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/ozmasterai/torus-framework/browsernpx skills add OZmasterAI/Torus-Framework --skill browsergit clone --depth 1 https://github.com/OZmasterAI/Torus-FrameworkWhat 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 | $0.00000 | $0.00426 |
| Opus 5 | $0.00000 | $0.00213 |
| Sonnet 5 | $0.00000 | $0.00085 |
| Haiku 4.5 | $0.00000 | $0.00043 |
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 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
/browser — Visual Verification via agent-browser
When to use
When user says "browser", "screenshot", "visual verify", "check the UI", or when implementing UI features that need visual proof of correctness.
Commands
/browser open <url>— Open a URL in headless browser/browser snapshot— Get page structure (interactive elements with @refs)/browser screenshot <path>— Capture screenshot to file/browser click <ref>— Click an element by @ref (from snapshot)/browser fill <ref> <value>— Fill a form field by @ref/browser verify <url>— Combined: open + snapshot + screenshot
Verify Flow (most common)
agent-browser open <url>agent-browser snapshot -i -c(interactive elements with @refs)agent-browser screenshot screenshots/<feature-name>.png- Analyze screenshot — if issues found, fix and re-verify
- Save final screenshot path in memory with feature context
Interactive Testing Flow
- Open URL
- Snapshot to discover interactive elements (@e1, @e2, etc.)
- Click/fill elements to test interactions
- Screenshot after each interaction to verify state changes
- Report results
Integration with /ralph
During /ralph Phase 2 (EXECUTE), after implementing a UI sub-task:
- Start the dev server if not running
/browser verify http://localhost:<port>/<page>- Only mark sub-task complete if screenshot confirms correctness
- Save screenshot path in iteration memory save
Rules
- ALWAYS use
screenshots/directory (create if needed) - ALWAYS include descriptive filenames:
screenshots/health-score-endpoint.png - NEVER mark UI work as "done" without a screenshot when /browser is available
- If agent-browser is not installed, report error and fall back to manual verification
- Screenshots are proof — reference them in memory saves and reports
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 · 42 lines · 0 tokens per session scan A b95cbcbad246
browser is a skill published in the GitHub repository OZmasterAI/Torus-Framework (5 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 426 tokens. 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
electron
Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include…
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
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.
playwright
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via playwright-cli or the bundled wrapper script.
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.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.