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 xiongQvQ/-b2b-lead-hunter-skill --skill b2b-lead-hunter-skillgit clone --depth 1 https://github.com/xiongQvQ/-b2b-lead-hunter-skillWrote 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/xiongqvq/-b2b-lead-hunter-skill/b2b-lead-hunter-skill)<a href="https://agentmods.dev/skills/xiongqvq/-b2b-lead-hunter-skill/b2b-lead-hunter-skill"><img src="https://agentmods.dev/badge/skills/xiongqvq/-b2b-lead-hunter-skill/b2b-lead-hunter-skill/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/xiongqvq/-b2b-lead-hunter-skill/b2b-lead-hunter-skill"><img src="https://agentmods.dev/badge/skills/xiongqvq/-b2b-lead-hunter-skill/b2b-lead-hunter-skill.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 | $0.00088 | $0.03215 |
| Opus 5 | $0.00044 | $0.01607 |
| Sonnet 5 | $0.00018 | $0.00643 |
| Haiku 4.5 | $0.00009 | $0.00321 |
Grade A, and why
b2b-lead-hunter 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.
How it starts
The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
B2B Lead Hunter
Purpose
Research foreign-trade B2B prospects and contact channels for physical-product export, distributor discovery, importer discovery, and outreach preparation.
Hermes owns judgment, evidence review, search iteration, language choice, and approval decisions. Scripts own deterministic normalization, page reading, contact extraction, dedupe, validation, template rendering, draft evaluation, export, and SMTP plumbing.
Default objective: produce a traceable lead file where every company, contact channel, decision maker, score, and outreach draft is tied to source URLs and structured artifacts. Quality gates override target count.
User Workflow Preference
User prefers continuous-cycle execution: mine leads → find decision makers → generate emails → send, all in one loop. Do not pause between stages unless the user explicitly asks to stop. After sending one batch, immediately resume mining the next. The cycle is:
search new leads → get contact emails → send generic emails
→ search decision makers → infer/find DM emails → send DM emails
→ search new leads (next country/niche) → repeat
Do not ask "continue or pause?" after each batch — just keep going until the user says stop.
Non-Negotiable Rules
- Use
scripts/read_jina.pyas the primary reader for every website or URL: seller site, candidate website, contact page, product page, directory profile, or source article. Use browser tools only when Jina fails or interaction is required. - Use Hermes native web search for search queries. Do not open Google, Bing, or other search engines in a browser.
- Keep lead discovery, outreach drafting, human approval, and SMTP sending as separate stages with separate files.
- Do not send email unless the user explicitly requests sending, SMTP config exists, approved records exist, suppression checks run, and
send_smtp.pyreceives matching passing evaluations. - Never auto-send to inferred emails, free-mail addresses, low/reject leads, directory-only leads, records without source URLs, or records without buyer-role evidence.
- A lead cannot enter strict
leads.csvunless company reality, buyer-role evidence, contactability, and source URLs are present. - Do not relax gates to satisfy
target_count. - Directories and B2B platforms are discovery sources, not final truth. Confirm with official or strong independent evidence before accepting.
- Customs/trade evidence is useful buying intent, but absence of customs data is not a rejection reason.
- Every outreach message must include truthful sender identity, source-backed personalization, a low-pressure CTA, and a clear opt-out line.
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 · 265 lines · 88 tokens per session scan A 8443a4b35047
b2b-lead-hunter is a skill published in the GitHub repository xiongQvQ/-b2b-lead-hunter-skill (30 stars, last pushed 3mo ago), licensed MIT. It adds 88 tokens to every session and 3,215 once invoked, about $0.0004 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
aig-scanner
A.I.G Scanner — AI security scanning for infrastructure, AI tools / skills, AI Agents, and LLM jailbreak evaluation via Tencent Zhuque Lab AI-Infra-Guard. Uses built-in exec + Python script, no plugin required. Requires AIGBASEURL to be configured. Triggers on: scan AI service, AI vulnerability scan, scan AI infra…
5writing
A paper-writing workflow for mathematical modelling competitions, supporting both Typst and LaTeX. It uses analysis, results, figures, and a competition template to assemble the document.
6verity
A final-checking workflow for mathematical modelling competition papers, using either Typst or LaTeX to build the document. It checks the finished paper and its supporting files before submission.
typst-author
Generate idiomatic Typst (.typ) code, edit and troubleshoot Typst documents and projects, and answer Typst syntax/reference questions. Use when working with .typ files or when the user explicitly asks for Typst document creation, editing, debugging, compilation, formatting, template work, or package usage.
1start-mathmodel
A starting workflow for mathematical-modeling competitions, which are contests where teams use mathematics, data, and code to solve real-world problems. It asks for preferences, creates planning files, and coordinates later analysis, modeling, coding, charting, diagram, writing, and verification stages.
4drawio
A diagram-making stage for mathematical-modeling projects. It uses existing analysis and results reports to create technical route maps, solution flowcharts, model diagrams, and data-processing diagrams in Drawio, a tool for creating structured diagrams, then exports them as PDF files.