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/puffinsoft/peek-cli/view-browser-tabnpx skills add puffinsoft/peek-cli --skill view-browser-tabgit clone --depth 1 https://github.com/puffinsoft/peek-cliWhat 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 | $0.00012 | $0.00291 |
| Opus 5 | $0.00006 | $0.00146 |
| Sonnet 5 | $0.00002 | $0.00058 |
| Haiku 4.5 | $0.00001 | $0.00029 |
Grade A, and why
view-browser-tab 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
You cannot see the consequences of your actions. It is important to get incorporate visual feedback. Use peek-cli to capture screenshots of tabs to aid in front-end development.
Iterate & capture often. Capturing a screenshot of a tab is remarkably cheap.
These are the commands:
peeked start- start the WebSocket server for connection w/ the Chrome Extensionpeeked stop- stop the serverpeeked status- get server & connection status.peeked list- get list of all open tabspeeked at <url>- capture screenshot of tab. Will save it to a temp file. You must read it after.
Run peeked status at the start of each session.
- if the server is not started, run
startand prompt the user to connect. - if the server is started & extension is connected, it's safe to run all
peekedcommands.
Connecting the extension to the server is a manual process that the user needs to perform. Nothing can be done on your end.
Don't run peeked stop unless the user asks because reconnecting is a manual process.
peeked at is safe to run simultaneously.
If you see a glowing border around the screenshot, that is an artifact from the capture process.
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 · 28 lines · 12 tokens per session scan A 6508e7ce3689
view-browser-tab is a skill published in the GitHub repository puffinsoft/peek-cli (117 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 291 once invoked, about $0.0001 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
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.