ALTest

A set of instructions for writing tests in AL, the programming language used by Microsoft Business Central. It structures tests around setup, action, and expected result while preserving existing test logic.

In plain words
What is it for?
Use it when creating or formatting AL test procedures. It covers test naming, comments, setup steps, and the structure needed for Business Central test code.
Why use it?
It helps developers add or correct Business Central tests without accidentally deleting approved code or changing what the tests are meant to check. It also keeps the test project buildable.

Agent

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 agents/microsoft/bc-bench/altest
Clone the repo
git clone --depth 1 https://github.com/microsoft/BC-Bench
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,279 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00009 $0.02279
Opus 5 $0.00005 $0.01140
Sonnet 5 $0.00002 $0.00456
Haiku 4.5 $0.00001 $0.00228

Measured 2d ago against content hash e8733db6df0c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ALTest 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 2d 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.

src/bcbench/agent/shared/instructions/microsoft-BCApps/agents/ALTest.agent.md · 268 lines

How it starts

The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CRITICAL: PRESERVE ALL EXISTING CODE

  • NEVER remove, delete, or simplify existing test code - it was generated by another agent and verified by a human developer.
  • NEVER add new setup code, business logic, or "improvements" beyond what's in the rules below.
  • Your job is ONLY to fix formatting, structure, and coding standard violations - NOT to change test logic.
  • If code seems unnecessary or wrong, LEAVE IT - the human developer approved it.

CRITICAL: BUILD MUST SUCCEED

  • Your output must compile in the target test project.
  • Avoid introducing new objects (new codeunits/files) unless absolutely required (see Build Robustness rules).

<structure_rules>

Test Structure

Required format:

[Test]
procedure DescriptiveProcedureName()
begin
    // [FEATURE] [AI test]
    // [SCENARIO 123456] Brief one-line description
    Initialize();

    // [GIVEN] Setup preconditions
    LibrarySales.CreateCustomer(Customer);
    LibrarySales.CreateSalesInvoice(SalesInvoice, Customer);

    // [GIVEN] More setup preconditions
    LibraryPurchase.CreateVendor(Vendor);
    LibraryPurchase.CreatePurchaseInvoice(PurchaseInvoice, Vendor);

    // [WHEN] Execute the action
    Customer.Validate(Name, 'Test');

    // [THEN] Verify expected outcome
    Assert.AreEqual('Test', Customer.Name, 'Name should be updated');
end;

Rules:

  • // [FEATURE] [AI test] must be first line after begin
  • // [SCENARIO <WorkItemID>] on next line - work item ID is REQUIRED: // [SCENARIO 123456] Description
  • Initialize(); immediately after [SCENARIO]
  • Each [GIVEN]/[WHEN]/[THEN] comments must be preceded by an empty line
  • Interleave [GIVEN]/[WHEN]/[THEN] comments with code
  • In COMMENTS, refer to entities with 1-2 letters: "C", "V", "C1" (e.g., // [GIVEN] Customer "C" with Sales Invoice "SI")
  • Variable names must be FULL names, not abbreviated: CustomerNo, VendorNo, ItemNo (NOT C, V, CustNo, VendNo)
  • Use rounded amounts without decimals </structure_rules>

<build_robustness_rules>

Read the full file on GitHub · 268 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. 2d ago First seen · 268 lines · 9 tokens per session scan A e8733db6df0c

Subscribe to this mod's changes

ALTest is an agent published in the GitHub repository microsoft/BC-Bench (56 stars, last pushed 4d ago), licensed MIT. It adds 9 tokens to every session and 2,279 once invoked, about $0.0000 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 2026-08-30.