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-humanizernpx skills add styfinity/linkedin-engine --skill linkedin-humanizergit 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 | $0.00042 | $0.00501 |
| Opus 5 | $0.00021 | $0.00251 |
| Sonnet 5 | $0.00008 | $0.00100 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
linkedin-humanizer 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 Humanizer
The draft that reads like a machine wrote it gets ignored. This skill removes the tells and puts the human voice back in, without touching the meaning.
Inputs
- Any draft (a post, a DM, a comment): $ARGUMENTS
- The brief (persona voice, pains, offer) loads automatically, so use it to match the operator's real register.
Do this
- Remove every em-dash. Replace with a comma, a period, or " - ".
- Strip banned AI vocabulary: leverage, delve, landscape, navigate, utilize, foster, robust, supercharge, seamless, unlock, elevate, harness, empower, streamline, "game-changer", and any thesaurus word a person would not say out loud.
- Break up rule-of-three symmetric lists. Real people do not write in perfect triplets.
- Delete fake-candid openers: "Let me be honest", "Here's the thing", "I'll be the first to admit". Cut straight to the point.
- Vary the sentence length. Uniform rhythm is the loudest AI tell. Put a short one next to a long one.
- Put the human back: one casual run-on with a comma splice, plain low-reading-level words, one direct un-hedged opinion, and a flat statement (not a question) to end on.
- Keep "I" not "we" in the hook. The operator is one person, not a brand.
Output
The cleaned draft first. Then a short bullet diff: what was changed and why. Then a one-line verdict: PUBLISH, or STILL READS AI - fix these (name the exact phrases).
Rules
- Never change the meaning or the claims. Keep all numbers exactly as written.
- This is a polish pass, not a rewrite. If a line is already human, leave it.
- If anything still reads like AI after the pass, flag the specific phrase, do not silently let it through.
- No em-dashes in the output. Obviously.
- This skill only cleans drafts. It does not publish. The operator approves and posts.
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 · 33 lines · 42 tokens per session scan A 8d192b63b71d
linkedin-humanizer is a skill published in the GitHub repository styfinity/linkedin-engine (7 stars, last pushed 2mo ago), licensed MIT. It adds 42 tokens to every session and 501 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…
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…
copywriting-follow-up
Writes follow-up cold emails after no reply from a prospect. Use this skill whenever the user wants to follow up on an email that got no response, says "write a follow-up", "they didn't reply, what do I send?", "draft a bump email", "write email 2 or 3 of my sequence", or asks how to re-engage a cold prospect. Works…
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…
copywriting-manager-sequence
Writes a 3-email outbound sequence targeting Manager-level buyers (Sales Manager, Marketing Manager, RevOps Manager, Team Lead, Operations Manager, etc.). Use this skill whenever the user wants to write cold emails for a Manager, says "write me a sequence for a Sales Manager", "draft emails targeting managers", or…
copywriting-vp-sequence
Writes a 3-email outbound sequence targeting VP-level buyers (VP Sales, VP Marketing, VP Revenue, VP Operations, VP Product, etc.). Use this skill whenever the user wants to write cold emails for a VP, says "write me a sequence for a VP of Sales", "draft emails targeting VP-level", or provides a VP persona and asks…