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/olo-dot-io/uni-cli/unicli-usagenpx skills add olo-dot-io/Uni-CLI --skill unicli-usagegit clone --depth 1 https://github.com/olo-dot-io/Uni-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 | $0.00077 | $0.01299 |
| Opus 5 | $0.00039 | $0.00649 |
| Sonnet 5 | $0.00015 | $0.00260 |
| Haiku 4.5 | $0.00008 | $0.00130 |
Grade B, and why
unicli-usage scanned grade B with 2 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
unicli <site> <command> [options] # Run any command Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
raw browser tools, legacy OpenCLI, curl, or computer-use for web, browser, How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
unicli Usage Guide
Quick Reference
unicli search "intent" # Find the right command first
unicli do "goal" -f json # Get candidates, schema, and next action
unicli describe <site> <command> # Inspect exact args and recovery steps
unicli list # List all available commands
unicli list --type web-api # Filter by adapter type
unicli list --site bilibili # Filter by site name
unicli list --personalized # Find signed-in user data operations
unicli search "my saved posts" --personalized
unicli upgrade --check -f json # Compare installed and latest releases
unicli upgrade # Interactive Y/N choice
unicli upgrade --yes -f json # Unattended Agent update
unicli upgrade --no -f json # Remind again after 24 hours
unicli upgrade --no-auto-update # Require explicit approval on this machine
unicli <site> <command> [options] # Run any command
unicli hackernews top --limit 5 # Example: HN top stories
unicli hackernews search "AI agents" # Example: search HN
unicli doctor # System health check
unicli browser doctor --json # Browser/profile/CDP reliability report
unicli browser doctor --repair # Start only the windowless broker
unicli browser start # Start hidden managed provider on demand
unicli browser --focus start # Explicit existing-Chrome foreground control
Output Formats
Every structured envelope may include meta.update. Persistent non-interactive
installations schedule the exact release automatically and expose progress in
meta.update.automatic_update. Confirm the installed version before retrying a
version-sensitive task. Non-interactive calls never open a prompt.
All commands support --format / -f.
| Format | Use Case |
|---|---|
md |
Default v2 AgentEnvelope for agents |
json |
Machine parsing / jq |
yaml |
Config-friendly envelope |
csv |
Spreadsheet import |
compact |
Pipe-friendly row stream |
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 · 142 lines · 77 tokens per session scan B 03e61badecef
unicli-usage is a skill published in the GitHub repository olo-dot-io/Uni-CLI (270 stars, last pushed 12d ago), licensed Apache-2.0. It adds 77 tokens to every session and 1,299 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 2 findings (unrestricted tool access, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
remote-browser
Controls an isolated Browser Use Cloud browser from a sandboxed machine with the current Browser Use CLI.
opencli-browser
Use when an agent needs to drive a real Chrome window via opencli — inspect a page, fill forms, click through logged-in flows, or extract data ad-hoc. Covers the selector-first target contract, compound form fields, stale-ref handling, network capture, and the agent-native envelopes the CLI returns. Not for writing…
opencli-adapter-author
Use when writing an OpenCLI adapter for a new site or adding a new command to an existing site. Guides end-to-end from first recon through field decoding, adapter coding, and verify. Replaces opencli-oneshot / opencli-explorer. For ad-hoc browser driving (no adapter), see opencli-browser instead; for a top-level…
cloud
Documentation reference for using Browser Use Cloud — the hosted API and SDK for browser automation. Use this skill whenever the user needs help with the Cloud REST API (v2, v3, or v4), browser-use-sdk (Python or TypeScript), X-Browser-Use-API-Key authentication, cloud sessions, browser profiles, profile sync, CDP…
opencli-autofix
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.