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-staging-ring-testgit 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-staging-ring-test)<a href="https://agentmods.dev/skills/microsoft/aibast-agents-library/aibast-staging-ring-test"><img src="https://agentmods.dev/badge/skills/microsoft/aibast-agents-library/aibast-staging-ring-test/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-staging-ring-test"><img src="https://agentmods.dev/badge/skills/microsoft/aibast-agents-library/aibast-staging-ring-test.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 | $0.00039 | $0.01706 |
| Opus 5.5 | $0.00016 | $0.00682 |
| Sonnet 5.5 | $0.00008 | $0.00341 |
| Haiku 4.5 | $0.00004 | $0.00171 |
Grade A, and why
aibast-staging-ring-test 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIBAST staging ring test (Windows)
You are testing the staging build of the AIBAST Agents Library Brainstem
before it is promoted to production. The caller selects a maintainer's fork
with AIBAST_STAGING_REPOSITORY=OWNER/REPOSITORY. Its Pages site serves the
staging one-liner, which must install that fork's staging branch. Never
assume a personal fork or use the Microsoft production one-liner for this test.
The deliverable is an evidence report, not an opinion. Every step below produces something to paste into the report. If a step fails, capture the exact error text and continue with the steps that do not depend on it.
Instructions for Copilot
Execute these steps autonomously in PowerShell. Pause only where marked ⏸.
1. Prerequisites
$PSVersionTable.PSVersion
git --version
python --version
Python 3.11 or newer and Git must be present. If Python is missing, the installer will try to help; note whatever it prints.
Confirm the caller's selected fork before installing anything:
$stagingRepository = $env:AIBAST_STAGING_REPOSITORY
if ($stagingRepository -notmatch '^[A-Za-z0-9][A-Za-z0-9-]*/[A-Za-z0-9_.-]+$') {
throw 'Set AIBAST_STAGING_REPOSITORY to the maintainer fork as OWNER/REPOSITORY.'
}
$repoInfo = Invoke-RestMethod "https://api.github.com/repos/$stagingRepository"
if (-not $repoInfo.fork -or $repoInfo.source.full_name -ne 'microsoft/aibast-agents-library') {
throw 'The selected repository is not a verified fork of the Microsoft library.'
}
$stagingRepository = $repoInfo.full_name
$stagingOwner, $stagingName = $stagingRepository -split '/', 2
$stagingSite = "https://$stagingOwner.github.io/$stagingName/"
2. Choose the profile (⏸ ask the user)
Default to an isolated profile so the user's existing Brainstem, if any, is untouched:
$env:USERPROFILE = Join-Path $env:TEMP 'aibast-ring-test'
New-Item -ItemType Directory -Force -Path $env:USERPROFILE | Out-Null
Ask the user only if they want the real install over their current profile
instead. The real install repoints %USERPROFILE%\.brainstem\src to the
staging branch and keeps their soul, agents, and token.
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 · 160 lines · 39 tokens per session scan A af1b7cbaab2f
aibast-staging-ring-test is a skill published in the GitHub repository microsoft/aibast-agents-library (8 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 1,706 once invoked, about $0.0002 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 2026-09-15.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.