competitor-spy

competitor-spy is a skill for Claude Code from Affitor/affiliate-skills. It costs 119 tokens per session (3,493 once invoked), scanned A, original, MIT.

A research workflow for studying affiliate competitors, including websites, YouTube channels, and social profiles. It looks for the programs they promote, their content, and possible traffic sources.

In plain words
What is it for?
Use it to analyze a named competitor or a whole niche, focusing on affiliate programs, content, traffic, or strategy at a chosen level of detail.
Why use it?
It helps reveal how other affiliates approach a niche instead of relying only on guesswork. It can also expose content gaps that competitors have not covered.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code; built for openclaw; mentions Gemini CLI.

Part of the research-skills plugin — 4 skills shipped together

Good fit Use it to analyze a named competitor or a whole niche, focusing on affiliate programs, content, traffic, or strategy at a chosen level of detail.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/affitor/affiliate-skills/competitor-spy
Install

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.

Any agent
npx skills add Affitor/affiliate-skills --skill competitor-spy
Clone the repo
git clone --depth 1 https://github.com/Affitor/affiliate-skills

Made for: Claude Code.

Or install research-skills, the plugin that ships this one along with the rest of its 4 skills.

Wrote 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.

agentmods badge for competitor-spy

README.md
[![agentmods](https://agentmods.dev/badge/skills/affitor/affiliate-skills/competitor-spy/github.svg)](https://agentmods.dev/skills/affitor/affiliate-skills/competitor-spy)
Your own site
<a href="https://agentmods.dev/skills/affitor/affiliate-skills/competitor-spy"><img src="https://agentmods.dev/badge/skills/affitor/affiliate-skills/competitor-spy/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for competitor-spy

Your own site · 80×15
<a href="https://agentmods.dev/skills/affitor/affiliate-skills/competitor-spy"><img src="https://agentmods.dev/badge/skills/affitor/affiliate-skills/competitor-spy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,493 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00119 $0.03493
Opus 5 $0.00060 $0.01747
Sonnet 5 $0.00024 $0.00699
Haiku 4.5 $0.00012 $0.00349

Measured 10d ago against content hash ae854372edef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

competitor-spy 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 10d 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

skills/research/competitor-spy/SKILL.md · 343 lines

How it starts

The opening of the file, as written. The whole thing — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Competitor Spy

Analyze competitor affiliate sites, YouTube channels, and social profiles to surface which programs they promote, what content drives their traffic, and which strategies are worth replicating. Outputs an actionable reverse-engineering report so you can skip years of trial and error.

Stage

This skill belongs to Stage S1: Research

When to Use

  • User wants to know what programs are working in a specific niche
  • User has a competitor site/channel in mind and wants to understand their strategy
  • User is entering a new niche and wants a shortcut to what works
  • User wants to find underserved content gaps a competitor hasn't covered
  • User asks "how do top affiliates in [niche] make money?"

Input Schema

{
  competitor_url: string      # (optional) Direct URL to competitor site, channel, or profile
  niche: string               # (optional) Niche to analyze if no specific competitor given
  platform: string            # (optional) "blog" | "youtube" | "tiktok" | "twitter" | "newsletter"
  depth: string               # (optional, default: "standard") "quick" | "standard" | "deep"
  focus: string               # (optional) "programs" | "content" | "traffic" | "all"
}

Workflow

Step 1: Identify Competitors to Analyze

If competitor_url is provided, skip to Step 2.

If only niche is provided, find 3-5 top competitors:

  1. web_search "best [niche] affiliate sites" — look for review/comparison sites
  2. web_search "[niche] review site affiliate" — find review-first monetization models
  3. web_search "[niche] blog affiliate income report" — income reports reveal programs
  4. Note: YouTube — web_search "youtube [niche] affiliate site:youtube.com" to find channels

Pick 3 competitors that are clearly affiliate-driven (review pages, comparison tables, "best X" content, Amazon links, affiliate disclaimers visible).

Step 2: Identify Affiliate Programs They Promote

For each competitor site/channel:

Method A — Link analysis:

  • web_fetch [competitor_url] and scan for outbound links
  • Look for: ?ref=, ?via=, /go/, aff_id=, ?affiliate=, shareasale.com, impact.com, partnerstack.com, awin.com, cj.com, linktr.ee
  • These patterns indicate affiliate links

Read the full file on GitHub · 343 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 10d ago First seen · 343 lines · 119 tokens per session scan A ae854372edef

Subscribe to this mod's changes

competitor-spy is a skill published in the GitHub repository Affitor/affiliate-skills (654 stars, last pushed 4d ago), licensed MIT. It adds 119 tokens to every session and 3,493 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

competitor-spy

Reverse-engineer successful affiliate strategies from competitors. Use this skill when the user asks about spying on competitors, researching what other affiliates promote, analyzing competitor affiliate sites, understanding how top affiliates in a niche make money, or says "what programs does X promote", "how does…

gabrielmoreira/agent-skills-mirror · 119 tokens

competitor-spy

Reverse-engineer successful affiliate strategies from competitors. Use this skill when the user asks about spying on competitors, researching what other affiliates promote, analyzing competitor affiliate sites, understanding how top affiliates in a niche make money, or says "what programs does X promote", "how does…

Gingg7260/affiliate-skills · 119 tokens

niche-opportunity-finder

Find untapped affiliate niches with real earning potential. Use this skill when the user asks about picking a niche, finding a niche to start affiliate marketing, what niche to get into, niche research, niche ideas, beginner niche selection, low competition niches, profitable niches, or says "I don't know what to…

Gingg7260/affiliate-skills · 123 tokens

affiliate-program-search

Research and evaluate affiliate programs to find the best ones to promote. Use this skill when the user asks anything about finding affiliate programs, comparing commission rates, evaluating affiliate opportunities, searching for products to promote, picking a niche, or mentions list.affitor.com. Also trigger for…

Gingg7260/affiliate-skills · 120 tokens

purple-cow-audit

Score product remarkability 1-10 to decide if it's worth promoting. Seth Godin's Purple Cow test. Triggers on: "is this product worth promoting", "should I promote", "product audit", "purple cow", "remarkable product", "is it remarkable", "rate this product", "product quality check", "worth my reputation", "product…

jiaxiaojunQAQ/SkillJect · 107 tokens

commission-calculator

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…

gabrielmoreira/agent-skills-mirror · 112 tokens