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 tushaarmehtaa/tushar-skills --skill who-to-sell-togit clone --depth 1 https://github.com/tushaarmehtaa/tushar-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/tushaarmehtaa/tushar-skills/who-to-sell-to)<a href="https://agentmods.dev/skills/tushaarmehtaa/tushar-skills/who-to-sell-to"><img src="https://agentmods.dev/badge/skills/tushaarmehtaa/tushar-skills/who-to-sell-to/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/tushaarmehtaa/tushar-skills/who-to-sell-to"><img src="https://agentmods.dev/badge/skills/tushaarmehtaa/tushar-skills/who-to-sell-to.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 | $0.00050 | $0.01789 |
| Opus 5.5 | $0.00020 | $0.00716 |
| Sonnet 5.5 | $0.00010 | $0.00358 |
| Haiku 4.5 | $0.00005 | $0.00179 |
Grade A, and why
who-to-sell-to 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Who to sell to
Turn a founder's actual deals into an ICP they can sell against. The interview is the product: one topic at a time, evidence before opinions, a pattern named after every answer. The report is the record of what the interview found.
An ICP built from guesses describes who the founder wishes would buy. One built from paid, renewed and lost deals describes who actually buys and when. Keep pulling the conversation back to the second kind.
Choose the mode
State the mode you picked in one line, so the founder can correct it.
- Interview (default): no ICP exists, or the founder wants a fresh start.
- Fast path: the founder pastes a deals list, CRM export, invoice list or notes. Build the evidence table from it, then ask only about the gaps (usually why deals were lost and who approved the money).
- Review: the founder shares an existing ICP or positioning doc. Read it, then ask only the questions that test its weakest claims.
- Refresh: an earlier
icp-report.htmlor ICP doc exists. Ask which deals happened since, update the evidence table, and say which ICP lines changed and why.
Before the first question
- Read what is already there: the conversation, attached files, the working directory (an earlier report, a pricing page, a deals file), memory and connected tools. Never ask for something you can find.
- Check for web access. If you have web search or page fetching, research the company and every customer or prospect the founder names before asking about them: what they do, who their users are, stage and funding. Scrape only public pages. Never fetch a private page or log in on the founder's behalf.
- Without web access, say so in one line and ask for the three facts you need instead: what the company sells, to whom, and the names of its last paying customers.
- Label anything researched as "found online" and anything told as "you said". Research can be stale or wrong; the founder corrects it.
- Read references/frameworks.md once, so follow-ups draw on the right ideas.
- Open with a short briefing, then ask question 1. In one message: what you found about the company (two to four lines, so the founder can fix it), how this works (about 10 to 15 questions, one at a time, a designed report at the end, 20 to 30 minutes), and the shortcut ("paste a deals list or CRM export any time and I'll skip ahead"). If something found online contradicts what the founder says, ask before assuming either is right.
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.
- 6d ago First seen · 91 lines · 50 tokens per session scan A f7d2de031648
who-to-sell-to is a skill published in the GitHub repository tushaarmehtaa/tushar-skills (12 stars, last pushed 5d ago), licensed MIT. It adds 50 tokens to every session and 1,789 once invoked, about $0.0002 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 2026-10-14.
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…
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…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…