agentmods.dev

linkedin-operator

linkedin-operator is a skill for Claude Code, Codex from samihalawa/linkedin-godmode-plugin. It costs 49 tokens per session (312 once invoked), scanned A, original, MIT.

A skill for operating an authenticated LinkedIn account through its current website and private web requests. LinkedIn is a professional networking site.

In plain words
What is it for?
Use it for authorized LinkedIn browsing and account actions, such as inspecting pages or carrying out user-approved changes.
Why use it?
It provides a method for reading LinkedIn or making requested account changes while checking the current page state and confirming results.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the linkedin-godmode-plugin plugin — 5 skills, 1 MCP server shipped together

not rated 0repo 7d ago A scan 49 tokens original MIT

Good fit Use it for authorized LinkedIn browsing and account actions, such as inspecting pages or carrying out user-approved changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/samihalawa/linkedin-godmode-plugin/linkedin-operator
View source ↗ samihalawa/linkedin-godmode-plugin npmjs.com
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.

Any agent
npx skills add samihalawa/linkedin-godmode-plugin --skill linkedin-operator
Clone the repo
git clone --depth 1 https://github.com/samihalawa/linkedin-godmode-plugin

Made for: Claude Code, Codex.

Or install linkedin-godmode-plugin, the plugin that ships this one along with the rest of its 5 skills, 1 MCP server.

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.

agentmods badge for linkedin-operator

README.md
[![agentmods](https://agentmods.dev/badge/skills/samihalawa/linkedin-godmode-plugin/linkedin-operator/github.svg)](https://agentmods.dev/skills/samihalawa/linkedin-godmode-plugin/linkedin-operator)
Your own site
<a href="https://agentmods.dev/skills/samihalawa/linkedin-godmode-plugin/linkedin-operator"><img src="https://agentmods.dev/badge/skills/samihalawa/linkedin-godmode-plugin/linkedin-operator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for linkedin-operator

Your own site · 80×15
<a href="https://agentmods.dev/skills/samihalawa/linkedin-godmode-plugin/linkedin-operator"><img src="https://agentmods.dev/badge/skills/samihalawa/linkedin-godmode-plugin/linkedin-operator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 312 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00049 $0.00312
Opus 5.5 $0.00020 $0.00125
Sonnet 5.5 $0.00010 $0.00062
Haiku 4.5 $0.00005 $0.00031

Measured 2mo ago against content hash 696226ff62b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

linkedin-operator 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 2mo 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.

skills/linkedin-operator/SKILL.md · 17 lines

What it actually says

LinkedIn operator

  1. Honor the user's explicitly selected authenticated controller. If the in-app Browser is named, do not open or treat another provider session as authoritative. For plugin-managed sessions, call browser_session status/list before opening another session.
  2. Prefer the dedicated local profile only when no controller was selected; use Anchor or Browserbase only when requested or configured.
  3. Read current state with browser_capture. Use accessible role/label/text locators before CSS/XPath.
  4. For UI work, call browser_navigate and browser_act with explicit caller-reviewed arguments.
  5. For private web requests, follow the capture-first method in references/operator-method.md; never guess a mutable endpoint.
  6. Before an account-visible change, inspect the target, execute once, and verify at the same layer. Do not infer success from a click alone.
  7. Never add unrequested loops, scheduling, campaign scope, challenge bypass, or cookie import/export. A caller's authorized batch may iterate through matching targets; do not invent a gate or broaden the batch. The selected controller's mandatory action-time confirmation policy still applies.

Use browser_task only when the user explicitly requests a provider AI task. Deterministic tools never need it.

Files

What ships with it

2 files 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.

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.

  1. 2mo ago First seen · 17 lines · 49 tokens per session scan A 696226ff62b0

Subscribe to this mod's changes

linkedin-operator is a skill published in the GitHub repository samihalawa/linkedin-godmode-plugin (0 stars, last pushed 7d ago), licensed MIT. It adds 49 tokens to every session and 312 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.

Browser automationMarketing and SEOanchor-browserbrowser-automationbrowserbasecodex-pluginlinkedinmcp
Related

linkedin-operator compared with skills from other repositories

linkedin-operator next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
linkedin-operatorsamihalawa/linkedin-godmode-pluginSkill07d agoMITA49Claude Code, Codex
mk:agent-browserngocsangyem/MeowKitSkill157d agoMITA114Claude Code
browsebrowserbase/stagehandSkill26kyesterdayMITA109Claude Code
opencli-autofixjackwener/OpenCLISkill31kyesterdayApache-2.0A61Claude Code
skill-bodycitrolabs/ego-liteSkill22ktodayMITA0Claude Code, Codex
moli-webfetchlexmount/moliSkill23ktodayApache-2.0A90Codex
pinchtabpinchtab/pinchtabSkill11k11d agoMITA94Codex