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-comment-enginenpx skills add styfinity/linkedin-engine --skill linkedin-comment-enginegit 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 | $0.00039 | $0.00522 |
| Opus 5 | $0.00019 | $0.00261 |
| Sonnet 5 | $0.00008 | $0.00104 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
linkedin-comment-engine 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 yesterday.
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 Comment Engine
Warming starts in the comments, not the inbox. This skill writes comments that add real value to someone else's post and quietly pull profile views from the people watching.
Inputs
- The post you want to comment on (paste the full text) and the author's relevance to your ICP (a buyer, a peer, a connector, an audience overlap): $ARGUMENTS
- The brief (persona tone, pains, offer, voice) loads automatically.
Do this
Write two comment variants the user can pick from:
- Add ONE genuine thing. Either a specific insight, a build detail, or a number from real work (attribute to "a post" or "a client", never a named entity). Not "great post", not generic praise.
- Agree-then-extend, or respectfully reframe. Build on the author's point with a second-order observation, or offer a sharper angle without making them wrong.
- Leave a soft hook at the end that earns a profile click: a half-told result, a "here is what most miss", or a question that signals you operate in their world. No pitch, no link.
- Variant A is short and punchy (one or two lines). Variant B is a longer mini-teaching comment (three to five lines) that demonstrates competence.
Output
Two labelled comment variants (A short, B mini-teaching) plus a one-line note on which to use when: A for high-traffic posts where brevity wins attention, B when the author is a direct ICP and you want them to read your whole profile.
Rules
- Never pitch in a comment. Never argue to win. The job is to make a decision-maker click your profile, not to score a point.
- Add value the author would thank you for, even if they never reply.
- Anonymise all proof: keep the numbers, drop the names.
- No em-dashes, no exclamation marks, no "great post", no "thanks for sharing".
- Draft only. Claude drafts, the operator reads and posts. When a reply comes back warm, hand it to /linkedin-reply-triager. Run /linkedin-humanizer on either variant if it reads stiff.
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.
- yesterday First seen · 31 lines · 39 tokens per session scan A 097e37e926f6
linkedin-comment-engine is a skill published in the GitHub repository styfinity/linkedin-engine (7 stars, last pushed 2mo ago), licensed MIT. It adds 39 tokens to every session and 522 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
growth-experimentation
Build a growth experimentation system — ICE scoring, growth sprints, experiment design, statistical significance, and learning repositories. Use when building an experimentation program, running growth sprints, prioritizing tests, or establishing a data-driven growth culture. Triggers on: "experimentation", "growth…
sdk-adoption-tracker
Given your SDK or library name, searches GitHub code search for public repos that import or require it, classifies each repo as company org, affiliated developer, solo developer, or tutorial noise, scores by adoption signal strength, detects new adopters by date, and outputs a ranked list of who is building on you…
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…
xiaohongshu-title
《小红书运营手册 · AI工作台》标题生成与优化技能。用于用户明确要为小红书笔记、封面短句、图文/短视频标题、种草、教程、测评、服务内容起标题、改标题、做标题方向选择时触发。输入可以是正文草稿、选题方向、产品卖点、账号定位、图片/视频描述或已有标题。默认用快速模式输出标题；用户要求分析、首推、理由、方向、诊断或优化时用诊断/优化模式。不要在普通文章标题、论文标题、新闻标题、课程命名等非小红书/社媒场景中自动触发。.
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…