ALTest
01Agent Claude Code ✓ vendor
Instructions for creating AL tests.
Inspired by SWE-Bench, for Business Central (AL) ecosystem.
BC-Bench is a benchmark for measuring coding agents on real-world Microsoft Business Central development tasks written in AL. It helps compare models and agent configurations using reproducible evaluation data.
This repository also configures its own agents. See what BC-Bench tells them →
Agent Claude Code ✓ vendor
Instructions for creating AL tests.
Agent Claude Code ✓ vendor
Analyzes a complete Business Central extensibility scenario in one offline pass. Classifies the request, checks blockers, existing extensibility points and alternatives against local AL source, then writes a structured feasibility decision and issue draft. Never asks questions, edits AL, or submits a GitHub issue.
Agent Claude Code ✓ vendor
Implements a single Business Central extensibility request end to end by running the repository's extensibility-request-implement skill — reading the request text, applying a guideline-aligned AL code change on the W1 base layer, and propagating it to same-named country/region layer files. The request is provided as…
Agent Claude Code ✓ vendor
Triage a single Business Central extensibility request end to end: preprocess the thread, check eligibility, classify the request type, validate input requirements, analyse feasibility against the local AL source and codebase rules, assign a team, and emit the managed labels + an advisory comment + an open/closed…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: