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 Zoominfo/zoominfo-mcp-plugin --skill tam-sizergit clone --depth 1 https://github.com/Zoominfo/zoominfo-mcp-pluginWrote 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/zoominfo/zoominfo-mcp-plugin/tam-sizer)<a href="https://agentmods.dev/skills/zoominfo/zoominfo-mcp-plugin/tam-sizer"><img src="https://agentmods.dev/badge/skills/zoominfo/zoominfo-mcp-plugin/tam-sizer/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/zoominfo/zoominfo-mcp-plugin/tam-sizer"><img src="https://agentmods.dev/badge/skills/zoominfo/zoominfo-mcp-plugin/tam-sizer.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 | $0.00134 | $0.02962 |
| Opus 5 | $0.00067 | $0.01481 |
| Sonnet 5 | $0.00027 | $0.00592 |
| Haiku 4.5 | $0.00013 | $0.00296 |
Grade A, and why
tam-sizer 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 9d 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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TAM Sizer
Iteratively refine a company-level ICP filter set against ZoomInfo's company database. Each pass returns a count, a banded sizing read, labelled sample views, and concrete refinement options. Terminates when the user finalizes — output is both the count and a structured filter-set artifact ready for build-list, score-accounts, or find-similar.
When to use
tam-sizer— user wants count + shape + working filter set, willing to iterate.build-list— filter set already settled; user wants the exportable list.find-similar— user has a seed account, not a filter-based market.
Scope
TAM here = company count AND working filter set, both first-class outputs.
This skill does NOT size contacts. Buyer-persona criteria ("CTOs", "VP Sales") are recorded but NOT applied to the count — they describe who you sell into, not who the account is. Persona discovery is build-list / search-contacts once the filter set is settled.
Input
- ICP description (recommended) — natural language, OR "my ICP" / "our ICP" / nothing (fall back to
get_gtm_context). - Use case (optional) — territory design / investor sizing / ICP sharpening (default).
- SAM hypothesis inputs (optional) —
addressable_fraction(0–1) andarpa_usd.
Workflow
1. Pull GTM context (always)
Call get_gtm_context(detailed: true) first. Use throughout — for filter defaults when the user is vague, sanity-check expectations on the sample, and refinement recommendations. If empty, proceed with user filters only and surface the absence.
2. Parse + merge ICP
Reconcile user text and GTM context. User text wins direct conflicts ("SF" overrides GTM's "North America"); GTM fills gaps. Tag every dimension as user-specified / inherited from GTM / unspecified. Persona criteria recorded but not applied.
3. Disambiguate ambiguous regions BEFORE the search
- "EU" can mean European Union (27 countries) or Europe (continent) —
continent: Europeincludes Russia, Turkey, UK, Switzerland, Norway. Ask one clarifying question if "EU" is unclarified. - "Asia" includes Russia; "Americas" vs "North America" vs "US/Canada" — confirm if uncertain.
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.
- 9d ago First seen · 239 lines · 134 tokens per session scan A 9b4c8bdedd08
tam-sizer is a skill published in the GitHub repository Zoominfo/zoominfo-mcp-plugin (7 stars, last pushed 5d ago), licensed MIT. It adds 134 tokens to every session and 2,962 once invoked, about $0.0007 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
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…