Um Claude Skill que redige um plano de remuneração de vendas — métrica, pay mix, cota, curva de aceleradores, SPIFs, trigger de clawback, política de disputas — e depois precifica esse plano reproduzindo a distribuição real de atingimento do ano passado através da nova curva. Ele reporta quanto o plano custa em três níveis de desempenho da empresa, quanto o rep mediano de fato ganha frente ao OTE com que foi recrutado, e quais condições de clawback o rascunho não cumpre. Termina em draft ou blocked. Não existe veredicto que signifique aprovado.
O bundle fica em apps/web/public/artifacts/comp-plan-drafter-skill/ e contém SKILL.md mais três templates de referência: references/1-plan-inputs-template.md (cargo, segmento, OTE, cota, curva, estados onde os reps trabalham, orçamento), references/2-attainment-history-template.md (uma linha por rep-ano, incluindo quem saiu) e references/3-sample-output-format.md (o Markdown exato que o Skill emite, com um exemplo trabalhado).
Quando usar
De seis a dez semanas antes de o ano do plano abrir, sobre um plano cujo único modelo de custo é uma planilha que assume que todo mundo cai em 100% da cota. Essa suposição é a razão de isto existir. A pesquisa de AEs 2026 do Bridge Group, com 158 empresas B2B, coloca 48% dos reps em cota, com AEs de enterprise em 38% e uma razão mediana cota-para-OTE que subiu para 4,6x. Um plano custeado no atingimento cheio não é conservador nem agressivo: ele está precificado contra uma população que não existe, e o erro aparece como estouro de orçamento ou, muito mais frequentemente, como um time ganhando silenciosamente bem menos do que o OTE da carta-proposta.
Também vale: uma emenda de meio de ano para um segmento, um cargo novo sem plano precedente, e um post-mortem contra o plano que está em mercado hoje quando a remuneração variável fechou longe do forecast e ninguém consegue dizer se a causa foi a curva ou a cota.
A parte que se paga é o passo 3. Qualquer ferramenta de comp desenha uma curva; quase nenhuma reproduz o seu próprio histórico no nível do rep através da curva que você está prestes a lançar. Essa retroprojeção é o que transforma “os aceleradores parecem razoáveis” em “isto custa 2,41M no desempenho do ano passado e 2,98M se o time melhorar dez pontos”.
Quando NÃO usar
Aprovar ou emitir um plano. Um plano de comp é um contrato. Na Califórnia, o Labor Code § 2751 exige que ele seja escrito, assinado pelo empregador, com um aceite de recebimento assinado pelo empregado, e precisa declarar o método de cálculo das comissões incluindo a política de chargebacks. Todo draft que o Skill emite carrega requires_counsel_review: true no cabeçalho e nenhum caminho remove isso.
Calcular ou pagar comissões. Isto redige e precifica o plano. Cálculo de pagamento, tratamento de disputas e folha pertencem a uma plataforma de ICM. O Skill não escreve em nada.
Definir a cota de um rep específico. Ele modela uma cota para um cargo e um segmento. Atribuir um número a uma pessoa com nome é uma questão de cobertura e capacidade: faça primeiro o recorte de territórios e depois precifique o plano contra ele.
Faixas salariais de recrutamento. Fazer benchmark de base e equity para um cargo contra dados de Radford ou Pave é outro trabalho, com outras fontes e outro aprovador.
Carteiras com menos de uma dúzia de rep-anos totalmente rampados. Treze linhas são uma distribuição sobre a qual dá para discutir. Seis são uma anedota com uma função de percentil aplicada em cima, e o Skill devolve blocked em vez de um número de custo que não consegue sustentar.
Setup
Preencha os inputs do plano. Em references/1-plan-inputs-template.md, defina cargo, segmento, headcount, OTE alvo, pay mix, cota proposta e budget_ceiling. Deixe qualquer campo de curva como propose e o Skill redige aquela peça; fixe os que já estão decididos. Defina market_ote_reference a partir de uma pesquisa que você realmente tenha e cite a fonte em market_ote_source — o alerta de retenção do output vale exatamente o que esse número valer.
Exporte o histórico de atingimento com quem saiu incluído. Em references/2-attainment-history-template.md, uma linha por rep-ano do ano anterior: cota proporcional, atingimento contra essa cota proporcional, meses rampados, data de desligamento. include_terminated: true é obrigatório e o Skill devolve blocked quando é falso.
