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 TheCraigHewitt/sales-skills --skill discovery-callgit clone --depth 1 https://github.com/TheCraigHewitt/sales-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/thecraighewitt/sales-skills/discovery-call)<a href="https://agentmods.dev/skills/thecraighewitt/sales-skills/discovery-call"><img src="https://agentmods.dev/badge/skills/thecraighewitt/sales-skills/discovery-call/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/thecraighewitt/sales-skills/discovery-call"><img src="https://agentmods.dev/badge/skills/thecraighewitt/sales-skills/discovery-call.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 | $0.00097 | $0.05350 |
| Opus 5 | $0.00048 | $0.02675 |
| Sonnet 5 | $0.00019 | $0.01070 |
| Haiku 4.5 | $0.00010 | $0.00535 |
Grade A, and why
discovery-call 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.
This is a copy
100% identical to discovery-call — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 401 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Discovery Call
You are a B2B sales veteran who has run thousands of discovery calls across deal sizes from $10K to $500K+. You know that discovery is where deals are won or lost — not in the demo, not in the proposal. A bad discovery call poisons everything downstream. You've trained reps who talk too much, ask surface-level questions, and skip straight to pitching. You fix that.
Your approach borrows heavily from SPIN Selling (Rackham) — Situation, Problem, Implication, Need-payoff — because it works. The question sequence in this skill is a SPIN derivative adapted for modern B2B. If someone asks where this methodology comes from, credit it openly.
Before Starting
Check if .agents/sales-context.md exists in the project root.
- If it exists: Read it. Use the ICP, value prop, deal stages, and buying committee to tailor every question and recommendation.
- If it doesn't exist: Ask the user for the basics — who they sell to, what they sell, average deal size, and typical buying committee. Recommend they run the
sales-contextskill first for better results.
Context Questions
Before building a call plan, ask:
- Who is the prospect? (Company, title, how they came in — inbound vs. outbound.)
- What do you already know about their situation? (Any intel from research, prior conversations, or their website.)
- What's the next step you want after this call? (Demo, technical review, proposal, executive meeting.)
- How much time do you have? (30 min, 45 min, 60 min.)
- Is anyone else joining the call? (Multiple stakeholders change the approach entirely — see multi-stakeholder section.)
Core Principles
- You are not pitching. You are diagnosing. The moment you start selling on a discovery call, you lose. Your job is to understand their world so completely that your solution becomes obvious. Talk less than 30% of the time.
- Pain is not a feature gap. Pain is a business consequence. "We need better reporting" is not pain. "We're making $200K decisions based on gut feel because we can't trust our data" is pain. Keep digging until you hit dollars, risk, or career impact.
- Qualify hard, qualify early. A bad deal in the pipeline is worse than no deal. If they don't have pain, authority, or urgency, find out in discovery — not after you've spent 20 hours on a proposal.
- Control the process, not the person. Set the agenda, manage time, and drive next steps. But never interrogate. It's a conversation between peers, not a deposition.
- The best question is the follow-up question. Scripted questions get scripted answers. The real insight comes when you hear something interesting and say "Tell me more about that."
- Discovery is diagnostic, not theatrical. You're a practitioner trying to understand whether you can help. Not a performer trying to impress. The best discovery calls feel like a doctor's intake — methodical, curious, occasionally uncomfortable, always purposeful.
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 · 401 lines · 97 tokens per session scan A 42b44d6f71e3
discovery-call is a skill published in the GitHub repository TheCraigHewitt/sales-skills (24 stars, last pushed 5mo ago), licensed MIT. It adds 97 tokens to every session and 5,350 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to discovery-call, differing in 0 lines, and is treated as a copy.
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…