What is linkedincli AGENTS.md?

Reference instructions for an AI agent that uses a command-line tool to manage LinkedIn profiles and posts. They explain authentication, available commands, and safe local handling of LinkedIn session data.

They help an agent log in, inspect profiles, and create, edit, or delete LinkedIn posts through the CLI or its MCP server.

They reduce guesswork about which LinkedIn actions are available and how to authenticate. They also clarify that live session data and LinkedIn requests must stay on the operator’s own computer.

How bcharleson/linkedincli configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to bcharleson/linkedincli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/bcharleson/linkedincli/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/bcharleson/linkedincli

Made for: Codex, OpenCode.

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/instructions/bcharleson/linkedincli/agents-md/github.svg)](https://agentmods.dev/instructions/bcharleson/linkedincli/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/bcharleson/linkedincli/agents-md"><img src="https://agentmods.dev/badge/instructions/bcharleson/linkedincli/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/bcharleson/linkedincli/agents-md"><img src="https://agentmods.dev/badge/instructions/bcharleson/linkedincli/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 5,967 This file is loaded in full into every session.

When invoked 5,967 The same file — it is already loaded in full.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.05967	$0.05967
Opus 5.5	$0.02387	$0.02387
Sonnet 5.5	$0.01193	$0.01193
Haiku 4.5	$0.00597	$0.00597

Measured 14d ago against content hash 938d1d4aece9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

linkedincli AGENTS.md scanned grade A with 1 finding 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 14d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

│ ├── transport.ts # Node fetch and optional local curl transport

AGENTS.md · 737 lines

How it starts

The opening of the file, as written. The whole thing — 737 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — LinkedIn CLI Agent Guide

This is the shared entry point for repository development guidance and the LinkedIn CLI / MCP tool reference. AI agents (Claude Code, Cursor, Windsurf, OpenClaw, etc.) should use this as the authoritative reference for managing LinkedIn.

Repository Development

The CLI and MCP server use the same CommandDefinition objects as their single source of truth. TypeScript uses strict mode and ESM; Commander.js powers the CLI, Zod v4 defines input schemas, and the MCP SDK exposes the tools. tsup bundles the CLI and MCP entry points. package.json declares Node.js 18+; check dependency engine requirements when choosing a runtime.

Architecture

src/
├── index.ts                 # CLI entry (Commander.js)
├── mcp.ts                   # Standalone MCP entry (stdio)
├── core/
│   ├── types.ts             # CommandDefinition and LinkedInClient interfaces
│   ├── client.ts            # Voyager requests, cookie/CSRF headers, retries
│   ├── transport.ts         # Node fetch and optional local curl transport
│   ├── redirects.ts         # Auth/challenge redirect classification
│   ├── handler.ts           # executeCommand(): endpoint/field mappings
│   ├── auth.ts              # resolveAuth(): Chrome, flags, env, config
│   ├── chrome-cookies.ts    # Local Chrome cookie import
│   ├── config.ts            # ~/.linkedin-cli/config.json manager
│   ├── errors.ts            # Typed errors
│   └── output.ts            # JSON, --fields, --quiet
├── commands/
│   ├── index.ts             # allCommands registry and registerAllCommands()
│   ├── auth/login.ts        # Special login, logout, status commands
│   ├── mcp/index.ts         # MCP start command
│   ├── profile/view.ts      # Profile commands
│   ├── posts/create.ts      # Create, edit, delete posts
│   ├── feed/feed.ts         # Member/company feeds
│   ├── engage/engage.ts     # Reactions, comments, reposts
│   ├── connections/         # Connection invitations and removal
│   ├── messaging/           # Conversations and messages
│   ├── search/search.ts     # People, companies, jobs, post-search limitation
│   ├── companies/           # Company profiles and following
│   ├── jobs/                # Job details and skill insights
│   └── analytics/           # Profile-view analytics
└── mcp/server.ts            # MCP tool registration loop

Read the full file on GitHub · 737 lines

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.

14d ago Changed · +74 lines · +914 tokens per session 938d1d4aece9
2mo ago First seen · 663 lines · 5,053 tokens per session scan A b87628281ecc

Subscribe to this mod's changes

linkedincli AGENTS.md is an instructions file published in the GitHub repository bcharleson/linkedincli (73 stars, last pushed 14d ago), licensed MIT. It adds 5,967 tokens to every session, about $0.0239 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Marketing and SEO

linkedincli AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
linkedincli AGENTS.mdbcharleson/linkedincli	Instructions file	73	14d ago	MIT	A	5,967	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

linkedincli: Instructions file for Codex