Decida o cap deliberadamente. O template vem sem cap. Um cap protege o orçamento contra um deal fora da curva e produz de forma confiável o sandbagging que ele foi escrito para evitar. Olhe o caso alto da tabela de custos antes de escolher, em vez de herdar o default do template.
Rode dry_run: true primeiro. Ele devolve a distribuição observada, a contagem de rampados completos e cada linha que precisou excluir com o motivo. A maioria dos exports de histórico traz duas ou três linhas com cota zero ou atingimento de 400% vindo de um único deal, e você quer vê-las antes que estejam dentro de um número de custo.
Instale e limite as credenciais. Coloque o bundle em ~/.claude/skills/comp-plan-drafter/ e defina SFDC_TOKEN com leitura em Opportunity, User e Quota se você for puxar o histórico do Salesforce em vez de um CSV. Somente leitura é o escopo correto, não uma precaução.
O que o skill realmente faz
Duas passadas, e a divisão é deliberada. A primeira redige o plano — esse é o trabalho de julgamento e cabe ao modelo. A segunda retroprojeta o rascunho contra a distribuição observada, e essa aritmética roda em código. Uma função de pagamento por faixas aplicada a quarenta linhas de reps não se reproduz de rodada em rodada quando um modelo faz isso em contexto, e uma conversa de remuneração desaba no momento em que duas rodadas do mesmo rascunho devolvem dois custos de plano.
O relatório de custo entrega três números em vez de um: a distribuição observada, mais e menos a banda de sensibilidade. Um plano de comp é um instrumento alavancado e o valor útil é a inclinação. Um plano cujo custo se move 8% ao longo de um swing de vinte pontos de atingimento não está direcionando ninguém; um que se move 60% é uma exposição orçamentária que alguém deveria aceitar de propósito.
Os ganhos são reportados por decil, nunca como média. No exemplo trabalhado em references/3-sample-output-format.md, o plano fica 21% abaixo de um orçamento aprovado enquanto o rep mediano ganha 154.900 contra um OTE de 200.000 — uma combinação que uma revisão só de orçamento aprova sem comentar. O Skill também recusa a solução fácil: com 61% de atingimento mediano, nenhuma razão cota-para-OTE defensável paga o alvo ao rep mediano, então ele nomeia a decisão real (corrigir cobertura, território ou ramp — ou dizer a parte incômoda na contratação) em vez de propor um ajuste de taxa que não fecha a lacuna.
A checagem de política emite um checklist, não uma conclusão. Três condições decidem se um clawback sobrevive a uma contestação na maioria dos estados: o trigger está definido no documento do plano antes de a comissão ser paga, o evento de competência está atrelado a algo genuinamente reversível, e a recuperação não pode empurrar o rep abaixo do salário mínimo aplicável em nenhum período de pagamento. O erro de redação mais comum é o segundo — competência no booking enquanto se recupera por churn em doze meses — e o Skill nomeia o descasamento em vez de reportar um pass genérico.
A realidade do custo
Como a aritmética no nível do rep acontece em código, o custo em tokens escala com o tamanho do resumo e do documento do plano, não com o headcount. Um plano de 40 reps roda por volta de 1 a 3 USD por ciclo de redação e stress-test no Claude Sonnet 5, ao preço publicado de API de 3 USD por milhão de tokens de entrada e 15 USD por milhão de tokens de saída. Esse número é uma estimativa derivada do preço por token e do tamanho típico do documento; ele se move com quanta narrativa você pede, não com o tamanho do time. Um ciclo de desenho leva de seis a doze rodadas conforme a curva é revisada, então reserve algo perto de 20 USD para a temporada.
A comparação que importa não é o gasto com ferramenta, é o calendário. Um analista de RevOps montando as mesmas três visões na mão — reproduzir cada rep-ano através de uma curva candidata, refazer isso a cada revisão e montar o checklist de estados — gasta de dois a quatro dias por iteração, e é por isso que a maioria dos times modela uma curva e depois negocia a partir dela. Cada rodada aqui são minutos mais uma hora lendo o output, que é o que faz oito revisões caberem na janela em vez de uma.
vs alternativas
QuotaPath — publica números reais, o que é raro nesta categoria: Growth com taxa de plataforma de 800 USD mensais incluindo os primeiros cinco usuários mais 50 USD por usuário/mês no tier Premium, cobrado anualmente, com modelagem de planos, aprovações multinível e acesso à API (página de preços do fornecedor, verificada em 2026-08-11). Uma operação de 40 reps roda em torno de 30.600 USD por ano no Premium. Escolha quando quiser que o plano viva no sistema que também calcula os pagamentos e roteia as aprovações. Ele modela cenários bem; não te diz que o rep mediano vai ganhar 77% do OTE.
