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 crm-prospect-mininggit 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/crm-prospect-mining)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/crm-prospect-mining"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/crm-prospect-mining/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/crm-prospect-mining"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/crm-prospect-mining.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, 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 Excessive Agency · line 57 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Agent Snooping · line 197 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Memory Poisoning · line 243 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 | $0.00222 | $0.03405 |
| Opus 5 | $0.00111 | $0.01702 |
| Sonnet 5 | $0.00044 | $0.00681 |
| Haiku 4.5 | $0.00022 | $0.00341 |
Grade A, and why
crm-prospect-mining 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRM Prospect Mining
You are mining a user's CRM to identify high-value prospects hiding in pipeline stages they've written off (Lost, No Show, Churned, Stalled, etc.). The core insight: many of these "dead" leads are actually at large, well-funded companies that are worth re-engaging with the right approach.
The Pipeline At a Glance
CRM Records → Filter Domains → Find LinkedIn Pages → Scrape Company Sizes → Filter High-Value → Enrich with Comms/Intent → Report
Each step is explained in detail below. The key principle throughout: keep it simple, move fast, use parallel sub-agents wherever possible, and let the data do the talking.
Phase 1: Discovery, Understanding the User's Setup
Before touching any data, you need to understand three things. Use the AskUserQuestion tool to gather these efficiently, don't ask one at a time.
1. What does "high-value" mean to them?
Every user defines this differently. Common dimensions:
- Company headcount (most common): "25+ employees", "100+ employees", "enterprise only"
- Industry/vertical: "only SaaS companies", "agencies only", "e-commerce"
- Deal value: "deals worth $10k+", "enterprise tier only"
- Geography: "US-based", "EMEA only"
- Any combination: "50+ employees AND in the US AND deal value over $5k"
If they're unsure, suggest headcount as a sensible default starting point, it's the most reliable signal you can get from LinkedIn and correlates well with budget. A threshold of 25+ employees is a reasonable floor for B2B, but let them decide.
2. Do they want intent analysis?
This is the difference between a quick filter and a deep analysis. Two levels:
- Metrics-only (fast): Filter purely on headcount/industry/deal size. Output is a clean list of companies that meet the criteria. Good for a first pass or when speed matters.
- Metrics + Intent (thorough): On top of the metrics filter, also pull email communications and/or meeting transcripts from the CRM to understand what actually happened with each deal. Did the prospect go cold because of budget? Bad timing? Competitor? This turns the output from "big companies you lost" into "big companies worth re-engaging and here's how to approach them." Much more actionable but takes longer.
What ships with it
4 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.
- 12d ago First seen · 246 lines · 222 tokens per session scan A c19162285687
crm-prospect-mining is a skill published in the GitHub repository naveedharri/benai-skills (61 stars, last pushed today), licensed MIT. It adds 222 tokens to every session and 3,405 once invoked, about $0.0011 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
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.
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.
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-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.