discovery-planning

discovery-planning is a skill for Claude Code from Doris-Labs/sales-skills. It costs 85 tokens per session (1,651 once invoked), scanned A, original, MIT.

A discovery-call planning workflow that turns what you know about a buyer into a small set of testable ideas and follow-up questions.

In plain words
What is it for?
Use it before a discovery meeting to plan questions, quantify pain, identify missing stakeholders, and choose the next advance.
Why use it?
It replaces a generic checklist with a way to uncover the buyer's problems, business impact, priorities, and decision process.

Skill for Claude Code

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

Part of the sales-skills plugin — 30 skills shipped together

Good fit Use it before a discovery meeting to plan questions, quantify pain, identify missing stakeholders, and choose the next advance.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/doris-labs/sales-skills/discovery-planning
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.

Any agent
npx skills add Doris-Labs/sales-skills --skill discovery-planning
Clone the repo
git clone --depth 1 https://github.com/Doris-Labs/sales-skills

Made for: Claude Code.

Or install sales-skills, the plugin that ships this one along with the rest of its 30 skills.

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-planning

README.md
[![agentmods](https://agentmods.dev/badge/skills/doris-labs/sales-skills/discovery-planning/github.svg)](https://agentmods.dev/skills/doris-labs/sales-skills/discovery-planning)
Your own site
<a href="https://agentmods.dev/skills/doris-labs/sales-skills/discovery-planning"><img src="https://agentmods.dev/badge/skills/doris-labs/sales-skills/discovery-planning/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-planning

Your own site · 80×15
<a href="https://agentmods.dev/skills/doris-labs/sales-skills/discovery-planning"><img src="https://agentmods.dev/badge/skills/doris-labs/sales-skills/discovery-planning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,651 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 $0.00085 $0.01651
Opus 5 $0.00043 $0.00826
Sonnet 5 $0.00017 $0.00330
Haiku 4.5 $0.00009 $0.00165

Measured 11d ago against content hash cfc314c57dd3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

discovery-planning 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 11d 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.

skills/discovery-planning/SKILL.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Discovery Planning

Purpose

Walk into discovery with a plan, not a checklist. Produce a hypothesis-driven question tree, a ladder that drives every pain to quantified impact and ranked priority, the stakeholders you intend to surface, and a structured question plan you can run live.

Inputs

  • The account and who you're meeting (name, role, function)
  • What you already know (prior calls, emails, CRM, public research)
  • The goal of this call — what you're trying to learn and what advance you want next

Method

1. Build a hypothesis-driven question tree

Don't list questions — list hypotheses, then hang questions off each one. A hypothesis is your best guess at a problem this buyer likely has, given their role/segment/triggers.

Hypothesis: "Reps lose deals because no one sees risk until it's too late"
├─ Open: "Walk me through how you find out a deal is slipping today."
├─ Probe (if confirmed): "How far in advance? Who flags it?"
├─ Probe (if denied):    "So you catch slippage early — what's your tell?"
└─ Disconfirm:           "When did this last surprise you, if ever?"

Rules for a good tree:

  • 3–5 hypotheses max. More than that means you haven't prioritized.
  • Each branch has an open question to surface, probes to deepen, and a disconfirming question so you're not just fishing for confirmation.
  • Order branches by likelihood × deal impact, not by your product's feature list.

2. Run the pain → impact → priority ladder

For every pain that surfaces, climb three rungs before moving on. Don't leave a pain sitting on rung one.

Rung Question shape What you're getting
Pain "What's hard about X today?" The named problem
Impact "What does that cost you — time, money, deals, risk?" Consequence
Priority "Where does fixing this rank against everything else on your plate?" Urgency / mandate

A pain with no impact is a complaint. A pain with impact but no priority won't get budget. You need all three rungs to qualify.

Read the full file on GitHub · 141 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. 11d ago First seen · 141 lines · 85 tokens per session scan A cfc314c57dd3

Subscribe to this mod's changes

discovery-planning is a skill published in the GitHub repository Doris-Labs/sales-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 85 tokens to every session and 1,651 once invoked, about $0.0004 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 2026-08-31.