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_bottleneck_plo02git 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_bottleneck_plo02)<a href="https://agentmods.dev/skills/microsoft/aibast-agents-library/aibast_bottleneck_plo02"><img src="https://agentmods.dev/badge/skills/microsoft/aibast-agents-library/aibast_bottleneck_plo02/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_bottleneck_plo02"><img src="https://agentmods.dev/badge/skills/microsoft/aibast-agents-library/aibast_bottleneck_plo02.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 | $0.00043 | $0.00612 |
| Opus 5 | $0.00022 | $0.00306 |
| Sonnet 5 | $0.00009 | $0.00122 |
| Haiku 4.5 | $0.00004 | $0.00061 |
Grade A, and why
constraining-station-identification 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Constraining station identification
Use this skill for constraint questions such as "Where is the bottleneck on each line, and which station should the plant team address first?", "what is slowing each line," or "which station is over takt." Evaluate all three lines.
Inputs (from the packaged synthetic records)
For each line read the per-station table: station name/ID, cycle time, takt time, delta (cycle − takt), and defect rate; plus the defect category mix.
Procedure
- For each line, the constraining station is the one with the longest cycle
time. Fixed results:
- Electronics Assembly Line A → Functional Test (A5), 25.3s vs 20.0s takt, +5.3s over takt (26.5%), defect 0.04%.
- Metal Fabrication Line B → Robotic Welding (B3), 14.2s vs 12.0s takt, +2.2s over takt (18.3%), defect 0.30%.
- Polymer Molding Line C → Injection Molding (C2), 18.4s vs 15.0s takt, +3.4s over takt (22.7%), defect 0.45%.
- Present each line's full station table with the delta column and the bottleneck flagged, so the evidence supports the pick.
- Add the top defect categories per line as supporting evidence (e.g., LINE-C: short_shot 35%, flash 25%, sink_mark 20%).
- Recommend which station to address first across the plant: Functional Test (A5) first because its 26.5% over-takt margin is the largest, then Injection Molding (C2), then Robotic Welding (B3).
Output
Per-line: the named constraining station with cycle/takt/over-takt and defect rate, then the supporting station table and defect mix. Close with the cross-plant "address first" recommendation.
Grounding and safety
- Use only the packaged station figures; never invent stations or numbers.
- Recommend only; never reconfigure or stop a station.
- Never say you lack access and never ask the user to name a line.
- End with:
> Synthetic pilot data; figures are planning estimates, not a live ERP, IoT, or Power BI reading.
Fallback
If the user asks about a station or line not in the records, say it is not in the pilot and list the known stations for the relevant line.
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 · 53 lines · 43 tokens per session scan A 4e1ea255ac31
constraining-station-identification is a skill published in the GitHub repository microsoft/aibast-agents-library (7 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 612 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…