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.
Borrowing it
Nothing to install: this file belongs to microsoft/BC-Bench. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/microsoft/BC-Bench/main/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/microsoft/BC-BenchWrote 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/instructions/microsoft/bc-bench/copilot-instructions)<a href="https://agentmods.dev/instructions/microsoft/bc-bench/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/microsoft/bc-bench/copilot-instructions/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/instructions/microsoft/bc-bench/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/microsoft/bc-bench/copilot-instructions.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 | $0.00996 | $0.00996 |
| Opus 5.5 | $0.00398 | $0.00398 |
| Sonnet 5.5 | $0.00199 | $0.00199 |
| Haiku 4.5 | $0.00100 | $0.00100 |
Grade A, and why
BC-Bench copilot-instructions.md 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 17d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository: microsoft/BC-Bench
This is a benchmark for evaluating coding agents on real-world Business Central (AL) development tasks, inspired by SWE-Bench. Unlike traditional model benchmarks, BC-Bench is designed to help select models and rapidly iterate on mcp servers, custom instruction/agents, etc for engineers. The repository contains:
- Dataset: Benchmark entries following SWE-Bench schema with BC-specific adjustments
- Python Package (
src/bcbench/): CLI tools, agent implementations, and validation utilities - Core Library (
packages/bcbench-core/): Reusable, distributable evaluation library consumed bybcbench; must never importbcbench, read environment variables, or contain BC-Bench policy - PowerShell Scripts (
scripts/): Environment setup and dataset verification using AL-GO/BCContainerHelper - Tools (
tools/): Ad-hoc scripts for GitHub Artifacts download, etc - Agent Evaluations: Focuses on GitHub Copilot CLI and Claude Code
- Experiments: MCP Servers, custom instructions, custom agents, skills, etc. and their performance on the benchmark
- Notebooks (
notebooks/): Analysis and visualization of benchmark results
Key Context
- Primary language: Python (with AL/Business Central as the target evaluation language)
- Uses
uvfor dependency management: e.g.uv add <package>to add packages,uv run <command>to run commands - Uses
pre-commitfor code quality checks (ruff linting/formatting, trailing whitespace, etc.)
Categories
BC-Bench is category-based and designed to grow over time. It currently has two categories, bug-fix and test-generation. They share the same dataset tasks and execution-based setup, but use different prompts, expected outputs, and evaluation pipelines. Future categories such as code-review can be added within the same overall benchmark structure, though they may require different inputs, setup, or evaluation methods.
Coding Patterns and Guidelines
- Prefer strong typing and type hints
- Prefer simple code for fast iteration
- Prefer modular, testable components
- Prefer pure functions where possible
- Prefer explicit over implicit
- Prefer designs where invalid states are unrepresentable
- Prefer high-order functions like map, filter, reduce over loops
- Prefer immutable data structures where possible
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.
- 17d ago Changed · +3 lines · +106 tokens per session b28e82671b90
- 1mo ago Changed · +1 lines · +11 tokens per session 4aa05f2334c6
- 1mo ago First seen · 66 lines · 879 tokens per session scan A 6a7e82c11e64
BC-Bench copilot-instructions.md is an instructions file published in the GitHub repository microsoft/BC-Bench (58 stars, last pushed today), licensed MIT. It adds 996 tokens to every session, about $0.0040 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 2026-08-30.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.