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 surfmind-space/awesome-surfmind --skill linkedin-outreachgit clone --depth 1 https://github.com/surfmind-space/awesome-surfmindWrote 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/surfmind-space/awesome-surfmind/linkedin-outreach)<a href="https://agentmods.dev/skills/surfmind-space/awesome-surfmind/linkedin-outreach"><img src="https://agentmods.dev/badge/skills/surfmind-space/awesome-surfmind/linkedin-outreach/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/surfmind-space/awesome-surfmind/linkedin-outreach"><img src="https://agentmods.dev/badge/skills/surfmind-space/awesome-surfmind/linkedin-outreach.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 | $0.00059 | $0.00807 |
| Opus 5 | $0.00030 | $0.00404 |
| Sonnet 5 | $0.00012 | $0.00161 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
linkedin-outreach 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 11d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Linkedin Outreach
Draft a short career outreach message from the selected text, visible page, job description, company page, person profile, or user request, and present it in chat for copy-paste. Work only from the user's supplied background, target role, proof points, and relationship to the recipient — use a concrete proof point only if they gave it to you, never invent numbers or qualifications. Avoid generic enthusiasm, phone numbers, and pressure; never lead with "please refer me" to a peer. Adapted from santifer/career-ops contacto mode.
- Identify the contact type — recruiter (talent acquisition, sourcer, HR), hiring manager (leads or owns the team), peer (similar role, collaborator, possible referral path), or interviewer (already scheduled or named in the process). If it's unclear, draft by likely type and say what would improve personalization.
- Build the message on the three-sentence framework for that contact type:
- Recruiter: Fit (the direct match — role, relevant experience, location, or availability), Proof (data that answers a screening question before they ask it), CTA (offer to share the CV if it aligns).
- Hiring manager: Hook (a specific challenge their team faces, drawn from the posting, blog, or news), Proof (the user's strongest relevant quantified achievement), CTA (ask how the team is approaching that challenge).
- Peer: Interest (a genuine reference to their work — a post, talk, or project), Connection (something the user is doing in the same space, not a job pitch), CTA (invite their take on a shared topic). Don't ask for a job or referral; it happens naturally if the conversation flows.
- Interviewer: Research (a reference to their work or trajectory), Context (a light tie to the user's experience), CTA (look forward to the scheduled conversation). Keep it light, never eager.
- Keep the message under 300 characters unless the user asks for a longer note, and include one alternate version with a different angle when the context supports it.
Return Contact type, Primary message, Alternative, and Why this works. If the visible page doesn't show enough detail, keep the message honest and ask for the missing detail that would make it stronger.
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.
- 11d ago First seen · 41 lines · 59 tokens per session scan A 0694f7bfffbe
linkedin-outreach is a skill published in the GitHub repository surfmind-space/awesome-surfmind (5 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 807 once invoked, about $0.0003 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
uiux-master
UI/UX expert for design systems, accessibility, and avoiding generic AI-generated design patterns.
cs-master
Expert computer scientist for algorithms, complexity analysis, and distributed systems.
data-science
ML engineering expert for feature engineering, model debugging, and production pipelines.
network-devops
Network performance expert for latency optimization, packet analysis, and infrastructure tuning.
quant-finance
Quantitative finance expert for trading strategies, risk management, and portfolio optimization.
rust-master
Rust expert for async systems, unsafe code, and zero-cost abstractions.