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 agentmods add rules/gingg7260/affiliate-skills/cursorrulesgit clone --depth 1 https://github.com/Gingg7260/affiliate-skillsWhat 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 | $0.00595 | $0.00595 |
| Opus 5 | $0.00298 | $0.00298 |
| Sonnet 5 | $0.00119 | $0.00119 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
cursorrules 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 3d 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
86% identical to cursorrules — 20 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Affitor Affiliate Skills — Cursor Rules
What This Repo Is
45 AI-powered skills for affiliate marketers. Each skill automates a specific workflow (content creation, program research, SEO, outreach, analytics, etc.) using live data from the Affitor API.
How Skills Work
- Each skill lives in
skills/<stage>/<skill-name>/SKILL.md SKILL.mdis a self-contained instruction file: it defines inputs, workflow steps, and expected outputs- Skills are designed to be chained — the output of one skill feeds the next
- Run a skill by reading its
SKILL.mdand executing the documented workflow
Directory Layout
skills/ # Skills grouped by stage (research, content, blog, landing, distribution, analytics, automation, meta)
registry.json # Master index of all 45 skills with metadata
API.md # Full Affitor API reference
prompts/ # Bootstrap prompt for any AI
shared/
references/ # Cross-skill reference docs (FTC rules, glossary, branding)
Affitor API
- Base URL:
https://list.affitor.com/api/v1 - Programs endpoint:
GET /programs - Key fields per program:
reward_value— commission amount or percentagereward_type— "cps_recurring" | "cps_one_time" | "cps_lifetime" | "cpl" | "cpc"cookie_days— attribution window in daysstars_count— community star count (popularity signal)slug,name,tags[],url,description
- Always fetch real data from the API. Never fabricate program details.
Key Rules
- FTC disclosure required — any content that promotes an affiliate program must include
a clear disclosure ("I may earn a commission..."). See
shared/references/ftc-compliance.md. - Data from API, not guesses — commission rates, cookie windows, and program names must come from live API responses.
- Portable output — skill outputs must work standalone (markdown, plain text, CSV). No platform-specific formatting unless the skill explicitly targets one.
- Follow the SKILL.md workflow exactly — each step is intentional. Don't skip steps.
- Chain outputs — skills are composable. Pass structured output from one skill as input to the next when building multi-step workflows.
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.
- 3d ago First seen · 50 lines · 595 tokens per session scan A de40fa530562
cursorrules is a cursor rule published in the GitHub repository Gingg7260/affiliate-skills (5 stars, last pushed 4d ago), licensed MIT. It adds 595 tokens to every session, about $0.0030 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to cursorrules, differing in 20 lines, and is treated as a copy.
Other cursor rules, from other repositories
cursorrules
45 AI-powered skills for affiliate marketers. Each skill automates a specific workflow (content creation, program research, SEO, outreach, analytics, etc.) using live data from the Affitor API.
research-mode
このルールは Gemini Flash 等の軽量AIが「情報収集だけ」を行う際に適用する。 コードの変更は一切行わない。 調査結果を構造化して返すことだけが目的。.
code-standards
Code quality standards, development practices, and project-specific guidelines.
deployment-urls
Standards for managing deployment URLs and preventing broken links in documentation.
github-optimization
GitHub repository optimization standards for better discoverability and professional presentation.
deployment
Deployment guidelines, Cloudflare Workers compatibility, and environment management.