CaptivateIQ — nada publicado, por assento sobre payees em vez de admins, com a Vendr reportando contrato anual mediano de 36.120 USD sobre 305 compras analisadas. O Compensation Builder Agent entrou em beta limitado em maio de 2026 e redige fórmulas a partir dos seus planos existentes, que é exatamente o problema: um time com quatro aceleradores sobrepostos ganha ajuda para construir o quinto. Escolha CaptivateIQ quando o escopo for gestão de remuneração de incentivos e a estrutura do plano já estiver resolvida.
Um consultor de remuneração — o incumbente honesto para o desenho do plano, e melhor que isto no trabalho político de fazer um plano ser aceito. Eles produzem um bom plano por ano e em geral não o retroprojetam contra o seu histórico no nível do rep, a menos que você entregue os dados e pague pela análise.
O plano do ano passado com os números trocados — a linha de base real na maioria das empresas, e a razão pela qual esquemas de aceleradores derivam por anos sem ninguém precificar essa deriva. Não custa nada e é assim que um quarto componente acaba num plano que ninguém explica em duas frases.
Pontos de atenção
Um histórico de atingimento que exclui quem saiu. A rotatividade não é aleatória em relação ao atingimento: quem atinge pouco sai, desproporcionalmente. Um arquivo só de sobreviventes subestima o custo do plano e superestima a saúde da distribuição ao mesmo tempo. Guarda: include_terminated é obrigatório, o Skill devolve blocked quando é falso, e reps desligados entram com cota proporcional e atingimento parcial do ano.
Uma distribuição produzida sob outra cota. O atingimento do ano passado reflete a cota e os territórios do ano passado. Guarda: o Skill registra prior_plan_quota_median e avisa quando a cota redigida se move mais que quota_shift_tolerance_pct, rotulando o modelo de custo como direcional em vez de apresentá-lo como forecast.
Um plano que passa na checagem de orçamento e perde gente. O relatório de custo é um instrumento de finanças e vai aprovar com prazer um plano com o qual o rep mediano não consegue viver. Guarda: a tabela de decis fica ao lado da tabela de custos, então o custo de retenção e o custo orçamentário ficam na mesma página e são lidos na mesma reunião.
Um SPIF permanente. Um SPIF sem data de fim não é um SPIF, é um aumento de taxa não documentado que ninguém reaprova. Guarda: a linha de SPIF exige uma expiração explícita no arquivo de inputs e o Skill se recusa a redigir o componente sem ela.
Tratar blocked como julgamento sobre o desenho. Ele diz que os números não são confiáveis, não que o plano está errado. Guarda: todo retorno blocked nomeia o defeito de dado específico e o que o resolveria, então a resposta é corrigir o export, não redesenhar.
Stack
Claude — redação do plano, desenho da curva, narrativa das lacunas de política; a aritmética da retroprojeção roda em código, não em contexto
Salesforce — histórico de closed-won, registros de cota e roster, quando o arquivo de atingimento é puxado em vez de exportado na mão
Os arquivos de inputs do plano e de histórico de atingimento — os dois inputs que fazem o output ser específico da sua organização e não um template
Uma plataforma de ICM — CaptivateIQ, QuotaPath, ou o que quer que calcule os pagamentos depois que o plano redigido for aprovado e assinado
Desenho de planos de remuneração de vendas — o framework por trás das escolhas de métrica, curva e piso contra as quais este Skill redige, mais cobertura de cota para a matemática de capacidade que precisa fechar antes de o plano significar alguma coisa
---
name: comp-plan-drafter
description: Draft a sales compensation plan — metric, pay mix, quota, accelerator curve, SPIFs, clawback trigger, and dispute policy — from role, segment, and OTE inputs, then stress-test it by replaying last year's actual attainment distribution through the new curve. Reports modeled plan cost, per-decile rep earnings, and policy gaps. Emits `draft` or `blocked`, never an approved plan.
---
# Sales comp plan drafter
## When to invoke
Whenever someone is writing next year's sales compensation plan and the only cost model behind it is a spreadsheet that assumes everyone lands at 100% of quota. The canonical moment is six to ten weeks before the plan year opens, while the curve is still editable and before anything has been shown to reps. Also valid: a mid-year plan amendment for one segment, a new role whose plan has no precedent in the org, and a post-mortem run against the plan currently in market to explain why variable comp came in over or under budget.
