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 styfinity/linkedin-engine --skill linkedin-cold-revivergit clone --depth 1 https://github.com/styfinity/linkedin-engineWrote 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/styfinity/linkedin-engine/linkedin-cold-reviver)<a href="https://agentmods.dev/skills/styfinity/linkedin-engine/linkedin-cold-reviver"><img src="https://agentmods.dev/badge/skills/styfinity/linkedin-engine/linkedin-cold-reviver/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/styfinity/linkedin-engine/linkedin-cold-reviver"><img src="https://agentmods.dev/badge/skills/styfinity/linkedin-engine/linkedin-cold-reviver.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 | $0.00044 | $0.00548 |
| Opus 5.5 | $0.00018 | $0.00219 |
| Sonnet 5.5 | $0.00009 | $0.00110 |
| Haiku 4.5 | $0.00004 | $0.00055 |
Grade A, and why
linkedin-cold-reviver 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 1mo 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 — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LinkedIn Cold Reviver
A dying thread does not get revived by chasing. It gets revived by a new gift. This skill spots the cooling, then writes one revival message that is itself a value bomb.
Inputs
- The thread that has gone quiet (paste the full back-and-forth, with rough dates if you have them): $ARGUMENTS
- The brief (persona pains, offer, voice) loads automatically, so do not re-ask for context it already holds.
Do this
- Confirm it is actually cooling. Read the thread. Name the signal: a reply that trailed off, a "let me think", days of silence after warmth. If it is not cold yet, say so and stop.
- Find a brand-new angle. Do not reopen the old question. Pick a different pain, a different proof, or a different artefact tied to their world. One angle, not three.
- Build the value bomb. Write the message so the useful thing lands even if they never reply: a teardown, a specific number, a one-page resource, a stolen-with-pride tactic. They keep the value either way.
- Write the standalone CTA. It must work with zero memory of the prior thread. It names the artefact, states the one-word reply cost ("Reply 'send' and it's yours"), and names the outcome they get from it.
Output
- The revival message (the value bomb plus the standalone CTA), ready to read.
- A one-line note: why this angle is different from the one that went quiet.
- If they bite, hand the reply to /linkedin-reply-triager. Run /linkedin-humanizer on the draft before it ever sends.
Rules
- Never just re-ask the old question. A nag is not a revival.
- The value must land even if they bin you. If the message only works on a reply, rewrite it.
- One new angle, not a pile of follow-ups. No "just bumping this", no "did you see my last message".
- Draft only. Claude drafts, you approve, nothing sends without you. Sending happens only through the opt-in CLI/MCP layer wired to your own LinkedIn session or provider key, hard-capped at 20 actions/day for new accounts.
- No em-dashes. No guaranteed-result promises.
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.
- 1mo ago First seen · 32 lines · 44 tokens per session scan A ab2ecfdfa562
linkedin-cold-reviver is a skill published in the GitHub repository styfinity/linkedin-engine (9 stars, last pushed 3mo ago), licensed MIT. It adds 44 tokens to every session and 548 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
LinkedIn Automation
Automate LinkedIn marketing, lead generation, content publishing, and professional networking.
linkedin-carousels
Use when building a LinkedIn carousel / document post — the swipeable multi-page PDF — slide by slide: cover hook, narrative arc, one idea per slide, CTA closer, PDF export spec. NOT the account/format plan (that is linkedin-strategy), NOT a text or single-image feed post (that is linkedin-content), NOT a 16:9 talk…
deepline-ads-audiences
Use this skill when building, enriching, auditing, or uploading B2B paid ads audiences to Google Customer Match, Meta/Facebook Custom Audiences, or LinkedIn Matched Audiences. Triggers on phrases like '/deepline-ads-audience', '/deepline-ads-audiences', 'upload this audience', 'create custom audiences', 'personal…
deepline-analytics
Use this skill when answering business analytics, RevOps, GTM metric, pipeline, revenue, funnel, customer, or warehouse questions with Deepline. Triggers on phrases like 'query Snowflake', 'analyze pipeline', 'total ACV', 'break down by quarter', 'use the semantic layer', 'run a semantic query', or any use of…
deepline-engine
Build, publish, and verify a Deepline Play as a durable state machine over Customer DB tables, including a small paid pilot. Invoke this skill explicitly when the user asks to build an engine.
deepline-gtm
GTM leads, enrichment, outreach, Plays, developer signals/Reo.dev. Providers…