Agent skill · Audited from source
qiaomu-opencli-browser
skill · joeseesun/opencli-skillMIT licenceAudited 22 Oct 2026 · source ccd4e8bab454
Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit ccd4e8bab454 and found no filesystem, network or shell access and no hard-coded secrets. What it does: Make websites accessible for AI agents. Navigate, click, type, extract, wait — using Chrome with existing login sessions. No LLM API key needed.
Cite
Cite this page
ModelsAtlas. “qiaomu-opencli-browser (joeseesun/opencli-skill)”. Retrieved 22 Oct 2026. https://modelsatlas.com/skills/joeseesun/qiaomu-opencli-browser
Trust audit
Audit 0.4.1 · source read 22 Oct 2026
SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 13,985 of 14,816 audited skills.
What the source does
- FilesystemNone observedNo reads or writes in the source
- NetworkNone observedNo outbound calls in the source
- ShellNone observedNo commands run in the source
- DependenciesPinnedNothing floats
- SecretsNone foundNo keys in source
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | PASS | 0 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | NA | 0 |
L2 Instructions | Prompt injection, authority framing, hidden directives | PASS | 0 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: no behavioural pass.
Findings (0)
No findings at any severity. We re-audit when the source changes.
Audit 0.4.1 · source sha ccd4e8bab454 · 22 Oct 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- Publisherjoeseesun GitHub userOwner of the repository this skill is read from
- Source folderjoeseesun/opencli-skill/qiaomu-opencli-browserThe exact folder we audited
- LicenceMITAs the repository states it
- Commit pinned for this verdictccd4e8bab454A new audit runs when the source changes
- Repository statusNot archivedLast push 195 days ago
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: Make websites accessible for AI agents. Navigate, click, type, extract, wait — using Chrome with existing login sessions. No LLM API key needed.
---
name: qiaomu-opencli-browser
description: Make websites accessible for AI agents. Navigate, click, type, extract, wait — using Chrome with existing login sessions. No LLM API key needed.
author: joeseesun
upstream: jackwener/opencli
allowed-tools: Bash(opencli:*), Read, Edit, Write
---
# OpenCLI Browser — Browser Automation for AI Agents
Control Chrome step-by-step via CLI. Reuses existing login sessions — no passwords needed.
## Prerequisites
```bash
opencli doctor # Verify extension + daemon connectivity
```
Requires: Chrome running + OpenCLI Browser Bridge extension installed.
## Critical Rules
1. **ALWAYS use `state` to inspect the page, NEVER use `screenshot`** — `state` returns structured DOM with `[N]` element indices, is instant and costs zero tokens. `screenshot` requires vision processing and is slow. Only use `screenshot` when the user explicitly asks to save a visual.
2. **ALWAYS use `click`/`type`/`select` for interaction, NEVER use `eval` to click or type** — `eval "el.click()"` bypasses scrollIntoView and CDP click pipeline, causing failures on off-screen elements. Use `state` to find the `[N]` index, then `click <N>`.
3. **Verify inputs with `get value`, not screenshots** — after `type`, run `get value <index>` to confirm.
4. **Run `state` after every page change** — after `open`, `click` (on links), `scroll`, always run `state` to see the new elements and their indices. Never guess indices.
5. **Chain commands aggressively with `&&`** — combine `open + state`, multiple `type` calls, and `type + get value` into single `&&` chains. Each tool call has overhead; chaining cuts it.
6. **`eval` is read-only** — use `eval` ONLY for data extraction (`JSON.stringify(...)`), never for clicking, typing, or navigating. Always wrap in IIFE to avoid variable conflicts: `eval "(function(){ const x = ...; return JSON.stringify(x); })()"`.
7. **Minimize total tool calls** — plan your sequence before acting. A good task completion uses 3-5 tool calls, not 15-20. Combine `open + state` as one call. Combine `type + type + click` as one call. Only run `state` separately when you need to discover new indices.
8. **Prefer `network` to discover APIs** — most sites have JSON APIs. API-based adapters are more reliable than DOM scraping.
## Command Cost Guide
| Cost | Commands | When to use |
|------|----------|-------------|
| **Free & instant** | `state`, `get *`, `eval`, `network`, `scroll`, `keys` | Default — use these |
| **Free but changes page** | `open`, `click`, `type`, `select`, `back` | Interaction — run `state` after |
| **Expensive (vision tokens)** | `screenshot` | ONLY when user needs a saved image |
## Action Chaining Rules
Commands can be chained with `&&`. The browser persists via daemon, so chaining is safe.
