the repository root.
PR Title Format
Use conventional commit style:
<type>(<scope>): <summary>
Types
feat: New featurefix: Bug fixperf: Performance improvementrefactor: Refactor without behavior changedocs: Documentation onlytest: Tests onlybuild: Build/dependency changesci: CI workflow/config changeschore: Maintenance tasks
Scope Suggestions
corecliagentsbenchmarksdocsskills
Summary Rules
- Imperative present tense (for example:
Add,Fix,Refactor) - Start with capital letter
- No trailing period
- Keep it specific and concise
Workflow
- Inspect local changes:
git status
git diff --stat
git log origin/main..HEAD --oneline
- Decide title components:
- Type
- Scope
- Summary
- Push branch if needed:
git push -u origin HEAD
- Create draft PR:
gh pr create \
--draft \
--base main \
--title "<type>(<scope>): <summary>" \
--body "$(cat <<'PRBODY'
## Summary
- What changed
- Why it changed
## Testing
- [ ] `uv run ruff check .`
- [ ] `uv run pytest`
## Related
- Optional: `closes #<issue-number>`
PRBODY
)"
Body Guidelines
Summary: explain behavior change and key files touched.Testing: list commands actually run.Related: reference GitHub issues when available.
Examples
fix(cli): Propagate skills command exit code
docs(benchmarks): Correct LexBench split filenames
refactor(agents): Guard duplicate agent registration names
Validation Checklist
- Title follows
<type>(<scope>): <summary>. - Summary accurately reflects the patch.
- Testing section contains real commands/results.
- Related issue links are included when relevant.
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.
- 2d ago First seen · 125 lines · 26 tokens per session scan A a266059d395a
create-pr is a skill published in the GitHub repository lexmount/browseruse-agent-bench (19 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 26 tokens to every session and 564 once invoked, about $0.0001 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
agent-browser
Browse the web for any task — research topics, read articles, interact with web apps, fill forms, take screenshots, extract data, and test web pages. Use whenever a browser would be useful, not just when the user explicitly asks.
dingtalk_channel_connect
Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.
browser_cdp
当用户明确希望连接到已运行的 Chrome 浏览器、扫描本地 CDP 端口、显式指定 cdpport，或让多个 agent / 工具共享同一个浏览器时，使用本 skill。browser 默认不开放调试端口；仅当用户明确希望其他本地工具附加时才显式传入 cdpport。.
browser_visible
当用户需要控制 browser 的浏览器启动方式时，使用本 skill。browser 默认由 Playwright 直接管理、不开放调试端口（需让其他本地工具附加时显式传 cdpport）；headed 控制是否显示窗口，privatemode 保留用于兼容、不再改变默认行为，browserargs 传入额外的 Chromium 启动参数，executablepath 指定自定义浏览器可执行文件路径。.
browser_visible
Use this skill when the user needs to control the browser launch mode for browser. By default browser is managed by Playwright and opens no debugging port (pass an explicit cdpport to let another local tool attach); headed controls whether the window is visible, and privatemode is kept for backward compatibility and…
browser
Drive a live browser with async Python against QwenPaw's builtin Browser SDK. The full reference is below; re-load this browser skill after context compaction.