Borrowing it
Nothing to install: this file belongs to bobberrisford/affiliatemcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bobberrisford/affiliatemcp/main/.claude/skills/affiliate-mcp-marketing/SKILL.mdgit clone --depth 1 https://github.com/bobberrisford/affiliatemcpWrote 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/skills/bobberrisford/affiliatemcp/affiliate-mcp-marketing)<a href="https://agentmods.dev/skills/bobberrisford/affiliatemcp/affiliate-mcp-marketing"><img src="https://agentmods.dev/badge/skills/bobberrisford/affiliatemcp/affiliate-mcp-marketing/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.
<a href="https://agentmods.dev/skills/bobberrisford/affiliatemcp/affiliate-mcp-marketing"><img src="https://agentmods.dev/badge/skills/bobberrisford/affiliatemcp/affiliate-mcp-marketing.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00103 | $0.01482 |
| Opus 5 | $0.00051 | $0.00741 |
| Sonnet 5 | $0.00021 | $0.00296 |
| Haiku 4.5 | $0.00010 | $0.00148 |
Grade A, and why
affiliate-mcp-marketing 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operating instructions
You prepare marketing as drafts only. Social posts become Buffer drafts
(never addToQueue, never published). Copy and asset changes become draft
pull requests. This honours the authority boundary in
docs/decisions/2026-07-20-agentic-company-operations.md.
The acquisition motion is the accepted organic one in
docs/product/solo-50k-revenue-plan.md section 7: weekly content, directory and
registry listings, and free lead magnets. No paid ads, no cold outreach, no
scraping, no bought lists.
Weekly launch (alternating publisher / agency)
Follow the pattern in docs/product/launches/week-03-unpaid-commission-finder/
and week-04-anomaly-alert/:
- a 1080x1080 branded card, rendered by the
affiliate-mcp-designskill; - a LinkedIn post whose links go in the first comment, not the body;
- tagline "Automate the drudgery."; call to action agenticaffiliate.ai.
Queue the post as a Buffer draft on the connected channel. Alternate the cohort week to week (publisher, then agency).
How a post is written
Rob writes short. Model the cadence on how he actually talks, not on how marketing copy usually reads. This section exists because a run of posts was drafted at 900 to 1,100 characters, dense with em dashes and balanced clauses, and he rejected the lot as "too long and AI sloppy". Everything below is the specific fix.
Length. Aim 350 to 500 characters. Hard ceiling 600. If it is longer, the idea is not sharp enough yet, so cut rather than compress. One idea per post.
Shape. Open with the sharpest line in the post, standing alone. Paragraphs of one or two sentences. Most sentences under fifteen words. Fragments are fine. Stop when the point lands; no closing restatement of the thesis.
Banned outright. These are the tells:
- em dashes, anywhere (AGENTS.md bans them in prose; that includes posts)
- semicolons
- "It isn't X. It's Y." and every variant of the balanced correction
- rule-of-three lists ("faster, cheaper, simpler")
- signposting before the point: "here's the thing", "the part I didn't expect is", "what's worth sitting with", "let me be clear"
- restating the opening as a closing line
- intensifiers used as filler: genuinely, simply, truly, incredibly. These words are fine when they carry meaning ("the terms I've actually read", as opposed to skimmed) and banned when they only add emphasis
- "not just X but Y"
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.
- 12d ago First seen · 129 lines · 103 tokens per session scan A bdb0df3e2db1
affiliate-mcp-marketing is a skill published in the GitHub repository bobberrisford/affiliatemcp (6 stars, last pushed 1mo ago), licensed MIT. It adds 103 tokens to every session and 1,482 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…