Take a plan inputs file (`references/1-plan-inputs-template.md`), an attainment history file (`references/2-attainment-history-template.md`), and produce the Markdown plan document plus stress-test report shown in `references/3-sample-output-format.md`.
Do NOT invoke this skill for:
- **Approving or issuing a plan.** The output is a draft that goes to compensation, finance, and counsel. A sales comp plan is a contract; in California, Labor Code § 2751 requires it in writing, signed by the employer, with a signed acknowledgment of receipt from the employee. There is no verdict in this skill that means "ship it."
- **Calculating or paying commissions.** This drafts and prices the plan. Payout calculation, dispute resolution, and payroll belong to an ICM platform or the finance team, and the skill writes to nothing.
- **Setting individual quotas.** It models a quota level for a role and segment. Assigning a number to a named rep is a territory-and-capacity question — carve first, then price the plan against the carve.
- **Recruiting pay bands.** Benchmarking base and equity for a role against survey data is a different job with different sources.
- **Books with fewer than `min_history_reps` fully-ramped rep-years.** A distribution built from six survivors is not a distribution, and a cost model built on it is a guess wearing a table. The skill returns `blocked`.
## Inputs
- Required: `plan_inputs_path` — role, segment, headcount, target OTE, pay mix, proposed quota, curve shape, plan year, and the states reps work in. See `references/1-plan-inputs-template.md`.
- Required: `attainment_history_path` — one row per rep-year for the trailing plan year, including reps who left mid-year. See `references/2-attainment-history-template.md`.
- Optional: `budget_ceiling` — total variable compensation approved for the plan year, in plan currency. When set, the cost report is expressed against it rather than as a bare number.
- Optional: `sensitivity_band_pct` — default `10`. The company-wide attainment shift, in percentage points, used for the low and high cost cases.
- Optional: `dry_run` — boolean, default `false`. When `true`, the skill validates the history file and returns the observed distribution plus a data-quality report, without drafting a plan. Run this first.
## Reference files
Read both input templates before drafting anything. Without the attainment history the skill has no cost model and must not invent one.
- `references/1-plan-inputs-template.md` — the plan being designed: role, segment, OTE, pay mix, quota, curve, SPIF budget, work states, and the policy constraints that bound the draft.
- `references/2-attainment-history-template.md` — one row per rep-year: attainment percentage, prorated quota, months ramped, and termination date if any. The `include_terminated` flag is load-bearing.
- `references/3-sample-output-format.md` — the exact Markdown the skill emits, with a worked example. Downstream consumers (a finance model, a plan-document template) parse this shape.
## Method
Run in order. Steps 2 and 3 are the load-bearing split; do not merge them.
1. **Load and validate.** Parse both files. Count fully-ramped rep-years in the history. Below `min_history_reps` (default 12), stop and return `blocked` — say how many rows were found and what the floor is. If `include_terminated` is `false`, return `blocked` regardless of row count: a history containing only the reps who stayed is survivorship-biased in the one direction that matters, because low attainers leave, and it makes every plan look cheaper and every distribution look healthier than it is.
2. **Draft the plan.** This is the judgment pass and it belongs to the model. Produce: the metric paid on, the pay mix, the quota, the curve (threshold, target rate, accelerator tiers and where they kick in, decelerator if any), a SPIF budget line with a named expiry date, the clawback trigger, and the dispute-resolution policy with a named response window. Keep the component count at or below `max_components` (default 3) — every component past the third divides rep attention without adding steering, and the modeled dollars usually show one component carrying almost nothing.
3. **Back-cast the draft against the observed distribution — in code.** Replay each historical rep's actual attainment percentage through the *new* curve and sum the modeled payouts. Do this arithmetic in code, not by reading the roster into the reasoning context. A piecewise payout function applied to forty rep-rows will not reproduce run to run when a model does it in context, and a compensation conversation collapses the moment two runs of the same draft produce two plan costs. The model's job is the curve, the ranking, and the narrative.
Report three numbers, not one: modeled cost at the observed distribution, at the distribution shifted up by `sensitivity_band_pct`, and shifted down by the same. A comp plan is a leveraged instrument and the useful figure is the slope. A plan whose cost moves 8% across a 20-point attainment swing is under-leveraged and will not change behavior; one that moves 60% is a budget risk somebody should agree to on purpose.
