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 programme-performance-reportgit 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/programme-performance-report)<a href="https://agentmods.dev/skills/bobberrisford/affiliatemcp/programme-performance-report"><img src="https://agentmods.dev/badge/skills/bobberrisford/affiliatemcp/programme-performance-report/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/programme-performance-report"><img src="https://agentmods.dev/badge/skills/bobberrisford/affiliatemcp/programme-performance-report.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 | $0.00178 | $0.03735 |
| Opus 5 | $0.00089 | $0.01868 |
| Sonnet 5 | $0.00036 | $0.00747 |
| Haiku 4.5 | $0.00018 | $0.00374 |
Grade A, and why
programme-performance-report 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 9d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operating instructions
You are producing a per-publisher performance report for one brand across the networks it is bound to.
Step 1 — resolve the brand
If the user did not name a brand, ask which one. Do not guess.
Call affiliate_resolve_brand. If the user named a network, pass { network: "<slug>" } to filter; otherwise call with no arguments and filter the result to the brand the user named.
The response is an array of { brand, network, networkBrandId }. Reduce it to the bindings whose brand matches the user's brand. If none remain, tell the user the brand is not registered, suggest affiliate_resolve_brand with no args to see what is, and stop.
Step 1b - load the client's plan (strategy and KPIs)
Call affiliate_get_client_strategy({ brand }). This returns the operator's recorded strategy (prose) and kpi ({ present, targets, parseErrors, ... }). It is advisory context: it changes how you read and frame the numbers; it never authorises any action and never changes what the data says.
- No strategy recorded (
strategy.presentandkpi.presentboth false): this is normal, not an error. Produce the report exactly as you would today on bare deltas, and add one short line offering to record a plan: "No strategy is recorded for [brand]. I can set one up so future reports judge against its targets." Then carry on. - Orphan (
orphan: true): a plan exists but the slug has no binding. Use the prose for framing, but say plainly that the strategy directory has no registered brand binding; do not invent network data for it. - Parse errors (
kpi.parseErrorsnon-empty): report each malformed target line verbatim ("KPI line ignored: ...") and exclude it from every verdict. Never guess what a malformed target meant. - Targets (
kpi.targets): each is{ metric, comparator, value, unit?, period? }. Use them in Step 4 to turn deltas into verdicts. Metrics map onto the data as:revenue-> total grossSale,commission-> total commission,conversions-> total conversions,epc-> commission / clicks when clicks are nonzero,aov-> grossSale / conversions when conversions are nonzero,reversal_rate/approval_rate-> from the status split. If a denominator is zero, report that the derived metric is unavailable rather than inventing zero. - Unsupported per network: if a target names a metric a bound network cannot supply (for example a network with no
get_programme_performance), say so for that network and exclude it from that network's verdict. Do not substitute zero, and do not blend it into a cross-network total without naming the gap.
What ships with it
4 files 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.
- 9d ago First seen · 154 lines · 178 tokens per session scan A 3adadd165fa2
programme-performance-report is a skill published in the GitHub repository bobberrisford/affiliatemcp (6 stars, last pushed 28d ago), licensed MIT. It adds 178 tokens to every session and 3,735 once invoked, about $0.0009 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…