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 TaplioOfficial/taplio-linkedin-claude-skills --skill linkedin-connection-request-hookgit clone --depth 1 https://github.com/TaplioOfficial/taplio-linkedin-claude-skillsWrote 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/taplioofficial/taplio-linkedin-claude-skills/linkedin-connection-request-hook)<a href="https://agentmods.dev/skills/taplioofficial/taplio-linkedin-claude-skills/linkedin-connection-request-hook"><img src="https://agentmods.dev/badge/skills/taplioofficial/taplio-linkedin-claude-skills/linkedin-connection-request-hook/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/taplioofficial/taplio-linkedin-claude-skills/linkedin-connection-request-hook"><img src="https://agentmods.dev/badge/skills/taplioofficial/taplio-linkedin-claude-skills/linkedin-connection-request-hook.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 | $0.00119 | $0.01924 |
| Opus 5.5 | $0.00048 | $0.00770 |
| Sonnet 5.5 | $0.00024 | $0.00385 |
| Haiku 4.5 | $0.00012 | $0.00192 |
Grade A, and why
linkedin-connection-request-hook 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 25d 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.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LinkedIn Connection Request Hook
A connection request without a note gets accepted 30 to 40% of the time. With the right note, 70% and above. This skill writes that note, and when the person came from the user's comments, it references what they actually said.
When to trigger
The user says "write me a connection request to X", "I want to connect with Y", "what should I say in my invite", "invite the people who commented on my post", or the Warm Lead Finder skill hands over a lead.
Inputs to ask for (only if missing)
- The target : name, role, company, or a lead from the Warm Lead Finder.
- The context :
- Cold : no prior interaction.
- Post-comment : the user commented on their post (or they exchanged in a thread).
- Post-event : same event, webinar, podcast.
- Post-engagement : the target commented on the user's post. The MCP can pull the exact comment.
- Mutual contact : someone they both know.
- The honest reason to connect (interested in their work, want to do business, looking for advice).
The user's positioning, tone, and language come from get_me.
The 4 rules of a great connection request
- 300 characters. LinkedIn cuts past 300. Count them.
- One specific reference. Something only they would recognize : their post, their comment, a line they wrote, the event. Generic notes get ignored.
- No pitch. The request is to connect, not to sell.
- No "I would love to learn from you". The most worn-out line on LinkedIn, and it signals nothing to offer back.
Process by context
Cold
- Reference one specific thing they did or said publicly.
- State why you, specifically, want to connect. Two sentences.
Post-comment
- Reference the post and the exchange in the thread.
- Suggest the conversation continues in the network.
Post-event
- Name the event. Reference one specific moment.
Post-engagement (they commented on the user's post)
- Quote or paraphrase what they said, thank them for it specifically.
- Open the door : "happy to go deeper on [their point] if useful".
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.
- 25d ago Changed · +1 lines 33dba57f615b
- 1mo ago First seen · 111 lines · 119 tokens per session scan A 08e52c2e1e37
linkedin-connection-request-hook is a skill published in the GitHub repository TaplioOfficial/taplio-linkedin-claude-skills (9 stars, last pushed 23d ago), licensed MIT. It adds 119 tokens to every session and 1,924 once invoked, about $0.0005 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 2026-09-12.
linkedin-connection-request-hook compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| linkedin-connection-request-hookTaplioOfficial/taplio-linkedin-claude-skills | Skill | 9 | 23d ago | MIT | A | 119 | Claude Code |
| linkedin-humanizersergebulaev/linkedin-skills | Skill | 5.6k | 3d ago | MIT | A | 93 | Claude Code |
| linkedin-marketingsergebulaev/linkedin-skills | Skill | 5.6k | 3d ago | MIT | A | 97 | Claude Code |
| linkedin-reply-handlersergebulaev/linkedin-skills | Skill | 5.6k | 3d ago | MIT | A | 108 | Claude Code |
| linkedin-post-writersergebulaev/linkedin-skills | Skill | 5.6k | 3d ago | MIT | A | 120 | Claude Code |
| linkedin-comment-draftersergebulaev/linkedin-skills | Skill | 5.6k | 3d ago | MIT | A | 97 | Claude Code |
| linkedin-content-plannersergebulaev/linkedin-skills | Skill | 5.6k | 3d ago | MIT | A | 78 | Claude Code |