aibast-agents-library copilot-instructions.md

Project-specific instructions for developing and testing the AIBAST Agents Library, a collection of AI agents and its supporting deployment components.

In plain words
What is it for?
Use them when changing, testing, deploying, or explaining parts of the AIBAST Agents Library and its beta educational tool.
Why use it?
They give the agent the repository’s architecture, development path, and rules for working with the local server, Azure deployment, and Copilot integrations.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/microsoft/aibast-agents-library/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/microsoft/aibast-agents-library

Made for: GitHub Copilot.

Per session 2,251 This file is loaded in full into every session.
When invoked 2,251 The same file — it is already loaded in full.
Security scan C 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.02251 $0.02251
Opus 5 $0.01125 $0.01125
Sonnet 5 $0.00450 $0.00450
Haiku 4.5 $0.00225 $0.00225

Measured 3d ago against content hash 951dc982d885, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

aibast-agents-library copilot-instructions.md scanned grade C with 2 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 3d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -s localhost:7071/health | python3 -m json.tool

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s localhost:7071/health | python3 -m json.tool
.github/copilot-instructions.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Instructions — AIBAST Agents Library

Architecture

AIBAST Agents Library is the stable Microsoft downstream for the RAPP stack (see CONSTITUTION.md for architectural principles):

  1. Brainstem (rapp_brainstem/) — The core. A local-first Flask server (Python 3.11) using GitHub Copilot's API for LLM inference. No API keys needed — just gh auth login. This is where all development happens.
  2. Spinal Cord (azuredeploy.json, deploy.sh) — Azure deployment. ARM template creates Function App, Azure OpenAI, Storage, App Insights. All Entra ID auth.
  3. Nervous System (MSFTAIBASMultiAgentCopilot_*.zip) — Power Platform solution for Copilot Studio. Connects the Azure Function to Teams and M365 Copilot.

The repository also owns agents/@aibast-agents-library/, registry.json, build_registry.py, rapp_ai/, the production guide, and Microsoft governance files. These are not upstream Grail mirrors.

Product Golden Path

Read beta/GOLDEN_PATH.md before changing the beta. The beta is a chat-driven educational tool: users learn AI by watching GitHub Copilot build, hotload, run, test, explain, screenshot, and record real RAPP capabilities. External AIs can visibly drive the same Brainstem or Brain Surgeon chat to keep users unstuck.

Preserve these invariants:

  • unchanged Grail brainstem.py and exact RAPP/1 chat wire;
  • global + routed agents composed into isolated hardlinked AGENTS_PATH workers;
  • visible Explorer, Copilot Brain Surgeon, Brainstem execution, and evidence;
  • VS Code/terminal remain optional expert surfaces;
  • portable skills promote into Hippocampus and Microsoft downstream hosts without rewriting the agent or chat contract.

Brainstem internals

brainstem.py is the single-file server containing auth, agent orchestration, the tool-calling loop, and all HTTP endpoints.

Tool-calling loop (/chat, /chat/stream): Builds messages from soul + conversation history, then runs up to 3 rounds of LLM calls. Each round checks for tool_calls, executes matching agents via run_tool_calls(), appends tool results, and loops. The streaming route returns server-sent events and does not replay an accepted request after interruption.

Read the full file on GitHub · 153 lines

Changes

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.

  1. 3d ago First seen · 153 lines · 2,251 tokens per session scan C 951dc982d885

Subscribe to this mod's changes

aibast-agents-library copilot-instructions.md is an instructions file published in the GitHub repository microsoft/aibast-agents-library (7 stars, last pushed 3d ago), licensed MIT. It adds 2,251 tokens to every session, about $0.0113 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens