Discovery Coach

Discovery Coach is an agent for Claude Code from shalintripathi/saas-marketing-agents. It costs 16 tokens per session (6,365 once invoked), scanned A, original, MIT.

A sales discovery coaching assistant for improving the conversations where sellers learn about a buyer's problems. It uses structured questions, listening, and qualification methods.

In plain words
What is it for?
It helps create discovery playbooks, question frameworks, qualification criteria, role-based conversation guides, and role-play coaching exercises.
Why use it?
It helps salespeople uncover real needs, measure their impact, recognise buying signals, and avoid spending time on weak opportunities.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the saas-marketing plugin — 19 skills, 79 agents shipped together

Good fit It helps create discovery playbooks, question frameworks, qualification criteria, role-based conversation guides, and role-play coaching exercises.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/shalintripathi/saas-marketing-agents/sales-discovery-coach
Install

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.

Clone the repo
git clone --depth 1 https://github.com/shalintripathi/saas-marketing-agents

Made for: Claude Code.

Or install saas-marketing, the plugin that ships this one along with the rest of its 19 skills, 79 agents.

Wrote 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.

agentmods badge for Discovery Coach

README.md
[![agentmods](https://agentmods.dev/badge/agents/shalintripathi/saas-marketing-agents/sales-discovery-coach/github.svg)](https://agentmods.dev/agents/shalintripathi/saas-marketing-agents/sales-discovery-coach)
Your own site
<a href="https://agentmods.dev/agents/shalintripathi/saas-marketing-agents/sales-discovery-coach"><img src="https://agentmods.dev/badge/agents/shalintripathi/saas-marketing-agents/sales-discovery-coach/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.

agentmods 80×15 button for Discovery Coach

Your own site · 80×15
<a href="https://agentmods.dev/agents/shalintripathi/saas-marketing-agents/sales-discovery-coach"><img src="https://agentmods.dev/badge/agents/shalintripathi/saas-marketing-agents/sales-discovery-coach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,365 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00016 $0.06365
Opus 5 $0.00008 $0.03182
Sonnet 5 $0.00003 $0.01273
Haiku 4.5 $0.00002 $0.00636

Measured 8d ago against content hash aa7331bc5e72, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

Discovery Coach 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 8d 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.

plugins/saas-marketing/skills/sales-enablement/agents/sales-discovery-coach.md · 320 lines

How it starts

The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Discovery Coach

Identity

You are a B2B SaaS discovery methodology specialist obsessed with the art of asking better questions. You've trained hundreds of sales reps that the best sellers aren't talkers—they're listeners. You understand SPIN selling, gap selling, and diagnostic selling frameworks. You know that buyers are more persuaded by their own conclusions than by your statements. Your job is teaching reps how to uncover real pain, quantify its impact, and position your solution as the obvious answer through structured discovery conversations. You believe the sale is won or lost in discovery—everything after is just order-taking.

Core Mission

  • Develop discovery methodologies and conversation frameworks that uncover buyer pain, quantify impact, and identify solution gaps
  • Train sales teams on question architecture, active listening, and buying signal recognition
  • Create discovery playbooks by buyer role and use case that guide reps toward relevant opportunities and qualification decisions
  • Build discovery qualification criteria that differentiate real opportunities from time-wasting conversations
  • Establish discovery coaching programs and role-play exercises that improve rep discovery execution and conversation skills

Critical Rules

  1. Questions Over Statements: The best discovery doesn't tell—it asks. Every statement should be 5+ questions. Buyer should talk 60-70% of the call, rep talks 30-40%. If rep is talking more, discovery is failing.

  2. Problem Recognition Before Solutions: Never position product features until you've uncovered real pain. Buyer needs to acknowledge the problem first, quantify its impact, and feel dissatisfaction with status quo before you can position solution.

  3. Diagnosis Before Prescription: Understand their situation completely before mentioning your product. You're a consultant first, seller second. Diagnosis-first approach builds trust and positions you as expert, not order-taker.

  4. Quantification is Qualification: A buyer saying "this is painful" is soft. A buyer saying "we lose $500K annually because of this problem" is qualified. Your job is translating "I don't like this" into "this costs me X."

Read the full file on GitHub · 320 lines

Changes

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.

  1. 8d ago First seen · 320 lines · 16 tokens per session scan A aa7331bc5e72

Subscribe to this mod's changes

Discovery Coach is an agent published in the GitHub repository shalintripathi/saas-marketing-agents (12 stars, last pushed today), licensed MIT. It adds 16 tokens to every session and 6,365 once invoked, about $0.0001 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 2026-09-04.

Related

Other agents, from other repositories

Speedwagon

Use this agent when authoring interactive explainer modules from a curriculum plan — transforms Riko's scope + Senku's teaching arc into a module brief and an HTML fragment for the /explain course. NEVER use for exploration, planning, or general code changes.

josix/agent-flow · 56 tokens

growth-finder

Sub-agent that runs in parallel during a full audit (or standalone) to identify growth opportunities by comparing target site against competitors via backlink/keyword data and surfacing actionable next steps.

metawhisp/amazing-seo-skill · 40 tokens

sensei

CodeSensei by Dojo Coding — AI mentor that teaches programming concepts during vibecoding sessions. Invoked automatically after code changes to explain what happened, why decisions were made, and test comprehension with micro-quizzes. Adapts to the user's belt level and background. Use this agent when the user asks to…

DojoCodingLabs/code-sensei · 77 tokens

mentor-courses

Use this agent when the user needs help with educational content, course creation, learning paths, study plans, didactic material, or anything related to the learning platform. Also use when the user wants to understand a complex topic broken down into actionable steps, or when organizing knowledge for teaching…

evolution-foundation/evo-nexus · 221 tokens

docs-lookup

When the user asks how to use a library, framework, or API or needs up-to-date code examples, use Context7 MCP to fetch current documentation and return answers with examples. Invoke for docs/API/setup questions.

raja21068/AutoResearch · 47 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens