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 LeadMagic/gtm-skills --skill icp-scoringgit clone --depth 1 https://github.com/LeadMagic/gtm-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/leadmagic/gtm-skills/icp-scoring)<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.
<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>- NVIDIA SkillSpector pass
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 | $0.00071 | $0.03970 |
| Opus 5 | $0.00036 | $0.01985 |
| Sonnet 5 | $0.00014 | $0.00794 |
| Haiku 4.5 | $0.00007 | $0.00397 |
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.
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 — 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
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.
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.
- 8d ago First seen · 301 lines · 71 tokens per session scan A 959f82d1bfca
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.
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…
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…
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…
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…
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.
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…