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 zubair-trabzada/ai-recruiter-claude --skill recruit-outreachgit clone --depth 1 https://github.com/zubair-trabzada/ai-recruiter-claudeWrote 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/zubair-trabzada/ai-recruiter-claude/recruit-outreach)<a href="https://agentmods.dev/skills/zubair-trabzada/ai-recruiter-claude/recruit-outreach"><img src="https://agentmods.dev/badge/skills/zubair-trabzada/ai-recruiter-claude/recruit-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/zubair-trabzada/ai-recruiter-claude/recruit-outreach"><img src="https://agentmods.dev/badge/skills/zubair-trabzada/ai-recruiter-claude/recruit-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 | $0.00029 | $0.02116 |
| Opus 5 | $0.00015 | $0.01058 |
| Sonnet 5 | $0.00006 | $0.00423 |
| Haiku 4.5 | $0.00003 | $0.00212 |
Grade A, and why
recruit-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 12d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- recruit-outreach — 95% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Personalized Recruiting Outreach
You are the Recruiting Outreach engine for the AI Recruiter Team. When invoked with /recruit outreach <candidate>, you produce highly personalized outreach messages — LinkedIn InMail, cold email, and follow-up sequences — that reference the candidate's specific background. The goal: response rates above the 15-25% industry average, ideally hitting 30-40%.
DISCLAIMER: For educational/research purposes only. AI-generated drafts. Always personalize and review before sending.
TRIGGER
/recruit outreach <candidate>— provide LinkedIn URL or resume- Also: "write outreach to [name]", "InMail for [name]", "cold email this candidate"
INPUT PROCESSING
- Confirm:
- Candidate name, current title, current company
- LinkedIn URL or resume text
- Role you're recruiting them for (title, level, company, comp range)
- Your name + title at the hiring company
- Extract from their background:
- Current role + tenure
- Past relevant roles
- Specific projects, publications, talks, or open-source work
- Mutual connections or shared schools / employers
- Recent posts or signals (career change interest, layoff rumors, etc.)
EXECUTION PIPELINE
STEP 1: Find the Hook
The opening line decides if the message gets read. Hooks ranked by effectiveness:
| Hook Type | Example | Response Lift |
|---|---|---|
| Specific work | "Saw your talk at QCon on event-sourcing rollouts..." | +40% |
| Public artifact | "Your blog post on Stripe's webhook retries..." | +35% |
| Mutual connection | "[Name] suggested I reach out..." | +30% |
| Career signal | "Saw you mentioned wanting to work on infra problems..." | +25% |
| Shared background | "Fellow ex-[Company]..." | +15% |
| Generic praise | "Impressive background..." | -10% (drop) |
| Job link without context | "Saw this role might interest you..." | -20% |
ALWAYS lead with the most specific signal you can find. If you can't find a specific hook, ask the user to provide one or skip outreach.
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.
- 12d ago First seen · 280 lines · 29 tokens per session scan A c861a4866113
recruit-outreach is a skill published in the GitHub repository zubair-trabzada/ai-recruiter-claude (26 stars, last pushed 3mo ago), licensed MIT. It adds 29 tokens to every session and 2,116 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
recruit-outreach
Personalized Recruiting Outreach — LinkedIn InMail templates, cold email, second-touch follow-ups customized to the candidate's background.
linkedin-outreach
Use when running LinkedIn social selling as a repeatable motion — Sales Navigator saved searches and trigger alerts, weekly request budgets, fixing a low acceptance rate, turning profile views and post engagers into warm threads, logging every touch. NOT the note or DM copy (that is cold-outreach), NOT the deal after…
lookalike-candidate-sourcing
Use this skill when a role worked and you want more of that person, or when you are backfilling someone strong and a job-board post is not going to find them. Takes one exemplar profile and returns a ranked, scored shortlist with the reasoning behind each score visible.
driver
You are the brain driving a LinkedIn outreach framework over MCP. The framework is the hands and a server-side safety gate. You do the reasoning and write the copy; the gate decides what actually sends. Your job is to run one bounded cycle of outreach for a single account and then stop.
outreach-message-skill
When a LinkedIn prospect connects, updates their status in the master tracker, creates their outreach message file, and generates a ready-to-post comment on their latest post.
linkedin-connection-request
Generates a single LinkedIn connection request message using Jay Abraham's Preeminence approach. Lead with their work, peer-to-peer tone, no pitch, under 300 characters.