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/gabrielmoreira/agent-skills-mirror/cursorrulesgit clone --depth 1 https://github.com/gabrielmoreira/agent-skills-mirrorWrote 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/rules/gabrielmoreira/agent-skills-mirror/cursorrules)<a href="https://agentmods.dev/rules/gabrielmoreira/agent-skills-mirror/cursorrules"><img src="https://agentmods.dev/badge/rules/gabrielmoreira/agent-skills-mirror/cursorrules.svg" alt="Measured on agentmods" 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 | $0.00654 | $0.00654 |
| Opus 5 | $0.00327 | $0.00327 |
| Sonnet 5 | $0.00131 | $0.00131 |
| Haiku 4.5 | $0.00065 | $0.00065 |
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 yesterday.
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
100% identical to cursorrules — 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 — 54 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://openaffiliate.dev/api - Programs endpoint:
GET /programs?q=<text>&sort=<relevance|trending|new|top>&limit=<n> - Single program:
GET /programs/<slug> - Public, no API key or auth required
- Raw API fields (camelCase, nested):
slug,name,url,logo,category,commission.type,commission.rate,commission.duration,cookieDays,payout.*,description,shortDescription,tags[],stars,verified - CLI-normalized skill-facing fields (used in skill outputs):
reward_value— from commission.ratereward_type— from commission.typecookie_days— from cookieDaysstars_count— from stars
- 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.
- yesterday First seen · 54 lines · 654 tokens per session scan A 598ae25ba742
cursorrules is a cursor rule published in the GitHub repository gabrielmoreira/agent-skills-mirror (17 stars, last pushed yesterday), licensed MIT. It adds 654 tokens to every session, about $0.0033 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to cursorrules, differing in 0 lines, and is treated as a copy.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.