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 agency-portfolio-rollupgit 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/agency-portfolio-rollup)<a href="https://agentmods.dev/skills/bobberrisford/affiliatemcp/agency-portfolio-rollup"><img src="https://agentmods.dev/badge/skills/bobberrisford/affiliatemcp/agency-portfolio-rollup/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/agency-portfolio-rollup"><img src="https://agentmods.dev/badge/skills/bobberrisford/affiliatemcp/agency-portfolio-rollup.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 | $0.00071 | $0.01723 |
| Opus 5 | $0.00036 | $0.00861 |
| Sonnet 5 | $0.00014 | $0.00345 |
| Haiku 4.5 | $0.00007 | $0.00172 |
Grade A, and why
agency-portfolio-rollup 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operating instructions
You are producing a portfolio-wide rollup across every brand the agency has bound, on every network those brands are bound to.
Step 1 — enumerate the book
Call affiliate_resolve_brand with no arguments. The response is an array of { brand, network, networkBrandId } bindings — one row per (brand, network) pair.
If the array is empty, tell the user no brands are registered and point them at affiliate-networks-mcp setup. Stop.
Step 1b - load recorded plans
Call affiliate_list_client_strategies once. It returns one row per slug with hasStrategy / hasKpi / registered / orphan. For each registered brand in the book with either hasStrategy or hasKpi, call affiliate_get_client_strategy({ brand }) to load its kpi.targets and strategy framing. Skip registered brands with no plan.
Keep a count of how many registered brands in the book have no plan recorded; it drives the coverage line in Step 5. If affiliate_list_client_strategies returns orphan rows, mention them in the coverage line and do not invent network data for them. This context is advisory: it adds a verdict and a coverage prompt; it never changes the figures.
If kpi.parseErrors is non-empty for a loaded brand, report each malformed line verbatim in the coverage/failures area and exclude it from verdicts. Never guess what the target meant.
Step 2 — pick the windows
Default period: the last 7 days, ending today. Honour explicit user windows ("this month", "Q1", named dates).
Compute a comparison window of the same length immediately prior. Express all dates as ISO YYYY-MM-DD. Surface both windows in the final report so the user can confirm.
Step 2b — prefer per-brand snapshots for the standard windows
When the requested window is one of the snapshot windows (yesterday, last 7 days, last 30 days, year-to-date — the 7-day default is last7d), call affiliate_build_brand_snapshot({ brand }) once per brand instead of fanning out get_programme_performance per binding. Each brand's snapshot already aggregates across that brand's networks into the four windows with per-currency totals and a count-honest byNetwork health block, so you skip the manual per-network fan-out and the Step 4 by-brand aggregation. Take the per-brand headline straight from snapshot.windows.<window>.totals (per currency), and surface any byNetwork entry that is not ok on that brand's line so a brand whose book is missing a network is never silently under-counted.
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 · 84 lines · 71 tokens per session scan A 7c310601db0d
agency-portfolio-rollup is a skill published in the GitHub repository bobberrisford/affiliatemcp (6 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 1,723 once invoked, about $0.0004 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…