**Always chain when possible** — fewer tool calls = faster completion:
```bash
# GOOD: open + inspect in one call (saves 1 round trip)
opencli browser open https://example.com && opencli browser state
# GOOD: fill form in one call (saves 2 round trips)
opencli browser type 3 "hello" && opencli browser type 4 "world" && opencli browser click 7
# GOOD: type + verify in one call
opencli browser type 5 "[email protected]" && opencli browser get value 5
# GOOD: click + wait + state in one call (for page-changing clicks)
opencli browser click 12 && opencli browser wait time 1 && opencli browser state
# BAD: separate calls for each action (wasteful)
opencli browser type 3 "hello" # Don't do this
opencli browser type 4 "world" # when you can chain
opencli browser click 7 # all three together
```
**Page-changing — always put last** in a chain (subsequent commands see stale indices):
- `open <url>`, `back`, `click <link/button that navigates>`
**Rule**: Chain when you already know the indices. Run `state` separately when you need to discover indices first.
## Core Workflow
1. **Navigate**: `opencli browser open <url>`
2. **Inspect**: `opencli browser state` → elements with `[N]` indices
3. **Interact**: use indices — `click`, `type`, `select`, `keys`
4. **Wait** (if needed): `opencli browser wait selector ".loaded"` or `wait text "Success"`
5. **Verify**: `opencli browser state` or `opencli browser get value <N>`
6. **Repeat**: browser stays open between commands
7. **Save**: write a TS adapter to `~/.opencli/clis/<site>/<command>.ts`
## Commands
### Navigation
```bash
opencli browser open <url> # Open URL (page-changing)
opencli browser back # Go back (page-changing)
opencli browser scroll down # Scroll (up/down, --amount N)
opencli browser scroll up --amount 1000
```
### Inspect (free & instant)
```bash
opencli browser state # Structured DOM with [N] indices — PRIMARY tool
opencli browser screenshot [path.png] # Save visual to file — ONLY for user deliverables
```
### Get (free & instant)
```bash
opencli browser get title # Page title
opencli browser get url # Current URL
opencli browser get text <index> # Element text content
opencli browser get value <index> # Input/textarea value (use to verify after type)
opencli browser get html # Full page HTML
opencli browser get html --selector "h1" # Scoped HTML
opencli browser get attributes <index> # Element attributes
```
### Interact
```bash
opencli browser click <index> # Click element [N]
opencli browser type <index> "text" # Type into element [N]
opencli browser select <index> "option" # Select dropdown
opencli browser keys "Enter" # Press key (Enter, Escape, Tab, Control+a)
```
### Wait
Three variants — use the right one for the situation:
```bash
opencli browser wait time 3 # Wait N seconds (fixed delay)
opencli browser wait selector ".loaded" # Wait until element appears in DOM
opencli browser wait selector ".spinner" --timeout 5000 # With timeout (default 30s)
opencli browser wait text "Success" Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.
Install
Pinned to the audited commit ccd4e8b
git clone https://github.com/joeseesun/opencli-skill git -C opencli-skill checkout ccd4e8bab454
The author documents no install command, so this uses the repository directly. Our verdict covers commit ccd4e8bab454 only.
Works in
The author has not said which agents this skill supports, and we have not tested it in any.
Audit history
Every audit, every source change
- ✓SAFE B 89 / 100
first audit · source
ccd4e8bab454
Similar skills
obra/superpowers
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions…
obra/superpowers
Use when you have a spec or requirements for a multi-step task, before touching code
obra/superpowers
Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions
Questions about qiaomu-opencli-browser
What does the qiaomu-opencli-browser skill do?
Is qiaomu-opencli-browser safe to install?
What can qiaomu-opencli-browser access on my machine?
How current is this page?
Sources
- github.com/joeseesun/opencli-skill/tree/main/qiaomu-opencli-brow — the audited source at commit ccd4e8bab454 and every finding aboveObserved · 22 Oct 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- What does the qiaomu-opencli-browser skill do?
- Is qiaomu-opencli-browser safe to install?
- What can qiaomu-opencli-browser access on my machine?