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 agentmods add skills/leadmagic/gtm-skills/account-selectionnpx skills add LeadMagic/gtm-skills --skill account-selectiongit 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/account-selection)<a href="https://agentmods.dev/skills/leadmagic/gtm-skills/account-selection"><img src="https://agentmods.dev/badge/skills/leadmagic/gtm-skills/account-selection.svg" alt="Measured on agentmods" 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 | $0.00049 | $0.01680 |
| Opus 5 | $0.00024 | $0.00840 |
| Sonnet 5 | $0.00010 | $0.00336 |
| Haiku 4.5 | $0.00005 | $0.00168 |
Grade A, and why
account-selection 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 2d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Account Selection & Tiering
Overview
Account selection is the hardest part of ABM. Pick wrong and you waste 6 months. Pick right and you 3x your close rate. This skill builds a weighted scoring model to tier your TAM into Strategic, Scale, and Programmatic accounts.
Authoritative Foundations
- TOPO Account Selection — Named methodology governing recommendations in this skill's process.
- WbD ICP Framework — Named methodology governing recommendations in this skill's process.
- ITSMA — Account-Based Marketing — Tier-based ABM (1:1 / 1:few / 1:many); measure pipeline from target accounts, not lead volume.
- Lars Nilsson (Cloudera/Snowflake) — ABSD signal-based account selection — ABSD signal-based account selection
When to Use
- "Which accounts should we target?"
- "Tier our target account list"
- "Build an account scoring model"
- "Prioritize our TAM for ABM"
Step-by-Step Process
Phase 1: Build Scoring Model
Weight each dimension (must total 100 points):
Firmographic Fit (35 pts):
- Industry match (0-10): Direct ICP industry = 10, adjacent = 5, outside = 2
- Employee count (0-10): In sweet spot = 10, near = 5, outside = 2
- Revenue range (0-10): In sweet spot = 10, near = 5, outside = 2
- Geography (0-5): Target region = 5, acceptable = 3, outside = 1
Technographic Fit (25 pts):
- Current tech stack (0-15): Complementary tools present = 15, some = 8, none = 2
- Integration potential (0-10): High integration value = 10, medium = 5, low = 2
Behavioral Signals (25 pts):
- Website visits (0-10): Frequent, multi-page = 10, some = 5, none = 2
- Content engagement (0-10): Downloads, webinar attendance, newsletter = score by recency
- Social engagement (0-5): LinkedIn follows, comments, shares
Intent & Trigger (15 pts):
- Hiring signals (0-5): Role related to your product = 5
- Funding event (0-5): Recent raise = 5
- Tech change (0-5): Evidence of switching or evaluating
Phase 2: Tier Assignment
- Tier 1 (>80): 5-15 accounts. Immediate sales + marketing investment.
- Tier 2 (60-79): 15-50 accounts. Scaled ABM plays.
- Tier 3 (40-59): 50-200 accounts. Programmatic nurture.
- Below 40: Not ABM. Generic inbound/outbound only.
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.
- 2d ago Changed 79fe6cf33dc5
- 6d ago First seen · 148 lines · 49 tokens per session scan A 6accd9454297
account-selection is a skill published in the GitHub repository LeadMagic/gtm-skills (48 stars, last pushed 3d ago), licensed MIT. It adds 49 tokens to every session and 1,680 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
outreachmagic
Your agent goes blind after send. Sync sequencer webhooks, research leads via Serper, and find/verify emails — all in one local SQLite DB your agent queries directly.
cold-email
Expert cold email strategist for B2B outbound campaigns. Use when the user asks about cold email writing, email sequences, email deliverability, domain warmup, SPF/DKIM/DMARC setup, email personalization, cold email templates, email copywriting frameworks, email compliance (CAN-SPAM, GDPR), bounce management, inbox…
list-building
Expert B2B list building orchestrator for outbound sales campaigns. Use when the user asks about building lead lists, Sales Navigator search, boolean filters, ICP definition, ICP scoring, lead sources, data validation, email verification, list segmentation, Apollo prospecting, Clay Find People, list hygiene…
deduplicate
Deduplicate prospect lists, merge data from multiple sources, and ensure data quality across columns. Use when user asks about "deduplicate", "duplicates", "remove duplicates", "merge sources", "merge columns", "multiple data sources", "data quality", "clean up list", "duplicate contacts", "Clay auto-dedupe". Do NOT…
content-engagement
Content engagement signal tracking for B2B outbound. Use when the user asks about content engagement signals, LinkedIn post likes/comments, webinar attendance, newsletter engagement, Trigify setup, social engagement tracking, or community engagement signals. Do NOT use for website visitor tracking (use…
claygent
Use Clay's AI research agent (Claygent) for web research, custom data extraction, and information that does not exist in standard databases. Use when the user asks about Claygent, AI research in Clay, web browsing for data, custom data points, real-time company research, or scraping with AI. Triggers on "Claygent"…