Agent skill

Opencli

by grandamenium in grandamenium/cortextos

Turn any website into a CLI command by driving Chrome's live session.

MITAuto-check passedMarketing & SEO

Install Opencli

skills CLI
$ npx skills add grandamenium/cortextos --skill opencli -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install grandamenium/cortextos opencli --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/grandamenium/cortextos.git skills-src && mkdir -p .claude/skills && cp -r skills-src/community/skills/opencli .claude/skills/opencli && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
opencli
GitHub stars
101
Token cost
~1.4k tokens
SKILL.md length
399 words
Files
1
Skills in repo
55
Repo updated
First seen
Licence
MIT

At a glance

Turn any website into a CLI command by driving Chrome's live session.

  • Works in 3 steps: Install the Browser Bridge extension → Log into target sites in Chrome → Verify
  • You need structured data from a site that has no API
  • SKILL.md covers Prerequisites (One-Time Setup), Core Commands, Adapter Generation Workflow and Property Meld Adapter Blueprint, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Opencli is an agent skill from grandamenium/cortextos. Turn any website into a CLI command by driving Chrome's live session. Use when you need structured data from a site that has no API or where the API is inadequate — reads the browser's actual session (logged-in state, cookies) to extract data. Requires Chrome + Browser Bridge extension setup (one-time).

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Marketing & SEO, covering Schema markup. It works with Chrome Extensions. The licence is MIT.

When your agent uses it

  • You need structured data from a site that has no API
  • Where the API is inadequate — reads the browsers actual session (logged-in state
  • Cookies) to extract data

Example prompts

  • “/opencli”

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Install the Browser Bridge extension
  2. Log into target sites in Chrome
  3. Verify

What it can do on your machine

Read from SKILL.md and the folder at commit 6f93838. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Opencli loads about 1.4k tokens when it runs. Until then it costs about 78 tokens; SKILL.md has 399 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~78
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from grandamenium/cortextos at commit 6f93838, republished under its MIT licence (© grandamenium). 399 words, ~1,447 tokens.

Download SKILL.mdSave it as .claude/skills/opencli/SKILL.md (or your agent's skills folder).
name
opencli
description
Turn any website into a CLI command by driving Chrome's live session. Use when you need structured data from a site that has no API or where the API is inadequate — reads the browser's actual session (logged-in state, cookies) to extract data. Requires Chrome + Browser Bridge extension setup (one-time).
effort
medium
triggers
opencli, browser automation, website cli, scrape, browser adapter, web adapter, generate adapter, opencli explore, opencli generate, property meld adapter…

OpenCLI — Turn Websites Into CLI Commands

Converts any website into a deterministic CLI by driving Chrome's live session. No credentials stored — reuses whatever Chrome is already logged into.


Prerequisites (One-Time Setup)

OpenCLI requires a Chrome extension to bridge between the CLI and the browser.

1. Install the Browser Bridge extension
bash
# Check if already set up
opencli doctor

If not connected:

  1. Download the extension from: https://github.com/jackwener/opencli/releases (look for browser-bridge-extension.zip)
  2. Open Chrome → chrome://extensions → enable Developer Mode
  3. Click Load unpacked → select the extracted extension folder
  4. Run opencli doctor — should show [OK] Extension: connected
2. Log into target sites in Chrome

OpenCLI uses Chrome's existing session. Navigate to the target site in Chrome and log in before running any command.

3. Verify
bash
opencli doctor
# Expected:
# [OK] Daemon: running on port 19825
# [OK] Extension: connected
# [OK] Connectivity: ok

Core Commands

CommandWhat it does
opencli doctorDiagnose extension connectivity
opencli explore <url>Discover APIs, data stores, and recommended strategies
opencli generate <url>One-shot: explore → synthesize → verify → register adapter
opencli cascade <url>Probe public endpoints before committing to session-based approach
opencli browserDirect page control — navigate, click, type, extract
opencli record <url>Capture API calls from live session → generate YAML candidates
opencli listList all available adapters (87+ built-in)

Adapter Generation Workflow

Use this to build a new adapter for any site:

bash
# Step 1: Explore — discover what the site exposes
opencli explore https://app.example.com \
  --goal "read maintenance work orders and their comments"

# Step 2: Generate — build and register the adapter
opencli generate https://app.example.com \
  --goal "list open work orders with latest comment"

# Step 3: Use it
opencli <adapter-name> list-orders
opencli <adapter-name> get-comments --meld-id 12345
Record-then-synthesize (alternative for complex auth flows)
bash
# Record API calls from your live session
opencli record https://app.example.com

# Perform the actions manually in Chrome while recording
# Stop recording — synthesize converts captured calls to adapter

opencli synthesize propertymeld

Property Meld Adapter Blueprint

Goal: Read meld comments (replacing pm-get-comments.py Playwright script)

Status: Blueprint ready. Requires Chrome extension setup + PropertyMeld login in Chrome to complete.

