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/tacosyhorchata/pilot/clinpx skills add TacosyHorchata/Pilot --skill cligit clone --depth 1 https://github.com/TacosyHorchata/PilotWrote 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/tacosyhorchata/pilot/cli)<a href="https://agentmods.dev/skills/tacosyhorchata/pilot/cli"><img src="https://agentmods.dev/badge/skills/tacosyhorchata/pilot/cli.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00653 |
| Opus 5 | $0.00000 | $0.00327 |
| Sonnet 5 | $0.00000 | $0.00131 |
| Haiku 4.5 | $0.00000 | $0.00065 |
Grade A, and why
cli 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 4d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pilot CLI — Browser Automation
You have access to a persistent headless browser via pilot-cli shell commands.
The daemon starts automatically on first use — no setup needed.
How it works
Commands return short inline summaries + a file path for the full snapshot. Read the file with your Read tool only when you need element refs or more detail. This keeps conversation history lean — paths accumulate, not 50K snapshots.
Commands
# Navigate and get page content (preferred for read tasks)
# Returns: URL, title, first 400 chars of content, + path to full snapshot
pilot-cli get <url>
# Navigate to a URL
# Returns: "Navigated to <url> (200)\nSnapshot → /tmp/pilot-xxx.txt"
pilot-cli navigate <url>
# Get full page snapshot — always saves to file, returns path
# Read with Read tool when you need @eN refs to click/fill
pilot-cli snapshot
# Click an element — use @eN ref from snapshot file, or CSS selector
# Returns: "Clicked @e3 — snapshot → /tmp/pilot-xxx.txt"
pilot-cli click @e3
pilot-cli click "button[type=submit]"
# Fill an input
pilot-cli fill @e5 "search text"
# Type character by character (for inputs that reject fill)
pilot-cli type @e5 "search text"
# Press a key
pilot-cli press Enter
pilot-cli press Tab
# Scroll
pilot-cli scroll down 500
pilot-cli scroll up 300
# Current URL or title
pilot-cli url
pilot-cli title
# History
pilot-cli back
pilot-cli forward
Typical workflows
Read task ("go to X and tell me Y"):
pilot-cli get https://news.ycombinator.com
# Returns title + first 400 chars — usually enough to answer directly
# If you need more: Read /tmp/pilot-xxx.txt (path returned above)
Interaction task ("search for X, click Y"):
pilot-cli navigate https://www.npmjs.com
# Returns: "Navigated to ... → /tmp/pilot-aaa.txt"
# Read the snapshot to find refs
# [Read /tmp/pilot-aaa.txt]
# → find the search input ref, e.g. @e4
pilot-cli fill @e4 "zod"
pilot-cli press Enter
# Navigate result returns new snapshot path
pilot-cli snapshot
# → /tmp/pilot-bbb.txt
# [Read /tmp/pilot-bbb.txt] — find the result link ref
pilot-cli click @e7
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.
- 4d ago First seen · 89 lines · 0 tokens per session scan A db3cdba2319d
cli is a skill published in the GitHub repository TacosyHorchata/Pilot (32 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 653 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 2026-08-30.
Other skills, from other repositories
Agent Browser Automation
Fast Rust-based headless browser automation CLI with Node.js fallback for AI agents, featuring navigation, clicking, typing, snapshots, and structured commands optimized for agent workflows.
apitap
ApiTap gives AI agents cheap access to web data through three layers.
website-explorer
Discover website capabilities from user behaviors. Learn APIs and automate workflows.
real-browser-control
Connect an AI coding agent to the user's REAL Chrome via Real Browser MCP (local MCP server + Chrome extension over localhost WebSocket). Use for live UI verification, already-open tabs, existing cookies/SSO/2FA, staging admin panels, and any task where headless Playwright or a cloud agentic browser would miss the…
browser-automation
Control the user's real logged-in Chrome via Real Browser MCP (extension + local MCP). Use for live UI checks, existing SSO/cookies, and tabs already open. Triggers: real browser, my Chrome, not headless, verify in browser. Prefer over Playwright when session state matters. Prefer Playwright for CI.
aginxbrowser
Browser engine for AI agents: fetch JS-rendered and Cloudflare-protected pages as clean markdown, run 5-engine aggregated web search (Baidu, Bing, Sogou, WeChat, Google), take screenshots as visual input, extract structured data from SPAs, and drive multi-step interactions (click, type, fill forms, login, paginate)…