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 regen-coordination/org-os-template --skill web-browsinggit clone --depth 1 https://github.com/regen-coordination/org-os-templateWrote 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/regen-coordination/org-os-template/web-browsing)<a href="https://agentmods.dev/skills/regen-coordination/org-os-template/web-browsing"><img src="https://agentmods.dev/badge/skills/regen-coordination/org-os-template/web-browsing/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/regen-coordination/org-os-template/web-browsing"><img src="https://agentmods.dev/badge/skills/regen-coordination/org-os-template/web-browsing.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 | $0.00045 | $0.01172 |
| Opus 5 | $0.00023 | $0.00586 |
| Sonnet 5 | $0.00009 | $0.00234 |
| Haiku 4.5 | $0.00005 | $0.00117 |
Grade A, and why
web-browsing 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 8d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Browsing
What This Is
A real-browser capability for agents, powered by the browse.sh Browse CLI (Browserbase, built on Stagehand). Where plain fetch/search sees only static HTML, this skill drives an actual local Chrome session: navigate, snapshot the accessibility tree, click, fill, and extract structured content from JS-heavy pages.
This skill is portable org-os infrastructure: it contains no node-specific IDs or URLs. Node-specific setup notes live in TOOLS.md; setup instructions live in docs/integrations/BROWSE-INTEGRATION.md.
When to Use
- JS-heavy or interactive sites where WebFetch/search returns empty or broken content (grant portals, dashboards, SPAs).
- Multi-step navigation: search → filter → paginate → detail page.
- Structured extraction that needs the rendered DOM, not the raw HTML.
- Sites covered by a browse.sh catalog skill (check
browse skills find <term>first — a curated playbook beats rediscovering the site).
When NOT to Use
- Plain static pages — use WebFetch/search; it is cheaper and faster.
- Anything requiring login or credentials — gated, see Safety.
- Anything state-changing without prior approval — gated, see Safety.
Setup
Operator-level global install (not a repo dependency):
npm install -g browse
npm run browse:check # doctor: CLI present + version
npm run browse:check -- --live # + opens example.com and snapshots it
Full setup guide (incl. optional Claude Code plugin and the dormant cloud path): docs/integrations/BROWSE-INTEGRATION.md.
Core Loop
browse open <url> # start/point the session
browse snapshot # accessibility-tree snapshot with element refs
browse refs # list interactable element refs
browse click <ref> # interact (read-only navigation is fine)
browse fill <ref> <text> # ONLY as part of an approved flow — see Safety
browse get <selector> # extract content
browse screenshot # visual evidence when useful
browse stop # ALWAYS close the session when done
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.
- 8d ago First seen · 114 lines · 45 tokens per session scan A a7daf3982c2d
web-browsing is a skill published in the GitHub repository regen-coordination/org-os-template (5 stars, last pushed 6d ago), licensed MIT. It adds 45 tokens to every session and 1,172 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…