post-linkedin

post-linkedin is a skill for Claude Code, Codex from tang-vu/social-posting-skills. It costs 15 tokens per session (1,959 once invoked), scanned A, original, MIT.

A writing guide for preparing thought-leadership posts for LinkedIn, a professional networking website. It covers post length, media, hashtags, links, content formats, and the need for human review.

In plain words
What is it for?
It is for drafting LinkedIn posts, carousel documents, polls, videos, hashtags, and comments that contain links, ready for manual posting.
Why use it?
It helps shape LinkedIn content around the platform's publishing limits and audience expectations. It also warns against generic or overly automated writing.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit It is for drafting LinkedIn posts, carousel documents, polls, videos, hashtags, and comments that contain links, ready for manual posting.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tang-vu/social-posting-skills/post-linkedin
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 tang-vu/social-posting-skills --skill post-linkedin
Clone the repo
git clone --depth 1 https://github.com/tang-vu/social-posting-skills

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.

agentmods badge for post-linkedin

README.md
[![agentmods](https://agentmods.dev/badge/skills/tang-vu/social-posting-skills/post-linkedin/github.svg)](https://agentmods.dev/skills/tang-vu/social-posting-skills/post-linkedin)
Your own site
<a href="https://agentmods.dev/skills/tang-vu/social-posting-skills/post-linkedin"><img src="https://agentmods.dev/badge/skills/tang-vu/social-posting-skills/post-linkedin/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 post-linkedin

Your own site · 80×15
<a href="https://agentmods.dev/skills/tang-vu/social-posting-skills/post-linkedin"><img src="https://agentmods.dev/badge/skills/tang-vu/social-posting-skills/post-linkedin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,959 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 $0.00015 $0.01959
Opus 5 $0.00008 $0.00979
Sonnet 5 $0.00003 $0.00392
Haiku 4.5 $0.00002 $0.00196

Measured 11d ago against content hash f877328096bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

post-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 11d 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.

.agents/skills/post-linkedin/SKILL.md · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LinkedIn Posting Skill

Platform Overview

LinkedIn is the professional networking platform with 1B+ members. It's the best platform for B2B thought leadership, career content, and professional brand building. LinkedIn organic reach is still excellent compared to other platforms.

Platform Constraints

  • Character Limit: 3,000 characters per post
  • Media: Images, videos, documents (carousel PDFs), polls
  • Hashtags: 3-5 per post (at the bottom)
  • Links: Put in comments — links in body reduce reach by 25-35%
  • Linkless posts: Get 6x more reach and 18x more comments than posts with links
  • Videos: Native video gets 5x more reach than YouTube links
  • Carousels: Document posts get 2-3x reach
  • 80/20 Rule: 80% native content, 20% with links (in comments)

AI Content Warning (2025)

LinkedIn's algorithm now scrutinizes AI-generated content. Overly generic or automated posts get reduced reach. Authentic, human-driven content is strongly prioritized.

  • Posts analyzed for AI-generated material
  • Generic, template-like content is penalized
  • Add personal stories, specific details, and genuine voice to stand out
  • Human oversight is essential even when using AI to draft

MANDATORY: Put links in the FIRST COMMENT, NEVER in the post body.

  • Links in the body reduce reach by 25-35% (confirmed by LinkedIn's own algorithm)
  • Linkless posts get 6x more reach and 18x more comments
  • The ONLY correct strategy: Write a text-only post, publish it, then immediately add a comment with the link
  • Even "link in bio" is better than link in body
  • This is the single most important rule for LinkedIn reach

Posting Method: MANUAL PASTE

LinkedIn blocks browser automation via system policy. The agent generates content and saves it to posts/drafts/linkedin_post.md. You paste it manually.

Manual Paste Steps

  1. Agent generates LinkedIn-optimized content
  2. Content saved to posts/drafts/linkedin_post.md
  3. User opens linkedin.com in their browser
  4. User pastes the content into the post composer
  5. User adds any images or documents manually
  6. User clicks "Post"

Read the full file on GitHub · 232 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.

  1. 11d ago First seen · 232 lines · 15 tokens per session scan A f877328096bb

Subscribe to this mod's changes

post-linkedin is a skill published in the GitHub repository tang-vu/social-posting-skills (9 stars, last pushed 6mo ago), licensed MIT. It adds 15 tokens to every session and 1,959 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 2026-08-31.