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/stickerdaniel/browserjacknpx agentmods add skills/stickerdaniel/browserjack/setupWrote 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/stickerdaniel/browserjack/setup)<a href="https://agentmods.dev/skills/stickerdaniel/browserjack/setup"><img src="https://agentmods.dev/badge/skills/stickerdaniel/browserjack/setup/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/stickerdaniel/browserjack/setup"><img src="https://agentmods.dev/badge/skills/stickerdaniel/browserjack/setup.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00013 | $0.00157 |
| Opus 5.5 | $0.00005 | $0.00063 |
| Sonnet 5.5 | $0.00003 | $0.00031 |
| Haiku 4.5 | $0.00001 | $0.00016 |
Grade A, and why
setup 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 18d 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
Explain the trust boundary before installation: the bridge can control authenticated browser sessions, uses undocumented local OpenAI interfaces, and is currently an experimental macOS developer preview.
For a published release, install an exact reviewed version:
npx --yes [email protected] setup --client plugin --scope user
For a source checkout, run:
npm run build
node dist/cli.js setup --client plugin --scope user
Do not use @latest for a reviewed or reproducible installation. Do not enable global all-sites, file-upload, file-URL, or raw node_repl approval as part of setup.
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.
- 18d ago Changed 1f68bc7d8b76
- 1mo ago First seen · 22 lines · 13 tokens per session scan A f4eca5b459eb
setup is a skill published in the GitHub repository stickerdaniel/browserjack (2 stars, last pushed 2d ago), licensed MIT. It adds 13 tokens to every session and 157 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 2026-08-31.
Other skills, from other repositories
auto-research
Research uncertain questions with an explicit, user-approved web search or ChatGPT consultation, then present options and wait for implementation approval.
macos-harness
Read and operate the apps on this Mac from the shell. Use it when a task needs an app's UI and no API, CLI or purpose-built tool can do it.
host-computer-use
Beta desktop control through the connected A0 CLI host. Use for the user's host/local computer screenshots, screen inspection, menus, native app UI, OS-level clicking, scrolling, typing, or checking computeruseremote status. Use instead of linux-desktop for host/local machine control. Do not use for ordinary browser…
video-gen
Create video from existing clips, direct video-model calls, batch render scripts, FFmpeg timelines, or Remotion projects. Use when the deliverable is a video; use pi-image-gen for still images.
image-gen
Prompting workflow for imagegenerate when generating or editing raster images such as photos, illustrations, textures, sprites, mockups, concept art, or image-to-image edits. Use when the deliverable is a bitmap asset; keep repo-native SVG/vector/CSS/canvas work in source form.
nova-grounding
AX-first reading and grounded activation workflow for Nova desktop automation on macOS and Windows. Use for reading UI, clicking controls, OCR fallback, screenshots, and coordinate input without guessing.