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 growthenginenowoslawski/coldoutboundskills --skill perfect-company-listgit clone --depth 1 https://github.com/growthenginenowoslawski/coldoutboundskillsWrote 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/growthenginenowoslawski/coldoutboundskills/perfect-company-list)<a href="https://agentmods.dev/skills/growthenginenowoslawski/coldoutboundskills/perfect-company-list"><img src="https://agentmods.dev/badge/skills/growthenginenowoslawski/coldoutboundskills/perfect-company-list/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/growthenginenowoslawski/coldoutboundskills/perfect-company-list"><img src="https://agentmods.dev/badge/skills/growthenginenowoslawski/coldoutboundskills/perfect-company-list.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 | $0.00123 | $0.01907 |
| Opus 5.5 | $0.00049 | $0.00763 |
| Sonnet 5.5 | $0.00025 | $0.00381 |
| Haiku 4.5 | $0.00012 | $0.00191 |
Grade A, and why
perfect-company-list 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 26d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Perfect company list
Database filters fail in two directions at once.
- They miss real fits. Industry labels are self-reported, or guessed: many LinkedIn company pages carry the banner "This listing was automatically created by LinkedIn", which means nobody at the company picked the label. We found an FDIC bank listed as Construction, an SEC-registered wealth manager listed as Semiconductor Manufacturing, and a New Jersey school district listed as Retail Luxury Goods and Jewelry.
- They pull in junk. A plain
Banking+United Statesfilter returned 16,895 companies. About 10,500 of them were not banks: 3,679 mortgage companies and lenders, 2,414 credit unions, 2,210 dead sites or unrelated businesses (a Toyota dealer, a pawn and gun shop, a youth soccer club), 839 vendors that sell to banks, and the Federal Reserve Bank of St. Louis.
The fix is not a better filter. It is: use filters to cast a wide net, and use AI to decide who is in it. Judging is now cheap enough that pulling five times too many companies costs almost nothing.
The workflow
1. Learn your customers -> the industries and keywords they actually use
2. Pull every one of those industries + keywords (keep size and geo tight)
3. Judge every single row with one ICP question
4. Loop Claygent finds lookalikes of your fits -> dedupe -> same judge -> repeat
5. Stop when 20 runs in a row add one company or fewer
1. Learn from your customers
Put your customer list (or dream accounts) through Clay's Enrich Company and record, per customer:
- the LinkedIn industry they self-selected
- keywords in their description and job posts
- headcount and HQ geography (the fields databases get right)
Then tally the industries. In our bank demo, 50 known banks used as the "customer list" came back 43 Banking, 4 Financial Services, 2 blank and 1 Telecommunications. You pull all four.
2. Pull every industry and keyword
If even one customer shows up under an industry, pull every company in that industry inside your size and geography band. Add keyword searches over name and description ("bank", "school district", "wealth management") with no industry filter, which is how blank-industry records get in.
What ships with it
2 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.
- 26d ago First seen · 155 lines · 123 tokens per session scan A c9dc0a634de7
perfect-company-list is a skill published in the GitHub repository growthenginenowoslawski/coldoutboundskills (781 stars, last pushed 19d ago), licensed MIT. It adds 123 tokens to every session and 1,907 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 2026-09-29.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.