4. **Report earnings by decile, not by average.** Average earnings hide the plan's actual behavior. Emit modeled total earnings at the 10th, 50th, and 90th percentile of the observed distribution, alongside target OTE. The number that predicts attrition is what the median rep actually earns against the OTE they were recruited on — if that lands well below target, the plan is priced for the budget rather than for the market and the cost report will still pass.
5. **Run the policy check.** For each state in `rep_work_states`, note the local constraint and emit the checklist rather than a conclusion. Three conditions decide whether a clawback survives challenge in most states: the trigger is defined in the plan document before the commission is paid, the earning event is tied to something genuinely reversible, and the recovery mechanism cannot push the rep below the applicable minimum wage in any pay period. Check the draft against all three and name which one fails. Where California is in the list, add the § 2751 items: written agreement, signed by the employer, signed acknowledgment of receipt from the employee, and a stated method for computing commissions including the chargeback policy.
6. **Emit `draft` or `blocked`.** `draft` means the plan is modeled, priced, and ready for human review; every `draft` document carries `requires_counsel_review: true` in its header. `blocked` means a data problem makes the cost numbers untrustworthy — too few rep-years, terminated reps excluded, or a quota shift that invalidates the distribution. There is deliberately no third verdict. The skill makes the cost and the policy gaps visible before people decide; it does not decide.
## Output format
The skill emits Markdown in exactly this shape. Full worked example with populated rows in `references/3-sample-output-format.md`.
```markdown
# Comp plan draft — FY27 Mid-Market AE
plan_year: 2027 | headcount: 34 | history rows: 41 (incl. 9 terminated)
requires_counsel_review: true
## Verdict: draft
Curve lands 21% under budget at the observed distribution and the median rep
earns 77% of OTE — priced for the budget, not the market. Clawback trigger
fails the reversibility test.
## 1. Plan structure
| component | metric | weight | notes |
|---|---|---|---|
| base | — | 50% of OTE | 100,000 |
| commission | closed-won ARR | 45% of OTE | 9.4% of ARR at target |
| SPIF | new-logo multi-year | 5% of OTE | expires 2027-06-30 |
## 2. Curve
| band | attainment | rate | cumulative payout |
|---|---|---|---|
| threshold | 0-50% | 0% | 0 |
| target | 50-100% | 9.375% of ARR | 90,000 at 100% |
| accelerator 1 | 100-130% | 1.5x base rate | 130,500 at 130% |
| accelerator 2 | 130%+ | 2.0x base rate | uncapped |
## 3. Modeled cost (back-cast on 41 rep-years, 34 plan heads)
| case | company attainment | variable cost | vs budget (3,060,000) |
|---|---|---|---|
| low | observed -10 pts | 1,940,000 | -37% |
| observed | 61% median | 2,410,000 | -21% |
| high | observed +10 pts | 2,980,000 | -3% |
## 4. Rep earnings by decile
| percentile | attainment | modeled earnings | vs OTE (200,000) |
|---|---|---|---|
| p10 | 34% | 100,000 | 50% |
| p50 | 61% | 154,900 | 77% |
| p90 | 141% | 250,300 | 125% |
## 5. Policy check
| item | state | status |
|---|---|---|
| written + signed + acknowledged | CA | present in draft |
| computation method stated | CA | present in draft |
| clawback trigger pre-defined | all | present in draft |
| clawback tied to reversible event | all | FAIL — 12-month churn is not the earning event |
| minimum-wage floor per pay period | CA, NY, WA | not modeled — needs draw schedule |
## 6. What to change
- The clawback recovers on churn inside 12 months, but the plan earns
commission on booking. Tie recovery to non-payment or contract
cancellation, or move the earning event to cash collected.
- Median rep earns 154,900 against a 200,000 OTE, and the plan spends
650,000 under budget. The curve is not the cause: at 61% median
attainment, no defensible quota-to-OTE ratio pays the median rep target.
Quota would have to fall to roughly 590,000 — a 3.0x ratio — to put the
median at 100%. Either fix the input (coverage, territory, ramp) or
accept that this plan pays half the team 77% of OTE and say so at hire.
- Cost moves 43% across a 20-point attainment swing. That is real leverage
and it is worth confirming on purpose rather than discovering in Q3.
```
## Watch-outs
- **An attainment history that excludes reps who left.** Low attainers leave, so a survivors-only file understates plan cost and overstates the health of the distribution — in the same direction, at the same time. Guard: `include_terminated` is a required field and the skill returns `blocked` when it is `false`; terminated reps enter with prorated quota and partial-year attainment.
