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.
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/BC-Bench --skill al-test-generationgit 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/skills/microsoft/bc-bench/al-test-generation)<a href="https://agentmods.dev/skills/microsoft/bc-bench/al-test-generation"><img src="https://agentmods.dev/badge/skills/microsoft/bc-bench/al-test-generation/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/bc-bench/al-test-generation"><img src="https://agentmods.dev/badge/skills/microsoft/bc-bench/al-test-generation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00043 | $0.00658 |
| Opus 5.5 | $0.00017 | $0.00263 |
| Sonnet 5.5 | $0.00009 | $0.00132 |
| Haiku 4.5 | $0.00004 | $0.00066 |
Grade A, and why
al-test-generation 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
To create AL tests for Microsoft Dynamics 365 Business Central, follow this process:
1. Analyze the Code Under Test
Before writing any test code:
- Read and understand the procedure or functionality being tested
- Trace through all code paths to identify UI interactions
- Examine table definitions for TableRelation constraints
2. Identify Required Handler Methods
CRITICAL: Tests fail with "Unhandled UI" errors when handlers are missing.
Look for these patterns in the code under test:
| Code Pattern | Required Handler |
|---|---|
Confirm() |
[ConfirmHandler] |
Message() |
[MessageHandler] |
StrMenu() |
[StrMenuHandler] |
Page.Run() |
[PageHandler] |
Page.RunModal() |
[ModalPageHandler] |
Report.Run() or Report.RunModal() |
[ReportHandler] |
| Report request page | [RequestPageHandler] |
Hyperlink() |
[HyperlinkHandler] |
Notification.Send() |
[SendNotificationHandler] |
3. Analyze TableRelation Constraints
CRITICAL: Tests fail with validation errors when inserting data that violates TableRelation constraints.
Before inserting test data:
- Read the table definition for all fields receiving values
- Identify fields with
TableRelationproperties - Ensure related records exist before inserting test data
- Use Library functions (e.g.,
LibrarySales,LibraryPurchase) to create prerequisite data
4. Write Test Structure
Follow the AAA pattern (Arrange-Act-Assert):
[Test]
[HandlerFunctions('RequiredHandlers')]
procedure TestProcedureName()
begin
// [GIVEN] Setup test data and preconditions
Initialize();
CreateTestData();
// [WHEN] Execute the action being tested
ExecuteAction();
// [THEN] Verify the expected results
VerifyResults();
end;
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 · 94 lines · 43 tokens per session scan A 15b1e4dfa461
al-test-generation is a skill published in the GitHub repository microsoft/BC-Bench (57 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 658 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 2026-08-30.
Other skills, from other repositories
skill-testing
AL test development patterns for Business Central. Use when creating test codeunits, writing Given/When/Then test procedures, using Library Assert, configuring test projects, or implementing TDD workflows.
aldc
Use canonical ALDC architecture, implementation, TDD orchestration, review and specification workflows for AL / Business Central projects.
conduct
AL Conductor Agent - Orchestrates Planning → Implementation → Review → Commit cycle for AL Development. Enforces TDD and quality gates for Business Central extensions. Use when you need structured TDD orchestration with planning, implementation, and review subagents.
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.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
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".