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 sudoprivacy/sudocode --skill browsergit clone --depth 1 https://github.com/sudoprivacy/sudocodeWrote 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/sudoprivacy/sudocode/browser)<a href="https://agentmods.dev/skills/sudoprivacy/sudocode/browser"><img src="https://agentmods.dev/badge/skills/sudoprivacy/sudocode/browser/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/sudoprivacy/sudocode/browser"><img src="https://agentmods.dev/badge/skills/sudoprivacy/sudocode/browser.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 | $0.00020 | $0.00374 |
| Opus 5.5 | $0.00008 | $0.00150 |
| Sonnet 5.5 | $0.00004 | $0.00075 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
browser 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 21d 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
Browser
Use the installed ai-dev-browser package. Its CLI modules are generated from
ai_dev_browser.core; use the same functions for Python automation.
Install the package in your Python environment before invoking the tools.
Discover commands
python3 -m ai_dev_browser.tools.browser_start --help
python3 -m ai_dev_browser.tools.page_discover --help
Quick-start examples
python3 -m ai_dev_browser.tools.browser_start
python3 -m ai_dev_browser.tools.page_goto --session-id <returned-id> --url https://example.com
python3 -m ai_dev_browser.tools.page_discover --session-id <returned-id>
python3 -m ai_dev_browser.tools.click_by_text --session-id <returned-id> --text "Sign in"
python3 -m ai_dev_browser.tools.page_screenshot --session-id <returned-id> --path screenshot.png
python3 -m ai_dev_browser.tools.browser_stop --session-id <returned-id>
Choose headless/headful from the task and user preference; use browser_connect
to attach to an existing browser. Connecting preserves its current mode.
Use the session identity returned by start/connect for subsequent commands.
browser_stop closes an owned browser; use browser_disconnect to release
control of an attached browser while preserving its windows and tabs. Consult
--help for the selected tool before configuring transport or profile settings.
To inspect screenshot pixels, use scode's Read tool on the saved image.
The same operations are available from Python:
from ai_dev_browser.core import page_goto, click_by_text, page_discover
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.
- 21d ago Changed · +9 lines · -6 tokens per session 1524708080b3
- 2mo ago First seen · 34 lines · 26 tokens per session scan A 4c42787fd6de
browser is a skill published in the GitHub repository sudoprivacy/sudocode (522 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 374 once invoked, about $0.0001 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.
browser compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| browsersudoprivacy/sudocode | Skill | 522 | today | MIT | A | 20 | Claude Code, Codex |
| interactive-loginyc-software/qm | Skill | 16k | today | MIT | A | 46 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |
| azure-messaging-webpubsub-javamicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 43 | Claude Code |
| cua-driverdavidondrej/skills | Skill | 4.3k | 3d ago | MIT | A | 68 | Claude Code, Codex |
| open-design-browsercompozy/compozy | Skill | 2.8k | today | MIT | A | 56 | Claude Code, Codex |
| southwestborski/travel-hacking-toolkit | Skill | 895 | today | MIT | A | 40 | Claude Code |