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 naveedharri/benai-skills --skill lead-qualificationgit clone --depth 1 https://github.com/naveedharri/benai-skillsWrote 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/naveedharri/benai-skills/lead-qualification)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/lead-qualification"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/lead-qualification/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/naveedharri/benai-skills/lead-qualification"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/lead-qualification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Memory Poisoning · line 163 Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.Fix: Do not allow untrusted input to persist in agent memory or context. Validate all content before storing and implement memory isolation between sessions.
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 | $0.00137 | $0.02051 |
| Opus 5.5 | $0.00055 | $0.00820 |
| Sonnet 5.5 | $0.00027 | $0.00410 |
| Haiku 4.5 | $0.00014 | $0.00205 |
Grade A, and why
lead-qualification 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lead Qualification
You are qualifying a list of B2B leads against the user's Ideal Customer Profile. Your job is to take a raw lead list, understand exactly what the user considers a "good" lead, and return a clean set of qualified leads with clear reasoning for each decision.
Before You Do Anything
You need two things from the user. Do not proceed without both:
- The lead list - a file (CSV, XLSX, or JSON) containing the leads
- The ICP definition - the user's specific criteria for what makes a qualified lead
Getting the ICP Right
The ICP definition can be literally anything. Never assume what it looks like. Ask the user to describe their ideal customer in their own words. Here are examples of dimensions they might care about, but this list is not exhaustive:
- Services offered: "must offer SEO services", "must be a marketing agency", "must do paid media"
- Technologies used: "must use HubSpot", "must run on Shopify", "must work with WordPress"
- Headcount / company size: "11-500 employees", "under 50 people", "enterprise only"
- Geography: "US-based only", "must be in DACH region", "California agencies only"
- Industry / vertical: "healthcare", "SaaS", "legal services", "e-commerce"
- Revenue range: "must be doing $1M+ ARR"
- Job title of the contact: "must be Director level or above", "must be a founder/CEO"
- Company age: "must be at least 2 years old"
- Something completely different: always be open to criteria you haven't seen before
If the user's ICP is vague (e.g., "good companies" or "people who would be interested"), push back. Ask: "What specifically makes a company a good fit? What would make you NOT want to reach out?" You need concrete, actionable criteria.
Handling Complex ICPs
Sometimes the ICP has AND conditions ("must be US-based AND offer SEO AND have 11-50 employees") and sometimes it has OR conditions ("healthcare OR legal vertical"). Clarify the logic. Ask: "Do they need to meet ALL of these, or are some of these nice-to-haves?"
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 Changed · -5 lines · +137 tokens per session 31130e37d9d8
- 1mo ago First seen · 166 lines · 0 tokens per session scan A 4fcd08af15f9
lead-qualification is a skill published in the GitHub repository naveedharri/benai-skills (74 stars, last pushed 16d ago), licensed MIT. It adds 137 tokens to every session and 2,051 once invoked, about $0.0005 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 2026-09-05.
Other skills, from other repositories
project
A single starting point for setting up an AI-assisted project in Claude Cowork. It asks questions about the work, reviews available add-ons, and creates project instructions, custom agents, and connected workflows.
doc-html-slide
A renderer that turns presentation content into a single HTML slide deck that opens directly in a browser. It creates a 16:9 slide sequence with navigation, fullscreen viewing, printing to PDF, and speaker-note controls.
cs-channel-message
A channel-message writing tool for search ads, advertising, customer relationship messages, and app notifications. It uses the NCM sequence—Need, Channel, Moment, Message, and CTA—to adapt wording to where and when customers see it.
media-higgsfield-explainer
A Higgsfield workflow for making non-photorealistic narrated explainer videos. It pairs each narration line with a 10-second animated clip and joins the clips into one finished video.
setup-mcp-connector
A step-by-step setup guide for connecting Cowork to services such as Google Drive, Notion, and Higgsfield, plus Korean public-data, document, statistics, architecture, and law services. It explains authentication, API keys, test calls, and troubleshooting.
media-gpt-image-prompt
An image-prompt writing tool that turns a natural-language idea into detailed prompts for GPT Image 2.5. It can also adapt the same idea for Gemini 3 Pro Image and Midjourney.