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.
npx skills add librefang/librefang-registry --skill linkedingit clone --depth 1 https://github.com/librefang/librefang-registryWrote 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.
[](https://agentmods.dev/skills/librefang/librefang-registry/linkedin)<a href="https://agentmods.dev/skills/librefang/librefang-registry/linkedin"><img src="https://agentmods.dev/badge/skills/librefang/librefang-registry/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.
<a href="https://agentmods.dev/skills/librefang/librefang-registry/linkedin"><img src="https://agentmods.dev/badge/skills/librefang/librefang-registry/linkedin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00028 | $0.08685 |
| Opus 5.5 | $0.00011 | $0.03474 |
| Sonnet 5.5 | $0.00006 | $0.01737 |
| Haiku 4.5 | $0.00003 | $0.00869 |
Grade A, and why
linkedin-hand-skill 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -H "Authorization: Bearer $LINKEDIN_ACCESS_TOKEN" \ This is a copy
100% identical to linkedin-hand-skill — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 1,040 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LinkedIn Management Expert Knowledge
LinkedIn API Reference
Authentication
LinkedIn API uses OAuth 2.0 with bearer tokens.
Bearer Token:
Authorization: Bearer $LINKEDIN_ACCESS_TOKEN
Core Endpoints
Get authenticated user info:
curl -s -H "Authorization: Bearer $LINKEDIN_ACCESS_TOKEN" \
-H "LinkedIn-Version: 202405" \
"https://api.linkedin.com/rest/userinfo"
Create a text post (Posts API):
curl -s -X POST "https://api.linkedin.com/rest/posts" \
-H "Authorization: Bearer $LINKEDIN_ACCESS_TOKEN" \
-H "Content-Type: application/json" \
-H "LinkedIn-Version: 202405" \
-d '{
"author": "urn:li:person:MEMBER_ID",
"lifecycleState": "PUBLISHED",
"commentary": "Your post content here",
"visibility": "PUBLIC",
"distribution": {
"feedDistribution": "MAIN_FEED"
}
}'
Comment on a post:
curl -s -X POST "https://api.linkedin.com/rest/socialActions/URN/comments" \
-H "Authorization: Bearer $LINKEDIN_ACCESS_TOKEN" \
-H "Content-Type: application/json" \
-H "LinkedIn-Version: 202405" \
-d '{
"actor": "urn:li:person:MEMBER_ID",
"message": {"text": "Your comment here"}
}'
Like a post:
curl -s -X POST "https://api.linkedin.com/rest/socialActions/URN/likes" \
-H "Authorization: Bearer $LINKEDIN_ACCESS_TOKEN" \
-H "Content-Type: application/json" \
-H "LinkedIn-Version: 202405" \
-d '{
"actor": "urn:li:person:MEMBER_ID"
}'
Rate Limits
| Endpoint | Limit | Window |
|---|---|---|
| Posts | 25 posts | 24 hours |
| Comments | 10 comments | 1 minute |
| Likes | 20 likes | 1 minute |
| API calls (general) | 100 requests | 1 day |
LinkedIn Content Strategy
The LinkedIn Algorithm (2024-2025)
Key factors that affect reach:
- Dwell time: How long people spend reading your post. LinkedIn tracks both "read dwell" (time spent on post text) and "click dwell" (time spent after clicking "see more"). Longer posts that hold attention get amplified. Ideal: 800-1300 characters that reward reading to the end.
- Early engagement: Comments in the first 60-90 minutes are weighted heavily. The algorithm decides distribution tiers within 2 hours of posting.
- Meaningful comments: Long comments (3+ sentences) signal quality far more than likes. One thoughtful comment is worth ~10 likes in the algorithm. Reply-to-reply threads (nested comments) further boost the post.
- No external links: Posts with links get 40-50% less reach. The algorithm deprioritizes anything that drives users off-platform.
- Personal stories: Narrative content outperforms promotional content. The algorithm favors "knowledge and advice" posts from individuals over brand content.
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.
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.
- 2mo ago First seen · 1,040 lines · 28 tokens per session scan A eee70aa10e7b
linkedin-hand-skill is a skill published in the GitHub repository librefang/librefang-registry (11 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 8,685 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to linkedin-hand-skill, differing in 0 lines, and is treated as a copy.
linkedin-hand-skill compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| linkedin-hand-skilllibrefang/librefang-registry | Skill | 11 | 1mo ago | MIT | A | 28 | Claude Code, Codex |
| LinkedIn Automationclaude-office-skills/skills | Skill | 567 | 9mo ago | MIT | A | 19 | Claude Code, Codex |
| banner-designoyi77/1ai-skills | Skill | 17 | yesterday | MIT | A | 58 | Claude Code |
| content-writerEvovexAI/EvoFlow | Skill | 606 | yesterday | none | A | 45 | Claude Code, Codex |
| linkedin-post-creatorrefly-ai/refly-skills | Skill | 204 | 6d ago | none | A | 30 | Claude Code, Codex |
| Social Post Thread WriterNotysoty/openagentskills | Skill | 9 | 2mo ago | MIT | A | 30 | Claude Code, Codex |
| create-contentsundial-org/awesome-openclaw-skills | Skill | 674 | 8mo ago | none | B | 13 | Claude Code, Codex |