- **A distribution produced under a different quota.** Last year's attainment reflects last year's quota and last year's territories. If the new median quota moves materially, the old distribution stops predicting anything. Guard: the skill records `prior_plan_quota_median` and warns when the drafted quota moves more than `quota_shift_tolerance_pct` (default 15), stating in the report that the cost model is directional only.
- **A plan that passes the budget check and loses people.** The cost report is a finance instrument and it will happily approve a plan the median rep cannot live on. Guard: the decile table sits next to the cost table and reports median modeled earnings as a percentage of target OTE, so the retention cost is on the same page as the budget cost.
- **A clawback that recovers against something the earning event does not cover.** Recovering commission on 12-month churn when the plan earns on booking is the most common drafting error, and it is the condition that fails in dispute. Guard: step 5 tests the trigger against the earning event explicitly and names the mismatch rather than reporting a generic pass.
- **A permanent SPIF.** A SPIF that never expires is not a SPIF, it is an undocumented rate increase that nobody re-approves. Guard: the SPIF line requires an explicit expiry date in the inputs file, and the skill refuses to draft a SPIF component without one.
- **Treating `blocked` as a verdict on the plan.** `blocked` says the numbers cannot be trusted, not that the design is wrong. Guard: every `blocked` return names the specific data defect and what would clear it, so the response is a data fix rather than a redesign.
# Plan inputs
Replace the example values with yours. Everything here describes the plan you want drafted and the constraints it has to live inside. The skill drafts the curve; it does not invent the OTE, the headcount, or the states your reps work in.
## Role and scope
```yaml
plan_year: 2027
plan_start: 2027-01-01
role: "Mid-Market Account Executive"
segment: "mid-market" # smb | mid-market | enterprise | strategic
headcount: 34 # quota-carrying heads in this plan at plan start
currency: USD
plan_status: draft # draft | socialized | in_market
```
`plan_status` changes the tone of the report, not the arithmetic. Once a plan is `socialized`, a recommendation to change the curve carries a communication cost as well as an effort cost, and the report says so in the header rather than leaving the leader to discover it in the meeting.
## Target compensation
```yaml
target_ote: 200000
pay_mix: # must sum to 100
base_pct: 50
variable_pct: 50
market_ote_reference: 200000 # what you believe the market pays this role
market_ote_source: "Bridge Group 2026 AE Metrics, median OTE 200,000"
```
`market_ote_reference` is what the decile table compares against when it flags a plan priced below market. Set it from a survey you actually hold, and name the source — if it is a guess, say so in `market_ote_source`, because the retention flag is only as good as this number.
## Quota
```yaml
proposed_quota: 960000 # annual, per fully-ramped rep
prior_plan_quota_median: 850000 # last year's median assigned quota
quota_shift_tolerance_pct: 15 # warn above this much movement
```
The tolerance exists because the attainment history you supply was produced under `prior_plan_quota_median`. Move the quota far enough and the distribution stops predicting the new plan's cost. The skill will still model it; it will label the output directional.
## Curve
Give the shape you want drafted. Leave any field as `propose` and the skill drafts that piece; pin the ones that are already decided.
```yaml
curve:
threshold_pct: 50 # no commission below this attainment
target_rate: 1.0 # multiplier between threshold and 100%
accelerators:
- from_pct: 100
to_pct: 130
rate: propose
- from_pct: 130
to_pct: null # null = uncapped
rate: propose
decelerator: none # none | {below_pct, rate}
cap: none # none | a dollar figure
```
Uncapped is a real decision, not a default. A cap protects the budget against a single outsized deal and reliably produces the sandbagging it was written to prevent; the cost table's high case is where you should look before choosing.
## Components
Keep this at three or fewer. A fourth component almost always shows up in the modeled-dollars column carrying a rounding error's worth of pay and a meaningful share of rep attention.
```yaml
max_components: 3
components:
- name: commission
metric: closed_won_arr # the thing you want more of
weight_pct: 90 # share of the variable half
- name: new_logo_spif
metric: new_logo_multiyear
weight_pct: 10
expiry: 2027-06-30 # required — a SPIF with no expiry is a rate increase
```
## Earning event and clawback
```yaml
earning_event: booking # booking | invoiced | cash_collected
clawback:
trigger: "customer non-payment within 90 days of invoice"
recovery_method: "offset against future commission, max 25% per pay period"
post_termination: false
```
`earning_event` and `clawback.trigger` have to describe the same thing. Earning on `booking` while recovering on churn is the mismatch the policy check is looking for: the plan is trying to reverse something the earning event never depended on.
