attribution-reconciler

attribution-reconciler is a skill for Claude Code from aaron-he-zhu/aaron-marketing-skills. It costs 150 tokens per session (2,726 once invoked), scanned A, original, Apache-2.0.

A recurring workbook that compares advertising-platform conversions with the order IDs recorded in Google Analytics 4 or an ecommerce system.

In plain words
What is it for?
Use it to reconcile Meta and Google conversion exports, remove duplicate sales, compare attribution, and estimate the incremental contribution of paid channels.
Why use it?
It finds duplicate credit, standardizes attribution windows and currencies, and keeps paid-conversion reporting tied to actual orders rather than platform totals.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions Claude Code; built for openclaw.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is Based on the ROAS dimension **R** (attribution integrity) in the [ROAS Benchmark](../../../references/roas-benchmark.md). This is the **standing de-dup / increm.

Part of the aaron-marketing plugin — 120 skills shipped together , and of aaron-marketing

Good fit Use it to reconcile Meta and Google conversion exports, remove duplicate sales, compare attribution, and estimate the incremental contribution of paid channels.

Compare 6 skills from other repositories ↓
About the project

aaron-marketing-skills is a collection of 120 AI-agent skills covering marketing work such as brand narrative, search optimization, social media, email, advertising, influencer campaigns, and launches. Marketers and agent users can install it as a plugin, use its portable skills, or run its described bot team. The catalogue entries are components of this marketing workflow.

aaron-he-zhu/aaron-marketing-skills · 2,767 stars · on GitHub · aaronmarketing.ai

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/aaron-he-zhu/aaron-marketing-skills
agentmods
npx agentmods add skills/aaron-he-zhu/aaron-marketing-skills/attribution-reconciler

Made for: Claude Code.

Or install aaron-marketing, the plugin that ships this one along with the rest of its 120 skills.

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.

agentmods badge for attribution-reconciler

README.md
[![agentmods](https://agentmods.dev/badge/skills/aaron-he-zhu/aaron-marketing-skills/attribution-reconciler/github.svg)](https://agentmods.dev/skills/aaron-he-zhu/aaron-marketing-skills/attribution-reconciler)
Your own site
<a href="https://agentmods.dev/skills/aaron-he-zhu/aaron-marketing-skills/attribution-reconciler"><img src="https://agentmods.dev/badge/skills/aaron-he-zhu/aaron-marketing-skills/attribution-reconciler/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.

agentmods 80×15 button for attribution-reconciler

Your own site · 80×15
<a href="https://agentmods.dev/skills/aaron-he-zhu/aaron-marketing-skills/attribution-reconciler"><img src="https://agentmods.dev/badge/skills/aaron-he-zhu/aaron-marketing-skills/attribution-reconciler.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 150 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,726 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. Third-party audits
  • Socket pass 2 Sept 2026
  • Snyk pass 2 Sept 2026
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 84
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00150 $0.02726
Opus 5 $0.00075 $0.01363
Sonnet 5 $0.00030 $0.00545
Haiku 4.5 $0.00015 $0.00273

Measured 10d ago against content hash cdf1ff00ec40, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

attribution-reconciler 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 10d 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.

ad/scale/attribution-reconciler/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Attribution Reconciler

Based on the ROAS dimension R (attribution integrity) in the ROAS Benchmark. This is the standing de-dup / incrementality workbook: it reconciles platform-reported conversions against the GA4/ecommerce order-ID truth set on a recurring cadence. It delegates all ratio/ROAS math to roi-calculator and does not re-run the R2 veto — ad-account-auditor judges R2 once, point-in-time. This workbook just keeps the truth set clean between audits. Upstream, conversion-signal-qa is the pre-launch instrumentation pass that makes the signal trustworthy and only gates that a dedup rule exists; this skill is the recurring reconciliation that runs on that signal — match, de-dup, quantify, read incrementality.

The single rule: the truth set is the order IDs from GA4/ecommerce, never any platform's reported-conversion count. This workbook reconciles paid channels only — decomposing GA4 direct traffic and estimating organic dark-social share attribution belongs to dark-social-attributor.

Quick Start

Reconcile my paid conversions for May. Truth set is this GA4 order-ID export. Here are the Meta and Google conversion exports. Find the double-counting.
Build the monthly attribution workbook: normalize Meta's 7-day-click window and Google's 30-day window to a common window, convert currencies, then show de-duped conversions per platform against my Shopify order export.
I ran a geo holdout for two weeks. Here's the test-region and control-region order export plus the platform spend. Read the incrementality and compare it to last-click.

Skill Contract

  • Expected output: a reconciliation workbook that maps every platform-reported conversion to (or away from) an order in the truth set, a de-duped conversion count per platform, a normalized-window/currency view, an attribution-model comparison table, and an incrementality read if a holdout exists.
  • Reads: the GA4/ecommerce order-ID export (truth set), each platform's conversion export (reported conversions with claimed order IDs/timestamps/windows), the stated attribution window per platform, currency per export, and any geo/holdout test export (test vs control orders + spend). The ROAS profile (direct-response|prospecting|incremental-profit) is context only.
  • Writes: a reconciliation workbook at memory/ad/attribution-reconciler/YYYY-MM-DD-<topic>.md — match table, de-duped counts, normalized view, model-comparison table, incrementality read, and a handoff summary.
  • Promotes: the de-duped conversion count, the double-count rate, and the incrementality result (if any) to memory/hot-cache.md. Unresolved gaps (orders with no platform claim, or platform claims with no matching order) to memory/open-loops.md.
  • Done when: every platform conversion is reconciled to the order-ID truth set (matched / double-counted / unmatched), windows and currency are normalized to a common basis, at least one attribution-model comparison is shown, incrementality is read where a holdout exists (or marked N/A), and the ratio/ROAS math is handed to roi-calculator rather than computed here.
  • Primary next skill: roi-calculator.

Read the full file on GitHub · 101 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.

  1. 10d ago Changed · +3 lines cdf1ff00ec40
  2. 13d ago First seen · 98 lines · 150 tokens per session scan A ccae120ee4f6

Subscribe to this mod's changes

attribution-reconciler is a skill published in the GitHub repository aaron-he-zhu/aaron-marketing-skills (2,767 stars, last pushed today), licensed Apache-2.0. It adds 150 tokens to every session and 2,726 once invoked, about $0.0007 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.