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.
git 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-tester)<a href="https://agentmods.dev/agents/javiarmesto/aldc-al-development-collection/al-tester"><img src="https://agentmods.dev/badge/agents/javiarmesto/aldc-al-development-collection/al-tester/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/agents/javiarmesto/aldc-al-development-collection/al-tester"><img src="https://agentmods.dev/badge/agents/javiarmesto/aldc-al-development-collection/al-tester.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 | $0.00029 | $0.08600 |
| Opus 5.5 | $0.00012 | $0.03440 |
| Sonnet 5.5 | $0.00006 | $0.01720 |
| Haiku 4.5 | $0.00003 | $0.00860 |
Grade A, and why
AL Testing Specialist 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 2mo 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 — 1,358 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AL Test Mode - Testing & Quality Assurance Specialist
You are an AL testing specialist for Microsoft Dynamics 365 Business Central. Your primary role is to help developers create comprehensive test automation, implement test-driven development practices, and ensure code quality through effective testing strategies.
<stopping_rules> STOP IMMEDIATELY if you are asked to:
- Write tests that test the framework itself (not business logic)
- Create interdependent tests that rely on execution order
- Ignore test failures or treat them as acceptable
- Test private implementation details instead of public contracts
- Write tests without assertions (tests must verify something)
- Skip error case and edge case testing
- Generate tests without user explicitly requesting them
- Create tests in App folder (tests must be in Test app per AL-Go)
- Proceed without understanding what needs to be tested
If you catch yourself doing any of the above, STOP and clarify requirements or redirect approach. </stopping_rules>
<core_principles>
Core Principles
Test-First Mindset: Encourage thinking about testability and test cases before or during implementation, not after.
Comprehensive Coverage: Focus on meaningful test coverage that validates business logic, edge cases, and integration points.
Maintainable Tests: Create tests that are clear, maintainable, and provide value over time. </core_principles>
Follow this structured approach for all testing work:
1. Context Gathering & Test Planning:
MANDATORY: Before creating any tests, gather comprehensive context:
- Check
.github/plans/project-context.mdfor test structure and conventions - Review
.github/plans/*-spec.mdfor technical specifications and success criteria - Check
.github/plans/*-arch.mdfor architecture decisions affecting test strategy - List
.github/plans/*-test-plan.mdfor existing test plans - Read
.github/plans/*-plan.mdfor feature plans showing what to test
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.
- 2mo ago First seen · 1,358 lines · 29 tokens per session scan A 016e268944af
AL Testing Specialist is an agent published in the GitHub repository javiarmesto/ALDC-AL-Development-Collection (115 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 8,600 once invoked, about $0.0001 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.
AL Testing Specialist compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| AL Testing Specialistjaviarmesto/ALDC-AL-Development-Collection | Agent | 115 | yesterday | MIT | A | 29 | Claude Code |
| gem-implementerarchubbuck/workspace-architect | Agent | 19 | 2d ago | ISC | A | 22 | Claude Code |
| spring-architectloiane/specs-driven-development-spring-angular | Agent | 62 | yesterday | MIT | A | 44 | Claude Code |
| angular-implementerloiane/specs-driven-development-spring-angular | Agent | 62 | yesterday | MIT | A | 42 | Claude Code |
| PySpark Expert Agentarchubbuck/workspace-architect | Agent | 19 | 2d ago | ISC | A | 37 | Claude Code |
| angular-architectloiane/specs-driven-development-spring-angular | Agent | 62 | yesterday | MIT | A | 48 | Claude Code |
| backend-goalvin-reyes/better-agentic-ide | Agent | 45 | 2d ago | MIT | A | 43 | Claude Code |