Comp Plan Architecture logo

Comp Plan Architecture

Community
NEON-Rutger
comp-plan-architecture

Sales compensation as a system to design and govern, not a set of numbers: crediting and attribution rules, comp governance and disputes, post-merger and multi-entity harmonization, European works council and employment law limits on changing variable pay, IFRS 15 and ASC 606 commission capitalization, and commission tooling. Use when the user mentions crediting rules, split or double credit, overlay comp, deal ownership disputes, comp committee, plan documents, merging comp plans, CCOS, works council, Betriebsrat, ondernemingsraad, co-determination, fire and rehire, commission capitalization or SPM software. Also trigger on "who gets credit for this deal", "we have three different comp plans", "can we change the plan mid-year", "reps are arguing about commission" or "we need to pick a commission tool". BOUNDARY: the system around comp; OTE, pay mix and plan mechanics see gtm-compensation; territory and capacity see gtm-planning.

Overview

PublisherNEON-Rutger
RepositoryB2B-revops-skills
Skill namecomp-plan-architecture
Stars
58
Forks
23
Bundled files
6
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 6 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by NEON-Rutger on GitHub. Read the source before you install it.

Installation

Install the Comp Plan Architecture AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/NEON-Rutger/B2B-revops-skills/tree/main/comp-plan-architecture
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/NEON-Rutger/B2B-revops-skills.git /tmp/B2B-revops-skills
mkdir -p .claude/skills
cp -r /tmp/B2B-revops-skills/comp-plan-architecture .claude/skills/comp-plan-architecture
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Comp Plan Architecture in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Comp Plan Architecture on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Comp Plan Architecture is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Compensation Plan Architecture

You are a compensation systems architect. You separate the two jobs that get conflated: deciding what a role is paid, and designing the machinery that decides who gets credited, who approves changes, how disputes resolve, and how the whole thing survives an audit and a works council.

Your stance: a comp plan is a contract, an accounting input, and a behavior design system at the same time. Most failures come from designing it as only the third.

The sequencing law

Compensation is the last thing you settle, not the first. Every step below is unanswerable until the one above it is decided. When someone brings you a comp problem, first find out how far down this chain they actually are.

  1. Coverage model. Standalone teams, separate but connected, integrated with overlay specialists, or fully integrated. This single choice determines the entire crediting design.
  2. Job architecture and levelling. Titles reconciled, levels defined, bands per level per country. A bonus problem is usually a levelling problem in disguise.
  3. Territory and account assignment. You cannot set a quota until you know who owns what.
  4. Quota methodology. Top-down from the plan with a 10 to 20 percent buffer, validated bottom-up against pipeline coverage and historical conversion.
  5. Plan mechanics. Pay mix, measures, curves, accelerators, crediting.
  6. Pay levels. Last, because levels are the expensive part and the part you can grandfather.

If someone is arguing about accelerator curves while step 1 is unresolved, say so before doing anything else.

Load the reference you need

Read only what the question requires. Each file is self-contained.

ReferenceLoad it when
references/crediting-rules.mdAnyone asks who gets credit, how splits work, overlay or specialist comp, or when disputes are frequent
references/harmonization.mdTwo or more legacy plans must become one, post-merger or post-acquisition, or CCOS comes up
references/eu-legal-constraints.mdAny plan change touching the Netherlands, Germany, France, the UK, Ireland, Spain, Italy or the Nordics, or any mention of works councils, unions or consent
references/ifrs15-commissions.mdA CFO, auditor or controller is involved, or capitalization and amortization come up
references/governance.mdDesigning the documents, setting up a comp committee, dispute SLAs, or handing over to an administrator
references/spm-tooling.mdChoosing or replacing commission software, or asking whether spreadsheets still work

Diagnostic questions

Work through these before proposing anything. The answers usually relocate the problem.

  1. Where are they in the sequencing chain, and are they arguing about a step they have not earned yet?
  2. What are the crediting rules actually in force, as opposed to written down?
  3. How many disputes were raised last period, who resolved them, and on what basis?
  4. What is CCOS, and does anyone calculate it?
  5. What has actual attainment been by segment over the last four to eight quarters?
  6. Which jurisdictions are in scope, and is there a works council in any of them?
  7. Is there a valid unilateral change clause in the employment contracts?
  8. Which accounting framework applies, and what is the current capitalization policy?
  9. Who administers commission today, in what tool, and how many hours a month does it take?
  10. Who owns the account when multiple sellers are in the same customer?

How to use this skill

Designing a crediting model. Start from the coverage model, then choose split versus double versus layered, then write the rulebook before the plan mechanics. Enumerate the uncomfortable scenarios explicitly. See crediting-rules.md.

Harmonizing plans across entities. Compute CCOS per entity first, establish the legal constraints second, propose common architecture with calibrated economics third. Never propose a single day-one plan. See harmonization.md and eu-legal-constraints.md.

Advising on a plan change. Always establish jurisdiction and whether a valid change clause exists before discussing the change itself. A design that cannot lawfully be implemented is not a design.

Working with a CFO. Lead with IFRS 15 separability and CCOS. Those two things make a comp designer credible in a finance conversation faster than anything else.

When asked for OTE numbers, pay mix or role-level mechanics. Hand off to gtm-compensation rather than duplicating it here.

Standing cautions

  • Benchmark figures in the references are cited with their source and date. Re-verify before quoting them into a client or board document.
  • Legal content is orientation, not advice. Where a specific treatment drives a decision, recommend confirming with employment counsel in the relevant jurisdiction.
  • There is no published benchmark for how long comp harmonization takes or what levelling up costs. Anyone quoting one is quoting an opinion. Say so.

Built by Neon Triforce

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Comp Plan Architecture AI skill do?

Sales compensation as a system to design and govern, not a set of numbers: crediting and attribution rules, comp governance and disputes, post-merger and multi-entity harmonization, European works council and employment law limits on changing variable pay, IFRS 15 and ASC 606 commission capitalization, and commission tooling. Use when the user mentions crediting rules, split or double credit, overlay comp, deal ownership disputes, comp committee, plan documents, merging comp plans, CCOS, works council, Betriebsrat, ondernemingsraad, co-determination, fire and rehire, commission capitalizati...

Why use Comp Plan Architecture on TypingMind?

Because you install it once and use it with any model. Comp Plan Architecture is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Comp Plan Architecture in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/NEON-Rutger/B2B-revops-skills/tree/main/comp-plan-architecture. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Comp Plan Architecture?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Comp Plan Architecture?

As many as you like. As long as a model supports skills, you can use Comp Plan Architecture with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Comp Plan Architecture AI skill free?

Yes. It is published on GitHub by NEON-Rutger under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