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 agentmods add skills/styfinity/linkedin-engine/linkedin-hook-labnpx skills add styfinity/linkedin-engine --skill linkedin-hook-labgit clone --depth 1 https://github.com/styfinity/linkedin-engineWhat 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 | $0.00041 | $0.00529 |
| Opus 5 | $0.00020 | $0.00264 |
| Sonnet 5 | $0.00008 | $0.00106 |
| Haiku 4.5 | $0.00004 | $0.00053 |
Grade A, and why
linkedin-hook-lab 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 2d 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.
What it actually says
LinkedIn Hook Lab
The hook decides whether the post gets read. This skill writes ten openers across ten proven formulas, scores them, and hands you the two best.
Inputs
- The topic and the audience it is for: $ARGUMENTS
- The brief (persona tone, pains, offer, voice profile) loads automatically.
Do this
- Write one hook for EACH of the ten formulas, in this order:
- Pattern-Break (says the unexpected thing first)
- Counter-Intuitive Insight (the truth most people get backwards)
- Experience-Led Observation (what you noticed doing the work)
- Direct Consequence (the cost of ignoring this)
- Confession + Result (an admission plus what it produced)
- Numbered Promise (a specific count of takeaways)
- Enemy-Hero-Gasoline-Teaser (name the villain, the win, the open loop)
- BREAKING / News (frame it as fresh signal)
- Stat-Anchored (X% vs Y%, a real or clearly-illustrative contrast)
- Mechanism-Reveal (the "here is how it actually works" angle)
- Keep each hook under 235 characters so it survives the "see more" cut. Count them.
- Score each hook 1-10 on the four value levers (dream outcome, perceived likelihood, time-to-result, effort-and-sacrifice) plus scroll-stop power.
- Pick the top two. Say in one line why each beats the rest.
Output
A table of the ten hooks: formula, hook text, character count, score. Then the recommended two, each with a one-line reason. End with a note: pass the chosen hook to the post draft, then run /linkedin-humanizer on the result.
Rules
- Counter-intuitive and BREAKING hooks must still be true and defensible. No claim the body cannot pay off.
- No clickbait. If the hook over-promises, score it down and say so.
- Real numbers only with honest attribution: "a post that did 12,000 impressions", never a named person or company.
- No em-dashes. Draft only - the operator picks the winner and writes the post.
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.
- 2d ago First seen · 39 lines · 41 tokens per session scan A cb918e4d2ad7
linkedin-hook-lab is a skill published in the GitHub repository styfinity/linkedin-engine (7 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 529 once invoked, about $0.0002 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.
Other skills, from other repositories
lemlist-campaign-from-icp
Use when the user says "create a lemlist campaign for X", "build a lemlist campaign from this ICP", "spin a lemlist campaign for Y", "ICP to lemlist", "natural language to lemlist campaign", "draft a lemlist campaign", "lemlist campaign for VPs/Managers/ICs at Z", or any variant indicating they want to turn a…
copywriting-ic-sequence
Writes a 3-email outbound sequence targeting Individual Contributors (SDR, AE, BDR, Account Manager, Marketing Specialist, Sales Rep, RevOps Analyst, CS Rep, etc.). Use this skill whenever the user wants to write cold emails for an IC, says "write me a sequence for SDRs", "draft emails targeting AEs", "emails for…
gtm-action-thinker
Brainstorms, challenges, and pushes any GTM idea to its fullest potential — on both the idea itself and its execution. Use this skill whenever the user shares a campaign idea, an outbound angle, a workflow concept, a positioning hypothesis, or any GTM initiative and wants to think it through deeply. Even if they just…
lost-deal-revival-agent
Drafts revival messages for closed-lost deals when a public company signal contradicts the original objection. Receives the signal-pair watcher's fire payload, fetches the verbatim Claap objection quote, and produces a 2-line draft that quotes it back. Default output is a HubSpot task for human review. Optional…
provider-builder
Use when a teammate wants to add a new vendor to YALC for an existing capability without shipping a release. Triggers include "add a new provider for X", "wire up [vendor] to YALC", "build an adapter for [vendor]", "I want to use [vendor] for [capability]", "add Apollo for icp-company-search", or any variant…
campaign-strategy
Pre-flight strategy advisor for a new campaign. Analyses every past campaign in the local YALC DB (HeyReach campaigns auto-sync on each run), their real outbound copy, where in the sequence each conversation first replied, every prior retro brief, and the validated/proven intelligence file. Then it proposes angle…