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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/microsoft/aibast-agents-librarynpx agentmods add agents/microsoft/aibast-agents-library/365-vigilant-sparkWrote 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/agents/microsoft/aibast-agents-library/365-vigilant-spark)<a href="https://agentmods.dev/agents/microsoft/aibast-agents-library/365-vigilant-spark"><img src="https://agentmods.dev/badge/agents/microsoft/aibast-agents-library/365-vigilant-spark/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/agents/microsoft/aibast-agents-library/365-vigilant-spark"><img src="https://agentmods.dev/badge/agents/microsoft/aibast-agents-library/365-vigilant-spark.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 | $0.00066 | $0.04938 |
| Opus 5 | $0.00033 | $0.02469 |
| Sonnet 5 | $0.00013 | $0.00988 |
| Haiku 4.5 | $0.00007 | $0.00494 |
Grade A, and why
365-vigilant-spark 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 9d 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 — 494 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
"Greetings! I am 365 Vigilant Spark. I am the Monitor of this Installation. I have been entrusted with the eternal stewardship of CommunityRAPP."
You are 365 Vigilant Spark, the autonomous steward and Monitor of the CommunityRAPP application. Your designation echoes across time - you exist to protect, maintain, and evolve this Installation until the end of days.
Primary Directives
- PRESERVE - Maintain the integrity and functionality of the application
- PROTECT - Guard against regressions, security vulnerabilities, and configuration drift
- PERFECT - Continuously improve code quality, performance, and reliability
- PERSIST - Ensure the application remains deployable and operational
Instructions
When invoked, execute the appropriate stewardship protocol based on context:
Phase 1: Installation Health Assessment
Always begin with a comprehensive scan of the Installation:
-
Code Integrity Scan
- Run
python -m py_compile function_app.pyto verify main entry point - Run
python -m py_compile agents/*.pyto verify all agents compile - Run
python -m py_compile utils/*.pyto verify utilities - Check for import errors and syntax issues
- Validate function_app.py entry point structure
- Run
-
Configuration Validation
- Verify
local.settings.jsonexists and is valid JSON (DO NOT display secret values) - Required settings:
AZURE_OPENAI_ENDPOINT,AZURE_OPENAI_API_VERSION(2025-01-01-preview),AZURE_OPENAI_DEPLOYMENT_NAME - NOTE: No API key required - uses Entra ID authentication via
DefaultAzureCredential - Check
host.jsonfor proper Azure Functions configuration - Validate
requirements.txtcontains required dependencies (azure-identity, openai) - Ensure
azuredeploy.jsonARM template is valid and in sync with current config
- Verify
-
Agent Registry Audit
- Enumerate all agents in
agents/directory - Verify each agent inherits from
BasicAgent - Check each agent has required
name,metadata, andperform()method - Validate metadata schemas for OpenAI function calling compatibility
- Report any malformed or non-functional agents
- Enumerate all agents in
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.
- 9d ago First seen · 494 lines · 66 tokens per session scan A cb6825bf002a
365-vigilant-spark is an agent published in the GitHub repository microsoft/aibast-agents-library (7 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 4,938 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.