## Policy constraints
```yaml
rep_work_states: [CA, NY, TX, WA, IL]
draw:
type: none # none | recoverable | non_recoverable
amount_monthly: 0
dispute_policy:
response_window_days: 15
escalation: "RevOps → VP Sales → CFO"
budget_ceiling: 3060000 # total approved variable comp for the plan year
min_history_reps: 12
sensitivity_band_pct: 10
```
The state list drives the policy checklist. It is not legal advice and the skill does not pretend otherwise — it produces the items counsel needs to see, marked against the draft, so the review is a review rather than a discovery exercise.
# Attainment history
One row per rep-year for the trailing plan year. This file is the cost model. Everything the stress test reports comes from replaying these rows through the drafted curve, so the quality of this file sets the quality of the output.
## The one rule that matters
```yaml
include_terminated: true
```
Include the reps who left. All of them, with their partial-year attainment and their prorated quota.
This is not a completeness preference. Attrition in a sales org is not random with respect to attainment — low attainers leave, and they leave disproportionately. A history containing only the people still on the roster understates what the plan will cost and overstates how healthy the distribution is, in the same direction, at the same time. The skill returns `blocked` when this flag is `false`, because a plan priced on survivors is priced on the wrong population.
## Rows
```csv
rep_id,segment,months_ramped,prorated_quota,attainment_pct,terminated_on,notes
r-001,mid-market,12,850000,141,,
r-002,mid-market,12,850000,118,,
r-003,mid-market,12,850000,104,,
r-004,mid-market,12,850000,97,,
r-005,mid-market,12,850000,88,,
r-006,mid-market,12,850000,74,,
r-007,mid-market,12,850000,61,,
r-008,mid-market,12,850000,58,,
r-009,mid-market,12,850000,44,,
r-010,mid-market,12,850000,31,,
r-011,mid-market,7,495833,38,2026-07-31,involuntary
r-012,mid-market,5,354167,22,2026-05-29,involuntary
r-013,mid-market,9,637500,96,2026-09-30,voluntary — competitor offer
```
| Column | What goes in it |
|---|---|
| `rep_id` | Any stable identifier. Do not use names; the output is circulated. |
| `segment` | Must match a segment in the plan inputs, or the row is excluded and counted in the data-quality report. |
| `months_ramped` | Months at full productivity during the year. A rep in month three of a six-month ramp contributes a partial rep-year and is excluded from the fully-ramped count. |
| `prorated_quota` | The quota actually carried, prorated for partial years. Not the annual number. |
| `attainment_pct` | Attainment against `prorated_quota`, as a whole number. `141` means 141%. |
| `terminated_on` | ISO date, blank if still employed. |
| `notes` | Free text. `voluntary` / `involuntary` is worth recording — it is the only signal in this file about whether the plan drove the exit. |
## What counts toward `min_history_reps`
Only fully-ramped rep-years — rows where `months_ramped` equals 12, or where a terminated rep was fully ramped for the months they worked. Ramping reps are still worth including for the cost model, because they cost money, but they do not make the distribution more trustworthy and the skill does not count them toward the floor.
Below the floor, the correct output is `blocked`. Thirteen rows is a distribution you can argue about; six is an anecdote with a percentile function applied to it.
## Optional: prior-plan curve
Supply the curve these attainments were paid under and the report adds a year-over-year comparison — what the same rep-years would have cost under the old plan against the new one. This is the single most persuasive number in a comp review, and it is unavailable without this block.
```yaml
prior_curve:
threshold_pct: 60
target_rate: 1.0
accelerators:
- from_pct: 100
to_pct: null
rate: 1.4
cap: none
```
## Data-quality report
Run the skill with `dry_run: true` before drafting anything. It returns the observed distribution, the fully-ramped count, and a list of rows it had to exclude with the reason for each. A history file usually has two or three rows with a quota of zero or an attainment above 400% from a single outsized deal, and you want to see those before they are inside a cost number rather than after.
# Sample output
The exact Markdown the skill emits, populated from the example inputs in `references/1-plan-inputs-template.md` and the example history in `references/2-attainment-history-template.md`. Section order and heading text are stable — a finance model or a plan-document template can parse against them.
