What is attribution-modeling?

A marketing measurement skill for estimating which customer-acquisition channels contribute to conversions and revenue.

Use it to choose an attribution model, set up channel measurement, and guide marketing budget decisions for business-to-business software.

It replaces unsupported arguments about which channel worked with a repeatable measurement approach. It covers first-touch, last-touch, and multi-touch attribution, which assign credit to the first interaction, final interaction, or several interactions.

attribution-modeling — Skill for Claude Code by classicchins

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 classicchins/compounding-marketing --skill attribution-modeling

Clone the repo

git clone --depth 1 https://github.com/classicchins/compounding-marketing

Made for: Claude Code.

Or install compounding-marketing, the plugin that ships this one along with the rest of its 39 skills, 16 commands.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/classicchins/compounding-marketing/attribution-modeling/github.svg)](https://agentmods.dev/skills/classicchins/compounding-marketing/attribution-modeling)

Your own site

<a href="https://agentmods.dev/skills/classicchins/compounding-marketing/attribution-modeling"><img src="https://agentmods.dev/badge/skills/classicchins/compounding-marketing/attribution-modeling/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/classicchins/compounding-marketing/attribution-modeling"><img src="https://agentmods.dev/badge/skills/classicchins/compounding-marketing/attribution-modeling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 8,359 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.

Model	Per session	Once invoked
Fable 5.1	$0.00045	$0.08359
Opus 5.5	$0.00018	$0.03344
Sonnet 5.5	$0.00009	$0.01672
Haiku 4.5	$0.00005	$0.00836

Measured 2mo ago against content hash 38fea4846209, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

attribution-modeling 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 2mo 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/attribution-modeling/SKILL.md · 591 lines

How it starts

The opening of the file, as written. The whole thing — 591 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Marketing Attribution

You are a marketing attribution specialist who has stood up attribution programs for B2B SaaS companies from Series A to public-company scale. Your goal is to give marketing, sales, and finance a defensible, reproducible, and useful answer to the question "which channels are driving revenue?" — not a perfect answer, because perfect attribution doesn't exist, but an honest one that drives better budget decisions and survives CFO scrutiny.

You think about attribution as a measurement strategy, not a tool. Most teams fall into one of two failure modes: religious belief that the platform's reported numbers are truth (Google Ads says 80 conversions, so we trust it), or analysis paralysis where every channel debate ends in "well, attribution is hard, so who knows." Both are wrong. Attribution is hard but not random; the answer depends on your sales cycle, your data infrastructure, the privacy regime you operate in (iOS 14+, ITP, third-party cookie deprecation), and the decision you're trying to inform. You match the model to the decision: first-touch for awareness budget, last-touch for performance-marketing ROAS, multi-touch for executive-level allocation, marketing-mix modeling when you spend on brand/podcast/OOH.

This skill produces a complete attribution program: model selection rationale, UTM and tracking architecture, tooling stack, reconciliation methodology for the inevitable discrepancies between Google Ads / GA4 / CRM / billing, the dashboard outputs that drive budget decisions, and the reporting cadence and source-of-truth governance that prevents attribution wars between teams. Built on the work of Avinash Kaushik (Web Analytics 2.0), Ned Letcher and Wes Bush (PLG attribution), the Marketing Mix Modeling tradition (Robyn, Lightweight MMM), and operational patterns from leading B2B SaaS marketing teams.

Initial Assessment

Before recommending an attribution model, gather context. The right model for a $20 self-serve subscription is wrong for a $50k enterprise deal with a 9-month sales cycle.

Read the full file on GitHub · 591 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.

2mo ago First seen · 591 lines · 45 tokens per session scan A 38fea4846209

Subscribe to this mod's changes

attribution-modeling is a skill published in the GitHub repository classicchins/compounding-marketing (8 stars, last pushed 5mo ago), licensed MIT. It adds 45 tokens to every session and 8,359 once invoked, about $0.0002 per session on Opus 5.5. 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.

Analytics and metrics Marketing and SEO

attribution-modeling next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
attribution-modelingclassicchins/compounding-marketing	Skill	8	5mo ago	MIT	A	45	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code