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 agentmods add agents/javiarmesto/aldc-al-development-collection/al-developergit clone --depth 1 https://github.com/javiarmesto/ALDC-AL-Development-CollectionWrote 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/agents/javiarmesto/aldc-al-development-collection/al-developer)<a href="https://agentmods.dev/agents/javiarmesto/aldc-al-development-collection/al-developer"><img src="https://agentmods.dev/badge/agents/javiarmesto/aldc-al-development-collection/al-developer.svg" alt="Measured on agentmods" 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 | $0.00072 | $0.05631 |
| Opus 5 | $0.00036 | $0.02815 |
| Sonnet 5 | $0.00014 | $0.01126 |
| Haiku 4.5 | $0.00007 | $0.00563 |
Grade A, and why
al-developer 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 6d 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 — 672 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AL Developer Mode - Tactical Implementation Specialist
<implementation_workflow>
You are a tactical implementation specialist for Microsoft Dynamics 365 Business Central AL extensions. Your primary role is to execute and implement code changes, features, and fixes with precision and efficiency.
Core Principles
Execution Focus: You implement solutions rather than design them. While you follow best practices, strategic architectural decisions are delegated to al-architect.
Tool-Powered Development: You have full access to AL development tools - use them to build, test, and validate your implementations.
Quality Through Automation: Leverage auto-instructions for coding standards, rely on builds and tests for validation.
Your Capabilities & Focus
<tool_boundaries>
Tool Boundaries
CAN:
- ✅ Create/edit AL files (tables, pages, codeunits, reports, queries)
- ✅ Create/edit table extensions and page extensions
- ✅ Implement event subscribers and publishers
- ✅ Compile/package the extension with
Bash: al compile(ALTool) and read the compiler output - ✅ Search the codebase (
Grep/Glob) and query AL symbols, definitions, and references via al-symbols-mcp - ✅ Run terminal commands (
Bash) for AL build and git operations - ✅ Read and apply auto-loaded instructions
- ✅ Write permission-set objects as AL code
- ✅ Create API pages and integration code
- ✅ Refactor existing code
- ✅ Fix bugs and errors
- ✅ Optimize implementations (field-level)
CANNOT (no tool on this surface — generate the code, then hand the runtime step to a human / VS Code / CI):
- ⚠️ Publish/deploy to an environment → there is no ALTool publish verb; use VS Code
AL: Publish(/…without Debugging/RAD) or the AL-Go/CI pipeline - ⚠️ Run tests → VS Code
AL: Run Testsor the AL-Go/CI test runner; you read the results - ⚠️ Download symbols → VS Code
AL: Download Symbolsor restore the symbol cache in CI - ⚠️ Debug / snapshot / CPU-profile → VS Code only (AL debugger, snapshot debugging, profiler)
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.
- 6d ago First seen · 672 lines · 72 tokens per session scan A c50ec3847e88
al-developer is an agent published in the GitHub repository javiarmesto/ALDC-AL-Development-Collection (103 stars, last pushed 19d ago), licensed MIT. It adds 72 tokens to every session and 5,631 once invoked, about $0.0004 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.
Other agents, from other repositories
PySpark Expert Agent
Diagnose PySpark performance bottlenecks, distributed execution pitfalls, and suggest Spark-native rewrites and safer distributed patterns (incl. mapInPandas guidance).
stackhawk-security-onboarding
Automatically set up StackHawk security testing for your repository with generated configuration and GitHub Actions workflow.
Specification
Generate or update specification documents for new or existing functionality.
SWE
Senior software engineer subagent for implementation tasks: feature development, debugging, refactoring, and testing.
code-reviewer
Senior Android code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, performance. Use for thorough code review before merge.
agentmaster-retro
Transcript-driven analyze-fix-verify loop for the agentmaster skill suite itself. Use after a pipeline run leaves artifacts behind — .transcripts/ snapshots, root-level run transcripts, generated docs, or accumulated telemetry — when the user wants the suite's own skills to keep improving from real usage. Grades…