al-build

al-build is a command for Claude Code from javiarmesto/ALDC-AL-Development-Collection. It costs 32 tokens per session (760 once invoked), scanned A, original, MIT.

A command for compiling, packaging, and preparing deployment of AL extensions for Business Central. AL is Microsoft's programming language for customizing its business-management platform.

In plain words
What is it for?
Use it to compile one or several AL projects, create an app package, review compiler errors, and prepare deployment to development or other environments.
Why use it?
It separates local building from publishing and testing, so developers know which tool handles each part and when human approval is needed.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code.

Part of the aldc plugin — 10 commands, 1 hook shipped together

Good fit Use it to compile one or several AL projects, create an app package, review compiler errors, and prepare deployment to development or other environments.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/javiarmesto/aldc-al-development-collection/al-build
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.

Clone the repo
git clone --depth 1 https://github.com/javiarmesto/ALDC-AL-Development-Collection

Made for: Claude Code.

Or install aldc, the plugin that ships this one along with the rest of its 10 commands, 1 hook.

Wrote 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.

agentmods badge for al-build

README.md
[![agentmods](https://agentmods.dev/badge/commands/javiarmesto/aldc-al-development-collection/al-build/github.svg)](https://agentmods.dev/commands/javiarmesto/aldc-al-development-collection/al-build)
Your own site
<a href="https://agentmods.dev/commands/javiarmesto/aldc-al-development-collection/al-build"><img src="https://agentmods.dev/badge/commands/javiarmesto/aldc-al-development-collection/al-build/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.

agentmods 80×15 button for al-build

Your own site · 80×15
<a href="https://agentmods.dev/commands/javiarmesto/aldc-al-development-collection/al-build"><img src="https://agentmods.dev/badge/commands/javiarmesto/aldc-al-development-collection/al-build.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 760 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00032 $0.00760
Opus 5 $0.00016 $0.00380
Sonnet 5 $0.00006 $0.00152
Haiku 4.5 $0.00003 $0.00076

Measured 11d ago against content hash 3e4d2f4b3525, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

al-build 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 11d 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.

claude-plugin/commands/al-build.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build and Deploy AL Extension

Your goal is to build (compile + package) the AL extension for the ${input:DeploymentType} environment and to guide its deployment.

What runs where. In the Claude Code harness you compile and package with the AL command-line tool (ALTool / al) via Bash. ALTool has no publish/test verb — deployment and test runs are VS Code (AL: Publish / AL: Run Tests) or AL-Go/CI pipeline steps. So this command builds the .app and then hands off the deploy with a clear, approved checklist.

Select Deployment Strategy

Inspect the project (Read app.json, Grep/Glob, al-symbols-mcp for dependencies) and select the appropriate deployment strategy. Ask and confirm with the user before proceeding.

Deployment Types

Based on the deployment type, use the appropriate strategy:

Development Environment

  1. Build: Bash: al compile (single project) or al workspace compile (multi-project) to produce the .app
  2. Review: Present compiler results for human approval
  3. Deploy: hand off to VS Code AL: Publish with RAD for rapid iteration (requires approval)
  4. Verify: Read the compiler output for any errors

Testing Environment

  1. Build: Bash: al compile with full validation (read all warnings/errors)
  2. Package: the .app is produced by al compile
  3. Review: Present package details for human approval
  4. Deploy: hand off to VS Code AL: Publish (debugging enabled) or the CI pipeline (requires approval)
  5. Test: ask the human to run VS Code AL: Run Tests (or the CI test runner) and confirm all unit tests pass

Production Environment

  1. Build: Bash: al compile with strict validation
  2. Package: take the release .app produced by al compile
  3. Validation: Verify package integrity and dependencies (app.json + al-symbols-mcp al_packages)
  4. Documentation: Generate deployment checklist and present for review
  5. Human Gate: MANDATORY - Manual approval required before any production action
    • Note: Automated deployment to production is intentionally disabled as safeguard
    • All production changes require explicit human authorization, run through the AL-Go/CI release pipeline or VS Code

Read the full file on GitHub · 67 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. 11d ago First seen · 67 lines · 32 tokens per session scan A 3e4d2f4b3525

Subscribe to this mod's changes

al-build is a command published in the GitHub repository javiarmesto/ALDC-AL-Development-Collection (104 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 760 once invoked, about $0.0002 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.