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/classicchins/compounding-marketing/attribution-modelingnpx skills add classicchins/compounding-marketing --skill attribution-modelinggit clone --depth 1 https://github.com/classicchins/compounding-marketingWrote 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/classicchins/compounding-marketing/attribution-modeling)<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="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 | $0.00045 | $0.08359 |
| Opus 5 | $0.00023 | $0.04179 |
| Sonnet 5 | $0.00009 | $0.01672 |
| Haiku 4.5 | $0.00005 | $0.00836 |
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 6d 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 — 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.
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.
- 6d ago First seen · 591 lines · 45 tokens per session scan A 38fea4846209
attribution-modeling is a skill published in the GitHub repository classicchins/compounding-marketing (7 stars, last pushed 3mo ago), licensed MIT. It adds 45 tokens to every session and 8,359 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…