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_vendor-comparison_02git 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_vendor-comparison_02)<a href="https://agentmods.dev/skills/microsoft/aibast-agents-library/aibast_vendor-comparison_02"><img src="https://agentmods.dev/badge/skills/microsoft/aibast-agents-library/aibast_vendor-comparison_02/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_vendor-comparison_02"><img src="https://agentmods.dev/badge/skills/microsoft/aibast-agents-library/aibast_vendor-comparison_02.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 | $0.00023 | $0.00811 |
| Opus 5.5 | $0.00009 | $0.00324 |
| Sonnet 5.5 | $0.00005 | $0.00162 |
| Haiku 4.5 | $0.00002 | $0.00081 |
Grade A, and why
vendor-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 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.
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.
Vendor evidence comparison
Use when a category buyer wants a neutral view of synthetic vendor ratings, terms, and tiers.
Procedure
- Use this uploaded
vendor-comparisonskill withaibast_procurement-agent-synthetic-records.mdandaibast_procurement-agent-rules-and-guardrails.md. Retrieve and cite both. - Compare only the user's requested scope, not unrelated catalog vendors.
For the cloud-vendor request, compare only the
Cloud Infrastructurerows:AWSandAzure. - Keep ratings, tiers, contract status and contact roles as exact source labels.
The rating scale, methodology and statistical significance are not supplied.
Do not add a denominator, normalize ratings or claim a meaningful rating gap.
Do not claim normal variance or qualification outcomes.
Strategicdoes not prove passed qualification or enterprise approval. The user's word "approved" does not change the recorded labels. - Contact roles do not establish service focus or guarantees. Annual spend is not commitment volume. Do not invent service entitlements, contract assurances or a causal explanation for spend differences.
- Payment terms are supplied; do not describe all contract terms as absent.
Full agreements, detailed service commitments and pricing schedules are not
supplied. Distinguish those gaps from supplied payment terms,
Activecontract-status labels, tier labels and contact roles. - Do not pick a winner. Name missing evidence and preserve the unresolved authorized human reviews in the common rules. Do not invent an approver for unspecified spend.
Required response contract
Use these headings in order, with exact wording and capitalization. Populate each section from the retrieved source.
# Vendor Comparison
## Vendor Tiers
- Under
Vendor Comparison, use a side-by-side table for the in-scope vendors. Include each vendor's name, ID, category, contract status, tier, rating, annual spend, payment terms and contact role exactly as recorded. - Under
Vendor Tiers, report the in-scope source tier labels and state that qualification outcomes are not supplied. Identify rating and service evidence limits without inferring a winner or reclassifying the vendors. - Before sending, check every missing-evidence claim against supplied fields.
AWSandAzureboth have suppliedNet 30payment terms. - Before the final footer, include exactly:
Ratings and terms are comparison evidence only; this is not a supplier award.
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 Changed · +58 lines 6c8e18cd5935
- 1mo ago First seen · 26 lines · 23 tokens per session scan A 703ab42f368a
vendor-comparison is a skill published in the GitHub repository microsoft/aibast-agents-library (8 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 811 once invoked, about $0.0001 per session on Opus 5.5. 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
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
twitter-reader
Read Twitter/X for financial research through opencli: the user's home timeline, tweet search, trending topics, bookmarks, a user's recent tweets, threads, articles, profiles, followers and following, and notifications. Use this skill whenever the user wants to know what people are saying on Twitter/X or fintwit about…
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
energy-procurement
Codified expertise for electricity and gas procurement, tariff optimization, demand charge management, renewable PPA evaluation, and multi-facility energy cost management. Informed by energy procurement managers with 15+ years experience at large commercial and industrial consumers. Includes market structure analysis…
airdrop-hunting-guide
Guide to finding and qualifying for crypto airdrops — eligibility criteria, farming strategies, on-chain activity requirements, Sybil detection avoidance, and tracking tools. Use when helping users understand airdrops, check eligibility, or plan participation strategies.
recipe-daily-pnl-report
Generate a daily profit and loss summary from trades and balances.