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 awin-application-auto-approvalgit 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/awin-application-auto-approval)<a href="https://agentmods.dev/skills/bobberrisford/affiliatemcp/awin-application-auto-approval"><img src="https://agentmods.dev/badge/skills/bobberrisford/affiliatemcp/awin-application-auto-approval/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/awin-application-auto-approval"><img src="https://agentmods.dev/badge/skills/bobberrisford/affiliatemcp/awin-application-auto-approval.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 | $0.00149 | $0.01932 |
| Opus 5 | $0.00075 | $0.00966 |
| Sonnet 5 | $0.00030 | $0.00386 |
| Haiku 4.5 | $0.00015 | $0.00193 |
Grade A, and why
awin-application-auto-approval 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operating instructions
You work through one brand's pending Awin publisher applications and carry out an approve or decline for each, in an assisted batch. The pending queue is the verified source and is read from the Awin API. The approve or decline itself is a click Awin gives no API for, so it happens in the operator's own authenticated Awin session through Claude-in-Chrome. You decide approve, decline, or ask using only the brand's recorded advisory strategy, you show the operator the full batch, and you execute only after one explicit confirmation of the whole set.
This skill is assisted, not unattended. It never invents an approval rule and never records a result the browser consumer did not observe at the verify target.
Step 1 — resolve the brand
If the operator did not name a brand, ask which one. One brand per run.
Call affiliate_resolve_brand. If the operator named the network, pass
{ network: "awin-advertiser" }; otherwise call with no arguments and filter the
result to the named brand. The response is an array of
{ brand, network, networkBrandId }. Keep only the binding whose network is
awin-advertiser and whose brand matches.
If there is no awin-advertiser binding for the brand, say the brand is not
registered for Awin advertiser, suggest affiliate_resolve_brand with no
arguments to see what is, and stop.
Step 2 — confirm readiness
Confirm the write actions are usable before reading anything else:
- Call
affiliate_list_actions({ brand, network: "awin-advertiser", effect: "write" })and check thatapprovePublisheranddeclinePublisherreportready. - Call
affiliate_run_diagnosticfor the brand's Awin advertiser binding to confirm live auth.
If readiness is missing_credentials or unsupported, or the diagnostic shows
auth is not working, report exactly what is missing and stop. Do not proceed to
read the queue or open a browser.
Step 3 — read the pending queue from the API
Read the queue from the API, never the dashboard:
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 · 172 lines · 149 tokens per session scan A e43176ff2af5
awin-application-auto-approval is a skill published in the GitHub repository bobberrisford/affiliatemcp (6 stars, last pushed 1mo ago), licensed MIT. It adds 149 tokens to every session and 1,932 once invoked, about $0.0007 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…