A browser-automation add-on for LinkedIn, the professional networking website. It can work with a logged-in browser session or an isolated browser session.

Search LinkedIn, view profiles, check notifications and messages, and send connection requests or messages when the user confirms the action.

Routine LinkedIn work can require repeated page navigation and manual checks. It provides a way to view profiles, search for people, inspect messages, and manage connection requests through browser actions.

linkedin — Skill for Claude Code and Codex by CraftOS-dev: A browser-automation add-on for LinkedIn, the professional networking website.

Install

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.

agentmods

npx agentmods add skills/craftos-dev/craftbot/linkedin

Any agent

npx skills add CraftOS-dev/CraftBot --skill linkedin

Clone the repo

git clone --depth 1 https://github.com/CraftOS-dev/CraftBot

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/craftos-dev/craftbot/linkedin.svg)](https://agentmods.dev/skills/craftos-dev/craftbot/linkedin)

Your own site

<a href="https://agentmods.dev/skills/craftos-dev/craftbot/linkedin"><img src="https://agentmods.dev/badge/skills/craftos-dev/craftbot/linkedin.svg" alt="Measured on agentmods" height="20"></a>

Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 515 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00020	$0.00515
Opus 5	$0.00010	$0.00258
Sonnet 5	$0.00004	$0.00103
Haiku 4.5	$0.00002	$0.00052

Measured yesterday against content hash 95e31d22d522, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

linkedin 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 yesterday.

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.

skills/linkedin/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use browser automation to interact with LinkedIn - check messages, view profiles, search, and send connection requests.

Connection Methods

Option 1: Chrome Extension Relay (Recommended)

Open LinkedIn in Chrome and log in
Click the Clawdbot Browser Relay toolbar icon to attach the tab
Use browser tool with profile="chrome"

Option 2: Isolated Browser

Use browser tool with profile="clawd"
Navigate to linkedin.com
Log in manually (one-time setup)
Session persists for future use

Common Operations

Check Connection Status

browser action=snapshot profile=chrome targetUrl="https://www.linkedin.com/feed/"

View Notifications/Messages

browser action=navigate profile=chrome targetUrl="https://www.linkedin.com/messaging/"
browser action=snapshot profile=chrome

Search People

browser action=navigate profile=chrome targetUrl="https://www.linkedin.com/search/results/people/?keywords=QUERY"
browser action=snapshot profile=chrome

View Profile

browser action=navigate profile=chrome targetUrl="https://www.linkedin.com/in/USERNAME/"
browser action=snapshot profile=chrome

Send Message (confirm with user first!)

Navigate to messaging or profile
Use browser action=act with click/type actions
Always confirm message content before sending

Safety Rules

Never send messages without explicit user approval
Never accept/send connection requests without confirmation
Avoid rapid automated actions - LinkedIn is aggressive about detecting automation
Rate limit: ~30 actions per hour max recommended

If browser relay isn't available, extract the li_at cookie from browser:

Open LinkedIn in browser, log in
DevTools → Application → Cookies → linkedin.com
Copy li_at value
Store securely for API requests

Troubleshooting

If logged out: Re-authenticate in browser
If rate limited: Wait 24 hours, reduce action frequency
If CAPTCHA: Complete manually in browser, then resume

Read the full file on GitHub · 72 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

_meta.json 279 B

Changes

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.

yesterday First seen · 72 lines · 20 tokens per session scan A 95e31d22d522

Subscribe to this mod's changes

linkedin is a skill published in the GitHub repository CraftOS-dev/CraftBot (378 stars, last pushed 2d ago), licensed MIT. It adds 20 tokens to every session and 515 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 2026-09-03.

Browser automation agent-architecture ai ai-agents computer-use-agent content-engineering help-wanted

turix-mac

Computer Use Agent (CUA) for macOS automation using TuriX. Use when you need to perform visual tasks on the desktop, such as opening apps, clicking buttons, or navigating UIs that don't have a CLI or API.

TurixAI/TuriX-CUA · 53 tokens

browser-control

Control web pages in an existing Chromium remote-debugging session with deterministic sagui commands or the browser-only AI Agent. Use when Claude Code needs to inspect tabs, observe semantic elements, navigate, click, type, send keys, scroll, or complete a browser goal through CDP without controlling native macOS UI…

NakaokaRei/SwiftAutoGUI · 72 tokens

agent-smoke-test

Run manual development checks for SwiftAutoGUI AI Agent actions through the local sagui CLI. Use when Claude or Codex needs to test app-control or Accessibility BasicAction generation on macOS.

NakaokaRei/SwiftAutoGUI · 43 tokens

macos-control

Control macOS GUI applications via mouse automation, keyboard input, screenshots, image recognition, and AppleScript execution. Use when you need to interact with macOS app UIs, take screenshots, click buttons, type text, scroll, drag, or locate images on screen.

NakaokaRei/SwiftAutoGUI · 58 tokens

website-change-monitor

Watch important pages and notify when content changes.

frumu-ai/tandem · 13 tokens

browser-subagent-task-bounding

How to constrain browser subagents with deterministic stop conditions, step ceilings (max 5-8 steps), and selector-targeted DOM extraction to prevent runaway token costs and infinite navigation loops.

alivirgo/Major-AI-Skills · 44 tokens