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 aibast_throughput-options_plo03git 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/aibast_throughput-options_plo03)<a href="https://agentmods.dev/skills/microsoft/aibast-agents-library/aibast_throughput-options_plo03"><img src="https://agentmods.dev/badge/skills/microsoft/aibast-agents-library/aibast_throughput-options_plo03/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/aibast_throughput-options_plo03"><img src="https://agentmods.dev/badge/skills/microsoft/aibast-agents-library/aibast_throughput-options_plo03.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 | $0.00035 | $0.00890 |
| Opus 5 | $0.00017 | $0.00445 |
| Sonnet 5 | $0.00007 | $0.00178 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
improvement-option-comparison 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 6d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Improvement option comparison
Use this skill for requests such as "Give me the practical options to improve throughput without hiding the quality tradeoffs," "how do we raise output," or "what are our response paths." Always present three options per line and keep the quality tradeoff explicit.
Inputs (from the packaged synthetic records)
Per line: the throughput gap (uph), the bottleneck station and its cycle/takt, and the highest-defect station. Use the precomputed option figures in the rules reference.
Procedure
For each line, present exactly three labeled options and keep quality visible:
- Option 1 — Reduce the bottleneck cycle time (process re-engineering, tooling upgrade). Target cycle = takt × 0.95; expected gain = round(gap × 0.6).
- Option 2 — Add a parallel station at the bottleneck. Effective cycle = bottleneck cycle / 2; expected gain = round(gap × 0.85); investment estimate $45,000 – $120,000.
- Option 3 — Quality improvement at the highest-defect station (reduce rework loop and scrap); expected gain = round(gap × 0.2). Never drop this option — it is how the quality tradeoff stays visible.
Then state the combined projected operating score = round(current OEE × 1.12).
Precomputed results to use
- Electronics Assembly Line A (gap 38 uph): Option 1 Functional Test 25.3s → 19.0s, +23 uph; Option 2 parallel Functional Test 12.7s, +32 uph, $45,000 – $120,000; Option 3 quality at Final Assembly (0.18%), +8 uph; combined 79.4% (from 70.9%).
- Metal Fabrication Line B (gap 39 uph): Option 1 Robotic Welding 14.2s → 11.4s, +23 uph; Option 2 parallel Robotic Welding 7.1s, +33 uph, $45,000 – $120,000; Option 3 quality at Robotic Welding (0.30%), +8 uph; combined 96.1% (from 85.8%).
- Polymer Molding Line C (gap 72 uph): Option 1 Injection Molding 18.4s → 14.2s, +43 uph; Option 2 parallel Injection Molding 9.2s, +61 uph, $45,000 – $120,000; Option 3 quality at Injection Molding (0.45%), +14 uph; combined 76.2% (from 68.0%).
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.
- 6d ago First seen · 77 lines · 35 tokens per session scan A a9ed0cc962bc
improvement-option-comparison is a skill published in the GitHub repository microsoft/aibast-agents-library (7 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 890 once invoked, about $0.0002 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 2026-09-03.
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…