icp-scoring

icp-scoring is a skill for Claude Code from LeadMagic/gtm-skills. It costs 71 tokens per session (3,970 once invoked), scanned A, original, MIT.

A method for ranking target companies by how closely they match an ideal customer profile. It combines company details, technology, behavior, problems, timing, exclusions, and the people involved in buying.

In plain words
What is it for?
Use it to rank target-account lists, prioritize account-based marketing (ABM), define sales-routing rules, and exclude poor-fit companies.
Why use it?
It reduces wasted sales effort caused by judging accounts on only one or two factors, such as company size or industry.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code; mentions Codex; mentions Gemini CLI.

Part of the gtm-skills plugin — 196 skills shipped together

Good fit Use it to rank target-account lists, prioritize account-based marketing (ABM), define sales-routing rules, and exclude poor-fit companies.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/leadmagic/gtm-skills/icp-scoring
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 LeadMagic/gtm-skills --skill icp-scoring
Clone the repo
git clone --depth 1 https://github.com/LeadMagic/gtm-skills

Made for: Claude Code.

Or install gtm-skills, the plugin that ships this one along with the rest of its 196 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 icp-scoring

README.md
[![agentmods](https://agentmods.dev/badge/skills/leadmagic/gtm-skills/icp-scoring/github.svg)](https://agentmods.dev/skills/leadmagic/gtm-skills/icp-scoring)
Your own site
<a href="https://agentmods.dev/skills/leadmagic/gtm-skills/icp-scoring"><img src="https://agentmods.dev/badge/skills/leadmagic/gtm-skills/icp-scoring/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 icp-scoring

Your own site · 80×15
<a href="https://agentmods.dev/skills/leadmagic/gtm-skills/icp-scoring"><img src="https://agentmods.dev/badge/skills/leadmagic/gtm-skills/icp-scoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,970 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00071 $0.03970
Opus 5 $0.00036 $0.01985
Sonnet 5 $0.00014 $0.00794
Haiku 4.5 $0.00007 $0.00397

Measured 8d ago against content hash 959f82d1bfca, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

icp-scoring 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/check-output.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/foundation/icp-scoring/SKILL.md · 301 lines

How it starts

The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ICP Scoring

Overview

Most companies score leads on one or two dimensions — typically company size and industry — producing false positives that waste sales capacity and false negatives that leave revenue on the table. The non-obvious rule behind effective ICP scoring is that fit is multi-dimensional: a company can be perfect on firmographics but terrible on technographics, or vice versa. A single-axis score is noise disguised as signal.

This skill builds a weighted, four-dimensional ICP scoring model that captures firmographic fit, technographic fit, behavioral fit, and intent signals. Each dimension receives a configurable weight, and within each dimension, individual attributes are scored independently before being aggregated into a composite ICP score. The model also incorporates negative personas (attributes that disqualify regardless of other scores), buying committee mapping (who needs to be present for a deal to close), and language banks (how each persona talks about their problem).

The deliverables are an ICP Scoring Model specification (dimensions, attributes, weights, scoring rules), a Negative Persona Catalog that prevents wasted effort, and a Buying Committee Map aligned to Force Management's MEDDICC Champion identification methodology. The skill draws from Winning by Design's SPICED framework for the full customer lifecycle context and Gartner's buying committee research for decision-maker mapping.

When to Use

  • User says "score these leads" or "build an ICP scorecard" → activate this skill
  • User asks "how do I qualify accounts" or "what makes a good lead" → use this skill
  • User mentions "lead scoring model" or "account scoring" → this skill applies
  • User has a list of companies or contacts and wants to prioritize them
  • User is building Clay table enrichment workflows and needs scoring logic
  • After running gtm-context, when the ICP definition needs to become operational

Do NOT use for:

  • Scoring based on engagement alone (email opens, clicks, website visits) — that's lead scoring, not ICP scoring
  • Real-time intent signal monitoring — use signal-scoring for that
  • Simple yes/no qualification — ICP scoring produces a continuum, not a binary

Read the full file on GitHub · 301 lines

Files

What ships with it

3 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.

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 · 301 lines · 71 tokens per session scan A 959f82d1bfca

Subscribe to this mod's changes

icp-scoring is a skill published in the GitHub repository LeadMagic/gtm-skills (50 stars, last pushed 5d ago), licensed MIT. It adds 71 tokens to every session and 3,970 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 2026-09-03.

Related

Other skills, from other repositories

event-room-intelligence

Use this skill 1 to 3 days before any face-to-face event where you hold a registration export (a talk, conference, dinner, booth) and the question is 'I have the attendee CSV, who should I talk to?'. It maps every registrant to a company, joins the list against the live CRM, LinkedIn-verifies every person's title and…

swan-gtm/gtm-skills · 167 tokens

competitor-monitoring

Use this skill when you need to know what rival companies are doing — "what are my competitors doing", "competitor update", "competitor news", "competitive landscape", "market intel", "what's new with [company]", "track [company]", "competitor briefing", "who's making moves", "we keep losing deals to [company]" — or…

swan-gtm/gtm-skills · 157 tokens

multichannel-campaign-builder

Use this skill when someone needs a complete outbound sequence written — every touch across LinkedIn and email, not a single cold email. Produces three distinct angles to choose from, then the full sequence with each message ready to send, calibrated to the campaign type and channel mix and self-checked against a…

swan-gtm/gtm-skills · 139 tokens

cialdini-influence

Applies Cialdini's seven principles of ethical persuasion -- Reciprocity, Commitment and Consistency, Social Proof, Authority, Liking, Scarcity, and Unity -- to business contexts including sales, marketing, fundraising, and negotiation. Use when designing conversion funnels, optimizing sales processes, preparing…

fatihguner/foreman · 88 tokens

meeting-prep

Build a pre-meeting briefing — who's in the room, what they care about, your goal, and the questions to ask. Trigger when the user asks to prep for a meeting or call, "what should I know before", or names an upcoming meeting.

etrebels/claude-code-growth-os · 56 tokens

retention-feedback

Turn what customer success hears after the sale into product and retention actions. Trigger when an onboarding note, QBR, support thread, or usage review surfaces adoption friction, a churn-risk signal, a feature request that blocks expansion, or a customer who's ready to grow — or when the user says "log this for…

etrebels/claude-code-growth-os · 86 tokens