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/fisker086/aiops/browsernpx skills add fisker086/AIOps --skill browsergit clone --depth 1 https://github.com/fisker086/AIOpsWhat 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 | $0.00030 | $0.00515 |
| Opus 5 | $0.00015 | $0.00258 |
| Sonnet 5 | $0.00006 | $0.00103 |
| Haiku 4.5 | $0.00003 | $0.00052 |
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 Skill
Provides server-side headless browser automation using agent-browser CLI (Playwright/Chromium backend):
- Navigate to URLs (with auto-snapshot and bot detection)
- Snapshot accessibility tree with element references (e.g.,
@e5) - Click elements by reference
- Type text into input fields
- Scroll up/down
- Navigate back in history
- Press keyboard keys
- Take full-page screenshots (base64 PNG)
- Execute JavaScript in page context
- Read console messages and JS errors
- Session isolation per
task_id
Use builtin_browser tool with fields:
operation: one of "navigate", "snapshot", "click", "type", "scroll", "back", "press", "screenshot", "eval", "console", "close"url: URL to navigate to (required for navigate)ref: Element reference from snapshot (e.g.,@e5) for click/typetext: Text to type (for type) or key to press (for press)js: JavaScript expression to evaluate (required for eval)task_id: Session identifier (default: "default"); each task_id gets its own browser sessiondirection: Scroll direction "up" or "down" (default: "down")full: Full page screenshot "true"/"false" (default: "false")clear: Clear console/errors after reading "true"/"false"
Response format:
- Always return the result in a single message. When taking a screenshot, embed the base64 PNG inline in your reply via
— do not split into multiple messages.
Notes:
- Requires
agent-browserCLI installed:npx agent-browser install --with-deps - Each
task_idmaintains an isolated browser session with persistent state - Sessions auto-clean after 5 minutes of inactivity
- Element references from snapshot (e.g.,
@e5) are used for click/type — not CSS selectors - For simple HTTP fetches, prefer
builtin_http_client(faster, lighter)
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 · 44 lines · 30 tokens per session scan A 2fbe64529b6a
browser is a skill published in the GitHub repository fisker086/AIOps (21 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 515 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 2026-08-30.
Other skills, from other repositories
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.
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.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
traceway-setup
Analyze and instrument repositories for Traceway observability. Use when the user wants to plan, add, migrate, or verify Traceway or OpenTelemetry monitoring for backend, browser, full-stack, mobile or iOS, or AI-agent software, including project topology and user-approved setup-plan creation. Backends use OTLP/HTTP…