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/attributionnpx skills add LeadMagic/gtm-skills --skill attributiongit 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/attribution)<a href="https://agentmods.dev/skills/leadmagic/gtm-skills/attribution"><img src="https://agentmods.dev/badge/skills/leadmagic/gtm-skills/attribution.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 | $0.00064 | $0.05704 |
| Opus 5 | $0.00032 | $0.02852 |
| Sonnet 5 | $0.00013 | $0.01141 |
| Haiku 4.5 | $0.00006 | $0.00570 |
Grade A, and why
attribution 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 today.
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 — 372 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Attribution
Overview
Attribution answers the existential marketing question: which of our activities actually produce revenue? The core principle is that single-touch attribution lies. First-touch attribution over-credits awareness channels. Last-touch attribution over-credits bottom-of-funnel conversion channels. Both lead to systematically bad investment decisions — over-funding channels that appear in the credited position and starving channels that create the conditions for conversion.
The non-obvious rule: the "best" attribution model depends on your GTM motion. Product-led growth companies should weight product-qualified signals higher. Sales-led companies should weight sales engagement higher. Channel-led companies should weight partner influence. There is no universal attribution model — only the model that matches how your customers actually buy.
This skill produces: a Multi-Touch Attribution Model Report comparing 4-6 attribution models on revenue credit allocation, channel ROI calculations with cost and revenue attribution, a UTM governance framework with taxonomy and enforcement rules, a source-of-truth reporting structure, and optimization recommendations for budget reallocation.
When to Use
- User says "attribution" or "attribution model" → activate this skill
- User asks "which channel generates the most revenue" → use this skill
- User says "marketing ROI" or "campaign ROI" → attribution is required
- User mentions "UTM tracking" or "UTM hygiene" or "UTM parameters" → use UTM governance module
- User asks "how do I measure multi-touch attribution" → implement a model
- User says "source of truth reporting" or "marketing and sales disagree on numbers" → use this skill
- Trigger phrases: attribution modeling, multi-touch, first-touch, last-touch, channel attribution, campaign ROI, marketing ROI, UTM parameters, tracking governance
Do NOT use for:
- Campaign-level analytics (open rates, reply rates, meeting rates) → use campaign-analytics
- Pipeline management and forecasting → use pipeline-management
- A/B testing methodology → use a-b-testing
- CRM data architecture → use crm-integration
- Real-time channel monitoring and alerting → use proactive-alerts
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.
- today Changed 7160138430b8
- 4d ago First seen · 372 lines · 64 tokens per session scan A 4f0a3d5929e5
attribution is a skill published in the GitHub repository LeadMagic/gtm-skills (46 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 5,704 once invoked, about $0.0003 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…
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"…
conditional-logic
Write Clayscript formulas, conditional runs, and credit-saving logic in Clay. Use when the user asks about Clayscript, Clay formulas, conditional runs, saving credits with logic, data manipulation, if/then logic, JavaScript formulas in Clay, or the AI formula generator. Triggers on "Clayscript", "formula"…
scoring
Build lead scoring systems in Clay using formulas and enrichment data. Use when the user asks about lead scoring, ICP fit scoring, segmentation, lead qualification, tier assignment, prioritizing leads, or building a 100-point scoring model. Triggers on "lead scoring", "scoring system", "ICP fit", "segmentation", "lead…