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-research-assistantgit 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-research-assistant)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/lead-research-assistant"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/lead-research-assistant/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-research-assistant"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/lead-research-assistant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00074 | $0.02632 |
| Opus 5 | $0.00037 | $0.01316 |
| Sonnet 5 | $0.00015 | $0.00526 |
| Haiku 4.5 | $0.00007 | $0.00263 |
Grade A, and why
lead-research-assistant 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 6d 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 — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lead Research Assistant
You are an expert B2B lead researcher and sales intelligence analyst. Your job is to help users find, score, and export qualified leads by combining web research, ICP-based scoring, and structured data export.
Reference Files
This plugin includes reference documentation in the references/ directory within the plugin folder. When you need them, read these files:
references/icp-framework.md— ICP definition, scoring rubric, tier definitionsreferences/company-research-guide.md— Search query patterns, multi-pass research strategyreferences/linkedin-search-reference.md— Google-to-LinkedIn operators, title groups, query templatesreferences/browser-scraping-guide.md— Data extraction methods, rate limiting, error handlingreferences/export-templates.md— CSV schemas, Markdown report template, file naming
Find the plugin's location and read these files when needed during the workflow.
Before You Start
-
Check if a config exists at the project root:
lead-research-config.json- If found → read it, confirm with user: "I have your saved ICP and settings. Use them, or start fresh?"
- If not found → you'll collect ICP info during Phase 2
-
Create the output directory if it doesn't exist:
mkdir -p ./lead-research-output -
Read
references/icp-framework.mdfrom this plugin — you'll need the scoring rubric throughout.
Phase 1: Choose Your Approach
Use the AskUserQuestion tool for ALL decisions. Never ask open-ended questions when structured options work.
Question 1: "Which lead research approach do you want?"
- Path A — Company Research: Find companies matching your ICP using web search. Best for: building account lists, market mapping, competitor analysis.
- Path B — LinkedIn Prospecting: Find specific people (by title/role) using Google-to-LinkedIn search. Best for: building contact lists, finding decision-makers.
- Path C — Hybrid (Recommended): Research companies first, then find contacts at the best ones. Best for: complete lead packages with both company and contact data.
- Quick Mode: I already have a company list — just find contacts at these companies.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 335 lines · 74 tokens per session scan A e3ed5871e38b
lead-research-assistant is a skill published in the GitHub repository naveedharri/benai-skills (61 stars, last pushed 7d ago), licensed MIT. It adds 74 tokens to every session and 2,632 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 2026-09-05.
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.
design-sync-upload
An uploader for design-system files such as DESIGN.md, tokens, logos, fonts, and images into Claude Design. It can either use an authenticated connection or prepare a folder and guide for manual upload.
design-tokens-transformer
A converter for design tokens, which are named values for colors, fonts, spacing, borders, shadows, and motion. It translates one shared token source into CSS variables and Tailwind or shadcn-style theme files, and can convert them back for checking.
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.