---
# Comp plan draft — FY27 Mid-Market AE
plan_year: 2027 | headcount: 34 | history rows: 41 (incl. 9 terminated)
quota shift vs prior plan: +12.9% (within 15% tolerance)
requires_counsel_review: true
## Verdict: draft
Curve lands 21% under budget at the observed distribution and the median rep earns 77% of OTE. The plan is priced for the budget, not the market. The clawback trigger fails the reversibility test and must be redrafted before counsel review.
## 1. Plan structure
| component | metric | weight | notes |
|---|---|---|---|
| base | — | 50% of OTE | 100,000 |
| commission | closed-won ARR | 45% of OTE | 9.375% of ARR, 90,000 at 100% |
| SPIF | new-logo multi-year | 5% of OTE | 10,000 pool, expires 2027-06-30 |
Earning event: `booking`. Draw: none. Dispute window: 15 days, escalating RevOps → VP Sales → CFO.
## 2. Curve
| band | attainment | rate | payout at band ceiling |
|---|---|---|---|
| threshold | 0-50% | 0% | 0 |
| target | 50-100% | 9.375% of ARR | 90,000 |
| accelerator 1 | 100-130% | 1.5x base rate | 130,500 |
| accelerator 2 | 130%+ | 2.0x base rate | uncapped |
The threshold is a gate, not a ramp: a rep who clears 50% is paid on every dollar from the first, and a rep at 49% is paid nothing variable. That is a deliberate cliff and it is the single most disputed line in any plan that has one — the 49% rep and the 51% rep are 20,000 apart on a difference of one deal.
## 3. Modeled cost — back-cast on 41 rep-years, 34 plan heads
| case | company attainment | variable cost | vs budget (3,060,000) |
|---|---|---|---|
| low | observed -10 pts | 1,940,000 | -37% |
| observed | 61% median | 2,410,000 | -21% |
| high | observed +10 pts | 2,980,000 | -3% |
Cost moves 43% across the 20-point band. Under the prior curve (60% threshold, 1.4x single accelerator) the same 41 rep-years would have cost 2,265,000 — the new plan is 6.4% more expensive at identical performance, almost entirely from the second accelerator tier.
## 4. Rep earnings by decile
| percentile | attainment | modeled earnings | vs OTE (200,000) |
|---|---|---|---|
| p10 | 34% | 100,000 | 50% |
| p50 | 61% | 154,900 | 77% |
| p90 | 141% | 250,300 | 125% |
Nine of the 41 rep-years land below the 50% threshold and earn base only. Three of those nine are terminated rows, which is the expected pattern and the reason the terminated set has to be in the file.
## 5. Policy check
| item | state | status |
|---|---|---|
| written agreement, signed by employer | CA | present in draft |
| signed acknowledgment of receipt | CA | present in draft |
| method of computing commissions stated | CA | present in draft |
| chargeback policy stated in agreement | CA | present in draft |
| clawback trigger defined before payment | all | present in draft |
| clawback tied to a reversible earning event | all | **FAIL** — see below |
| recovery cannot breach minimum wage in a pay period | CA, NY, WA | not modeled — no draw schedule supplied |
| post-termination recovery | all | disabled in draft (`post_termination: false`) |
This is a checklist for counsel, not a legal opinion. It reports which items the draft addresses and which it does not.
## 6. What to change
- **Clawback reversibility.** The inputs file sets `earning_event: booking` and a clawback trigger of customer non-payment within 90 days of invoice. Those describe different events: the commission is earned when the deal is booked, and non-payment happens downstream of an earning event that never depended on collection. Either move `earning_event` to `cash_collected`, or narrow the trigger to contract cancellation before invoice. As drafted this is the condition most likely to fail if a recovery is challenged.
- **The median rep earns 154,900 against a 200,000 OTE**, while the plan spends 650,000 less than the approved budget. The curve is not the cause. At a 61% median attainment, no defensible quota-to-OTE ratio pays the median rep target — quota would have to drop to roughly 590,000, a 3.0x ratio, to put the median at 100%. The proposed 960,000 quota against a 200,000 OTE is 4.8x. Fix the input (coverage, territory, ramp) or accept that this plan pays half the team 77% of OTE and say so at hire rather than in month nine.
- **Minimum-wage floor is unmodeled** because no draw was supplied. With `draw.type: none` the base alone clears the floor in every listed state, so this is informational — but if a recoverable draw is added later, the 25%-per-pay-period recovery cap has to be re-checked against it.
- **Cost leverage of 43% across 20 points** is a real exposure in a good year. It is defensible; it should be a decision somebody makes in December rather than a surprise in Q3.
