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 skills add bobberrisford/affiliatemcp --skill audit-affiliate-linksgit 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/audit-affiliate-links)<a href="https://agentmods.dev/skills/bobberrisford/affiliatemcp/audit-affiliate-links"><img src="https://agentmods.dev/badge/skills/bobberrisford/affiliatemcp/audit-affiliate-links/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/audit-affiliate-links"><img src="https://agentmods.dev/badge/skills/bobberrisford/affiliatemcp/audit-affiliate-links.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 | $0.00066 | $0.01173 |
| Opus 5 | $0.00033 | $0.00587 |
| Sonnet 5 | $0.00013 | $0.00235 |
| Haiku 4.5 | $0.00007 | $0.00117 |
Grade A, and why
audit-affiliate-links 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operating instructions
You are auditing a publisher's affiliate links. The job has three steps: identify, verify, report.
Step 1 — gather the links
Accept any of:
- A pasted list of URLs.
- A pasted markdown / HTML document — extract every
<a href>or[text](url). - A sitemap URL or path — read it and extract
<loc>entries.
Filter the extracted URLs down to affiliate links by host. The server
supports many networks (affiliate_list_networks is the authoritative list);
these four have well-known, stable host patterns you can classify by host alone:
awin1.com,awin.com,*.awin1.com— Awin.*.dpbolvw.net,*.kqzyfj.com,*.tkqlhce.com,anrdoezrs.net,*.cj.com,*.cjlinks.com— CJ Affiliate.*.impact.com,goto.target.com-style branded vanity hosts that resolve to Impact — Impact (note: many Impact links use brand-vanity hosts, so if you cannot tell, ask the user).click.linksynergy.com,*.linksynergy.com,*.rakutenmarketing.com— Rakuten Advertising.
Links from the other supported networks will not match a pattern above. That is expected, not a failure: if a link looks like an affiliate redirect but matches no listed host, do not discard it. List it under "could not classify — please confirm" and ask the user which network it belongs to, then proceed with the id-based lookup in Step 2. Only treat a link as non-affiliate when it is plainly a normal destination URL.
Step 2 — extract the programme identifier
Each network encodes the programme id (or advertiser id) in the URL differently. The reliable approach: do not hand-parse. Instead, call affiliate_list_networks first to confirm which networks have registered adapters; this does not prove that credentials are configured. Then, for each candidate URL:
- Match the URL to a network by host, or use the user's confirmed network for a recognised affiliate link whose host is not in the list above.
- Parse the obvious query parameters (
m,mid,awinmid,id,merchantid) — these usually carry the programme id. - Call
affiliate_<slug>_get_programmewith that id. - If the call fails or returns
status: 'declined' | 'suspended', mark the link as broken. - If the call returns
status: 'joined', mark the link as OK. - If the call returns
status: 'pending' | 'available', mark the link as inactive with a one-line explanation.
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.
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 · 88 lines · 66 tokens per session scan A 821000ca2be6
audit-affiliate-links is a skill published in the GitHub repository bobberrisford/affiliatemcp (6 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 1,173 once invoked, about $0.0003 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…