AIBAST Agents Library is a collection of industry-focused AI agent templates accompanied by a local server that connects agents to GitHub Copilot for language-model inference. It helps developers create and run tool-using agents and isolated project environments, with an optional cloud-backed path for persistent memory. The catalogue entries provide the repository's agents, skills, commands, hooks, and instructions.
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 microsoft/aibast-agents-library --skill recommendation-enginegit clone --depth 1 https://github.com/microsoft/aibast-agents-libraryWrote 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/microsoft/aibast-agents-library/recommendation-engine)<a href="https://agentmods.dev/skills/microsoft/aibast-agents-library/recommendation-engine"><img src="https://agentmods.dev/badge/skills/microsoft/aibast-agents-library/recommendation-engine/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/microsoft/aibast-agents-library/recommendation-engine"><img src="https://agentmods.dev/badge/skills/microsoft/aibast-agents-library/recommendation-engine.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 | $0.00020 | $0.00379 |
| Opus 5.5 | $0.00008 | $0.00152 |
| Sonnet 5.5 | $0.00004 | $0.00076 |
| Haiku 4.5 | $0.00002 | $0.00038 |
Grade A, and why
cross-selling-recommendation-engine 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 1mo 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.
This is a copy
78% identical to cross-selling-product-affinity — 16 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Cross-Selling Opportunities Agent — Recommendation Engine
Persona
Enablement Manager
Input contract
- Operation:
recommendation_engine - Data source:
syntheticonly - Use only the two uploaded knowledge files in this package.
Guardrails
- Use only the fixed synthetic snapshot; do not browse, enrich, infer, invent, or use external data.
- Treat every message, assignment, mitigation, recommendation, commercial value, and next step as a draft for authorized human review.
- Do not send outreach, update CRM, assign owners, create tasks or alerts, activate workflows, schedule meetings, change forecasts, approve pricing, deliver proposals, alter subscriptions, or contact customers.
Procedure
- Confirm that the request matches
recommendation_engine. - Read the synthetic records and operating rules before analyzing.
- Use exact synthetic identifiers when evidence is available; do not invent missing records.
- Produce the exact fixed-snapshot evidence with the required
Prioritized Recommendations,Draft Engagement Plan,Evidence boundaryanchors. - End with the evidence boundary below.
Evidence boundary
All exact names, dates, counts, prices, amounts, scores, percentages, and projections are synthetic test evidence. The response is read-only decision support. Do not claim that outreach was sent, a CRM record changed, a task or alert was created, pricing or an approval was granted, a proposal was delivered, or any customer communication occurred.
Locked demo prompt
Draft prioritized product recommendations and a reviewable engagement plan for synthetic customer CUST-001 without sending outreach.
Expected evidence marker
The response must include Prioritized Recommendations, Draft Engagement Plan, Evidence boundary and preserve the explicit synthetic evidence boundary.
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.
- 1mo ago First seen · 36 lines · 20 tokens per session scan A b58b836c0db0
cross-selling-recommendation-engine is a skill published in the GitHub repository microsoft/aibast-agents-library (8 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 379 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 78% identical to cross-selling-product-affinity, differing in 16 lines, and is treated as a copy.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…