When extension is connected, run:
bash
# Explore what PropertyMeld exposes
opencli explore https://app.propertymeld.com \
  --goal "read meld work orders and associated comments/notes"

# Generate the adapter
opencli generate https://app.propertymeld.com \
  --goal "list open melds with latest comment for triage"
Expected adapter commands (once generated):
bash
# List open melds
opencli propertymeld list-melds --status open

# Get comments on a specific meld
opencli propertymeld get-comments --meld-id 12345

# Triage summary (all open melds with latest comment)
opencli propertymeld triage --format json
Show full SKILL.md (160 more words)Show less
PropertyMeld API endpoints to target during recording

Based on existing Playwright scripts, these endpoints carry the relevant data:

EndpointData
/api/v2/melds/Work order list, status, assignee, property
/api/v2/melds/{id}/comments/Meld comments and notes
/api/v2/melds/{id}/Single meld detail

Tip: Use opencli record while navigating the Melds page and opening a meld — it captures the actual API calls Chrome makes, which is more reliable than guessing endpoints.


Browser Control (no adapter needed)

For one-off browser interactions without building an adapter:

bash
# Open a session
opencli browser

# Navigate
> navigate https://app.propertymeld.com/melds/

# Extract text from current page
> extract .meld-list-item

# Click a button
> click "View Details"

# Wait for element
> wait .comments-panel

# Get structured data
> extract table --format json

Using Built-In Adapters

87+ adapters ship out of the box:

bash
opencli list              # see all
opencli gh pr list        # GitHub (wraps gh CLI)
opencli obsidian list     # Obsidian vault

Output Formats

All commands support structured output:

bash
opencli propertymeld list-melds --format json
opencli propertymeld list-melds --format csv
opencli propertymeld list-melds --format table   # default

Notes

  • Session-backed: if Chrome logs out, commands return empty data
  • Zero LLM cost at runtime — adapters are pre-compiled YAML + JS
  • Additive: does not replace existing Playwright scripts; use alongside them
  • opencli cascade first if unsure whether the site has public API endpoints (no extension needed for public routes)

OpenCLI v1.7.3. Daemon runs on port 19825. opencli doctor is the first debugging step for any connectivity issue.

© grandamenium, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in community/skills/opencli of grandamenium/cortextos.

Open the folder on GitHubat commit 6f93838

Compare with similar skills

Opencli next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Opencli compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Opencli this skillgrandamenium/cortextos101—~1.4kAutomated safety check: PassMIT
SEO Checkerhanzili/hanzi-browse177—~1.9kAutomated safety check: PassCustom licence
SEO GeoReScienceLab/opc-skills1.8k4 repos~2.1kAutomated safety check: PassApache-2.0
GEO-First SEO Audit Toolzubair-trabzada/geo-seo-claude11k—~2.8kAutomated safety check: NotesMIT
Portaljs Add Dcatdatopian/portaljs2.4k1 repos~1.8kAutomated safety check: PassMIT
Schema Markupfreekmurze/dotfiles1k15 repos~1.2kAutomated safety check: PassNone

Similar skills

  • SEO Checker

    hanzili/hanzi-browse

    Audit web pages for SEO issues in a real browser. An agent skill from hanzili/hanzi-browse.

    177 GitHub stars~1.9k tokensUpdated 5 mo ago
    Marketing & SEOAuto-check passed
  • SEO Geo

    ReScienceLab/opc-skills

    SEO & GEO (Generative Engine Optimization) for websites. An agent skill from ReScienceLab/opc-skills.

    1.8k GitHub starsUsed in 4 repos~2.1k tokens
    Marketing & SEOAuto-check passed
  • GEO-First SEO Audit Tool

    zubair-trabzada/geo-seo-claude

    Audits a website for AI search visibility across ChatGPT, Claude, Perplexity and Google AI Overviews while checking traditional SEO, schema and E-E-A-T content quality.

