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 skills add indranilbanerjee/neels-plugins --skill attribution-reportgit clone --depth 1 https://github.com/indranilbanerjee/neels-pluginsWrote 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/indranilbanerjee/neels-plugins/attribution-report)<a href="https://agentmods.dev/skills/indranilbanerjee/neels-plugins/attribution-report"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/neels-plugins/attribution-report/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.
<a href="https://agentmods.dev/skills/indranilbanerjee/neels-plugins/attribution-report"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/neels-plugins/attribution-report.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00021 | $0.02342 |
| Opus 5.5 | $0.00008 | $0.00937 |
| Sonnet 5.5 | $0.00004 | $0.00468 |
| Haiku 4.5 | $0.00002 | $0.00234 |
Grade A, and why
attribution-report 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.
This is a copy
94% identical to attribution-report — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/digital-marketing-pro:attribution-report
GA4 AI Assistant channel (added 13 May 2026)
When generating attribution reports against a GA4 property, the AI Assistant default channel group is now a first-class channel. GA4 automatically categorizes sessions referred by ChatGPT, Gemini, Claude, and other recognized AI assistants under this channel (and sets Medium=ai-assistant). For any brand running an AEO program, include the AI Assistant channel in the channel set and compare its contribution across all attribution models (first-touch, last-touch, linear, time-decay, position-based, data-driven).
The model-comparison view is especially informative here: AI Assistant traffic often shows wildly different credit under first-touch vs last-touch because users frequently discover a brand via an AI assistant but convert via a later branded search or direct visit. Don't conclude "AI search doesn't drive revenue" from a last-touch number alone.
Source: GA4 default channel groups. For the upstream impression-side data, pair with /digital-marketing-pro:gsc-ai-performance (GSC AI Performance Report rolled out 3 June 2026, deliberately no click data — so GA4 is your click attribution surface).
Purpose
Generate multi-touch attribution analysis showing how different marketing channels and campaigns contribute to conversions. Compare multiple attribution models side-by-side, allocate revenue across touchpoints, and provide actionable budget reallocation recommendations based on true channel contribution. This command moves beyond simplistic last-click attribution to reveal the full customer journey — identifying which channels drive awareness, which nurture consideration, and which close conversions — so marketing budgets can be allocated based on actual contribution rather than positional bias.
Input Required
The user must provide (or will be prompted for):
- Attribution models to compare: Two or more models to run side-by-side —
first-touch(100% credit to the first interaction that initiated the journey),last-touch(100% credit to the final interaction before conversion),linear(equal credit distributed across all touchpoints),time-decay(exponentially more credit to touchpoints closer to conversion, with configurable half-life — default 7 days),position-based(40% to first touch, 40% to last touch, 20% distributed across middle interactions), ordata-driven(algorithmic allocation based on conversion path patterns and counterfactual analysis). At least two models should be compared to reveal attribution bias - Conversion events to attribute: The conversion actions to analyze —
purchases(completed transactions with revenue),signups(account or trial creation),leads(form submissions, demo requests, contact inquiries), orcustom events(user-defined conversion points with optional revenue values). Multiple conversion events can be analyzed simultaneously with separate attribution for each - Time period: The analysis window — specific date range, relative period (last 30 days, last quarter), or year-over-year comparison. Longer periods provide more conversion paths for reliable model comparison but may include seasonal distortions
- Conversion window: The lookback window for attributing touchpoints to a conversion —
7 days(short-cycle purchases, impulse buys),14 days(standard eCommerce),30 days(B2B lead gen, considered purchases), or90 days(enterprise B2B, high-value purchases with long sales cycles). Touchpoints outside the conversion window are excluded from attribution - Channels to include: Which marketing channels to attribute across — paid search, paid social, organic search, direct, email, referral, display, video, affiliate, or specific campaign groups. All channels are included by default unless the user restricts scope
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 First seen · 58 lines · 21 tokens per session scan A 602ccd803206
attribution-report is a skill published in the GitHub repository indranilbanerjee/neels-plugins (6 stars, last pushed 2d ago), licensed MIT. It adds 21 tokens to every session and 2,342 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to attribution-report, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
continuous-improvement-loop
Run the Part 12 continuous improvement loop into a quarterly brief for leadership. "produce the quarterly improvement brief".
yearly-planner
Produce the Part 8 yearly planner: quarterly themes and monthly initiatives. "plan the whole year month by month".
attribution-report
Run attribution on real conversion paths, comparing models. "which channels actually drive revenue".
validate-output
Validate content structure against a schema: sections, word counts. "scan for leftover placeholders".
add-integration
Add a custom MCP integration: scaffold the server, write .mcp.json, test it. "add a new MCP server".
client-proposal
Draft a client proposal or RFP response: scope, deliverables, KPIs, pricing tiers. "respond to this RFP".