Commission Calculator

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

Audit 0.4.1 · source sha 2515ce9634da · 15 Oct 2026Report an issue or request a re-scan

• PublisherAffitor GitHub organizationOwner of the repository this skill is read from
• Source folderAffitor/affiliate-skills/skills/research/commission-calculatorThe exact folder we audited
• LicenceMITAs the repository states it
• Commit pinned for this verdict2515ce9634daA new audit runs when the source changes
• Repository statusNot archivedLast push 2 days ago
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: Calculate realistic affiliate earnings projections before committing to a program. Use this skill when the user asks about affiliate earnings, projecting income, calculating commissions, estimating how much they can…

---
name: commission-calculator
description: >
  Calculate realistic affiliate earnings projections before committing to a program.
  Use this skill when the user asks about affiliate earnings, projecting income,
  calculating commissions, estimating how much they can make, comparing program
  payouts, or says "how much can I make promoting X", "calculate my affiliate income",
  "is this commission worth it", "how long to first $1000", "compare earnings
  between programs", "traffic to income calculator", "what conversion rate should
  I expect", "earnings estimate for affiliate program", "how many sales do I need".
license: MIT
version: "1.0.0"
tags: ["affiliate-marketing", "research", "niche-analysis", "program-discovery", "commission", "revenue"]
compatibility: "Claude Code, ChatGPT, Gemini CLI, Cursor, Windsurf, OpenClaw, any AI agent"
metadata:
  author: affitor
  version: "1.0"
  stage: S1-Research
---

# Commission Calculator

Project realistic monthly affiliate earnings based on traffic estimates, platform
conversion rates, and program commission structures. Helps affiliates decide which
programs are worth their time before investing months of content creation.

## Stage

This skill belongs to Stage S1: Research

## When to Use

- User wants to project income before choosing a program
- User wants to compare the earnings potential of 2+ programs
- User is setting income goals and needs realistic benchmarks
- User is deciding whether a niche is worth entering based on earning potential
- User asks "how many page views / subscribers / followers do I need to make X"

## Input Schema

```
{
  programs: [
    {
      name: string            # (required) "HeyGen"
      reward_value: string    # (required) "30%" or "$50"
      reward_type: string     # (required) "cps_recurring" | "cps_one_time" | "cpl" | "cpa"
      reward_duration: string # (optional) "12 months" | "lifetime" | "first purchase"
      cookie_days: number     # (optional, default: 30) 30
      avg_product_price: number # (optional) Monthly plan price in USD. Needed for % commissions
    }
  ]
  traffic: {
    monthly_visitors: number  # (optional) Estimated monthly website visitors or video views
    email_subscribers: number # (optional) Email list size
    social_followers: number  # (optional) Followers on primary platform
  }
  platform: string            # (optional) "blog" | "youtube" | "tiktok" | "email" | "twitter"
  scenario: string            # (optional, default: "realistic") "conservative" | "realistic" | "optimistic"
  goal: string                # (optional) Target income, e.g., "$500/mo" or "$1000/mo"
  time_horizon: string        # (optional, default: "90 days") "30 days" | "90 days" | "12 months"
}
```

## Workflow

### Step 1: Gather Program Details

If program details are missing, pull from openaffiliate.dev (see `references/openaffiliate-api.md` in affiliate-program-search).

Key fields to extract: `reward_value`, `reward_type`, `cookie_days`.

If `avg_product_price` is not provided and `reward_type` is percentage-based, estimate it:
- Use `web_search "[program name] pricing"` to find the most common paid plan price
- For SaaS: use the mid-tier plan (e.g., $49/mo on a $19/$49/$99 structure)
- Note the assumption in output so user can adjust

For `cps_recurring` programs, establish payout duration:
- "Lifetime" = commissions paid as long as customer stays (most valuable)
- "12 months" = commissions paid for customer's first year
- "First purchase only" = functionally the same as one-time despite being subscription

### Step 2: Gather Traffic Estimates

If traffic data is not provided, prompt the user OR use platform benchmarks:

| Channel | Benchmark Ranges |
|---------|-----------------|
| New blog (0-6 months) | 500-2,000 visitors/mo |
| Growing blog (6-18 months) | 2,000-20,000 visitors/mo |
| Established blog (18+ months) | 20,000-200,000+ visitors/mo |
| YouTube channel (<1K subs) | 200-2,000 views/mo |
| YouTube channel (1K-10K subs) | 2,000-50,000 views/mo |
| TikTok (<10K followers) | 1,000-20,000 views/video |
| Twitter/X (<5K followers) | 50-500 impressions/tweet |
| Email list (<1K subscribers) | 200-400 opens/send |
| Email list (1K-10K subscribers) | 2,000-7,000 opens/send |

If user won't provide traffic, use "realistic" scenario benchmarks for their stated
platform and growth stage.

### Step 3: Apply Conversion Rate Assumptions

Use these industry-standard conversion rates as defaults. Adjust based on traffic quality
("buyer intent" content converts 5-10x better than informational content):

| Platform + Content Type | Click-through Rate | Affiliate Conversion |
|------------------------|-------------------|---------------------|
| Blog — product review | 3-6% | 2-5% |
| Blog — best-of listicle | 1.5-3% | 1-3% |
| Blog — tutorial/how-to | 0.5-1.5% | 0.5-2% |
| YouTube — dedicated review | 5-10% | 3-6% |
| YouTube — tutorial with mention | 1-3% | 1-3% |
| TikTok — product demo | 0.5-2% (bio link) | 0.5-2% |
| Email — dedicated send | 10-20% | 3-8% |
| Twitter/X — thread CTA | 0.5-2% | 0.5-2% |

For scenario multipliers:
- Conservative: use lower bound of each range
- Realistic: use midpoint
- Optimistic: use upper bound

### Step 4: Calculate Monthly and Projected Earnings

**Formula:**

```
Monthly clicks = Monthly visitors × Click-through rate
Monthly conversions = Monthly clicks × Affiliate conversion rate
Monthly commission = Monthly conversions × Commission per sale

Commission per sale:
  - Percentage-based: avg_product_price × (reward_value / 100)
  - Fixed: reward_value (as number)

For recurring (monthly SaaS) over time_horizon:
  Month 1 revenue = Month 1 conversions × commission_per_sale
  Month 2 revenue = (Month 1 conversions + Month 2 conversions) × commission_per_sale
  Month N = sum of all active subscribers × commission_per_sale
  [Cap at reward_duration if not lifetime]
```

Calculate for each program:
- Monthly commission at current traffic
- Cumulative commission at 

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

1. 2026-10-15
   ✓SAFE B 89 / 100

   first audit · source 2515ce9634da

Questions about Commission Calculator

• github.com/Affitor/affiliate-skills/tree/main/skills/research/co — the audited source at commit 2515ce9634da and every finding aboveObserved · 15 Oct 2026

Spotted something wrong? Report a correction · Methodology