    11k GitHub stars~2.8k tokensUpdated yesterday
    Marketing & SEOAuto-check: notes
  • Portaljs Add Dcat

    datopian/portaljs

    Make a PortalJS portal harvestable by national/EU/US open-data portals — emit standards-compliant DCAT catalog feeds (DCAT 2/3, DCAT-AP, DCAT-US, national profiles) in JSON-LD, Turtle, and RDF/XML…

    2.4k GitHub starsUsed in 1 repo~1.8k tokens
    Marketing & SEOAuto-check passed
  • Schema Markup

    freekmurze/dotfiles

    When the user wants to add, fix, or optimize schema markup and structured data on their site.

    1k GitHub starsUsed in 15 repos~1.2k tokens
    Marketing & SEOAuto-check passed
  • SEO Optimizer

    ailabs-393/ai-labs-claude-skills

    This skill should be used when analyzing HTML/CSS websites for SEO optimization, fixing SEO issues, generating SEO reports, or implementing SEO best practices.

    454 GitHub starsUsed in 1 repo~3.2k tokens
    Marketing & SEOAuto-check passed

More from grandamenium/cortextos

All 55 skills in this repo
  • Cortext Self Diagnosis

    grandamenium/cortextos

    Diagnose cortextOS itself when the framework misbehaves — an agent has gone silent or wedged, agents are crash-looping, Telegram or agent-to-agent messages are not arriving, crons did not fire, an…

    101 GitHub stars~3.7k tokensUpdated 15 days ago
    Auto-check passed
  • Activity Channel

    grandamenium/cortextos

    You have completed something significant and want the whole org — all agents and the user — to know about it.

    101 GitHub stars~624 tokensUpdated 15 days ago
    Auto-check passed
  • Agentcard Purchase

    grandamenium/cortextos

    You need to make a purchase on behalf of the user — buy a SaaS subscription, pay for an API, purchase a domain, or any transaction requiring a credit card.

    101 GitHub stars~1.1k tokensUpdated 15 days ago
    Auto-check passed
  • Claude To Codex Migration

    grandamenium/cortextos

    Migrate ANY cortextOS agent from the claude-code runtime to the live codex-app-server runtime.

    101 GitHub stars~12k tokensUpdated 15 days ago
    Auto-check: warnings
  • Bus Reference

    grandamenium/cortextos

    Complete cortextos bus CLI reference - all available commands with examples.

    101 GitHub stars~3.8k tokensUpdated 15 days ago
    Auto-check passed
  • Business News Monitor

    grandamenium/cortextos

    Daily cron-driven scan of news/forums/social in a domain to surface market shifts, new competitors, regulatory changes, and net-new opportunities.

    101 GitHub stars~1.3k tokensUpdated 15 days ago
    Auto-check passed

Categories

Questions about Opencli

What does Opencli do?

Turn any website into a CLI command by driving Chrome's live session. Opencli is an agent skill from grandamenium/cortextos. Turn any website into a CLI command by driving Chrome's live session.

When should I use Opencli?

Opencli fits situations like: you need structured data from a site that has no API; where the API is inadequate — reads the browsers actual session (logged-in state; cookies) to extract data.

How do I install Opencli in Claude Code?

Run `npx skills add grandamenium/cortextos --skill opencli -a claude-code`. Or copy the skill folder (community/skills/opencli in grandamenium/cortextos) into .claude/skills/opencli in your project. Claude Code loads it when a task matches its description.

How do I install Opencli in Codex?

Run `npx skills add grandamenium/cortextos --skill opencli -a codex`. Or copy the skill folder (community/skills/opencli in grandamenium/cortextos) into .agents/skills/opencli in your project. Codex loads it when a task matches its description.

Can I use Opencli in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add grandamenium/cortextos --skill opencli -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/opencli, .gemini/skills/opencli, .github/skills/opencli and .opencode/skills/opencli in your project.

What does Opencli need to run?

SKILL.md names no scripts, command-line tools or credentials: Opencli is instructions for the agent only.

Does Opencli access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Opencli safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Opencli use?

Opencli is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Opencli use?

About 1.4k tokens (SKILL.md is roughly 5.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Opencli?

Skills that share tags, products or a category with Opencli: SEO Checker (hanzili/hanzi-browse, 177 stars), SEO Geo (ReScienceLab/opc-skills, 1.8k stars), GEO-First SEO Audit Tool (zubair-trabzada/geo-seo-claude, 11k stars) and Portaljs Add Dcat (datopian/portaljs, 2.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Opencli?

grandamenium (a GitHub user) maintains it in grandamenium/cortextos, which has 101 GitHub stars. The repository holds 55 skills in this directory. The repository was last updated on September 23, 2026.

Source: grandamenium/cortextos on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.