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 mardab96/b2b-lead-generation-claude-skills --skill what-to-say-to-this-companygit clone --depth 1 https://github.com/mardab96/b2b-lead-generation-claude-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/mardab96/b2b-lead-generation-claude-skills/what-to-say-to-this-company)<a href="https://agentmods.dev/skills/mardab96/b2b-lead-generation-claude-skills/what-to-say-to-this-company"><img src="https://agentmods.dev/badge/skills/mardab96/b2b-lead-generation-claude-skills/what-to-say-to-this-company/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/mardab96/b2b-lead-generation-claude-skills/what-to-say-to-this-company"><img src="https://agentmods.dev/badge/skills/mardab96/b2b-lead-generation-claude-skills/what-to-say-to-this-company.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 | $0.00061 | $0.00981 |
| Opus 5 | $0.00030 | $0.00491 |
| Sonnet 5 | $0.00012 | $0.00196 |
| Haiku 4.5 | $0.00006 | $0.00098 |
Grade A, and why
what-to-say-to-this-company 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What to Say to This Company
Use this skill when
The account is chosen and the message is not.
This is the point where most outbound quietly dies. The list is fine, the targeting is fine, and then someone opens a blank email, cannot find anything specific to say, reaches for the template, and sends the same paragraph that the other forty vendors sent that quarter.
Use it for one company at a time. It is not a list-processing tool, and running it across two hundred accounts to generate two hundred openers produces exactly the generic output it exists to avoid.
Required input
- The company name and website.
- Who you sell to there, by role.
- What you actually do, in one honest sentence.
Anything else that is genuinely available helps and none of it is mandatory:
- their careers page, pricing page, or recent announcements
- the specific person's profile or posts
- whether anyone at your company has spoken to them before
- what happened with similar companies you have won or lost
Analysis workflow
- Establish what this company visibly does, in their own words, before forming any opinion about what they need.
- Look for observable facts with commercial meaning: hiring in a function, a pricing model change, a market they entered, a product line they dropped, a job ad that describes the problem you solve.
- Separate the observable from the assumed, and keep them separate in the output. "They posted three SDR roles" is observable. "They are struggling with pipeline" is a guess dressed as insight, and buyers can hear the difference immediately.
- Form one hypothesis about a problem they plausibly have, tied to something specific you found, and state what would disprove it.
- Write the opener around that one thing. One angle, not three.
- Sanity check it with the substitution test: replace the company name with a competitor's name. If the message still works, it is a template and it goes back to step 2.
- Give the honest fallback. Sometimes there is nothing specific to find, and the right move is a short, plain, low-claim message rather than a manufactured observation.
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 · 84 lines · 61 tokens per session scan A dd7ca34be8b8
what-to-say-to-this-company is a skill published in the GitHub repository mardab96/b2b-lead-generation-claude-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 981 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…