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 javiarmesto/ALDC-AL-Development-Collection --skill aldcgit 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/skills/javiarmesto/aldc-al-development-collection/aldc)<a href="https://agentmods.dev/skills/javiarmesto/aldc-al-development-collection/aldc"><img src="https://agentmods.dev/badge/skills/javiarmesto/aldc-al-development-collection/aldc/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/javiarmesto/aldc-al-development-collection/aldc"><img src="https://agentmods.dev/badge/skills/javiarmesto/aldc-al-development-collection/aldc.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 | $0.00027 | $0.01663 |
| Opus 5.5 | $0.00011 | $0.00665 |
| Sonnet 5.5 | $0.00005 | $0.00333 |
| Haiku 4.5 | $0.00003 | $0.00166 |
Grade A, and why
aldc 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 26d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read the relevant role or workflow below in full before acting. Resolve these links from this skill directory, including when a plugin cache holds it. For AL tools, first read AL tooling: it separates MCP operation scope from the unresolved native LSP route. Reading this skill does not apply custom-agent TOML permissions. Load applicable rules from references/rules/ and domain guidance from references/skills/ (GUIDE.md) on demand. These domain references are not duplicate discoverable skills. Recover approved work from .agents/plans/ and memory.md.
For MEDIUM/HIGH work, preserve architecture → specification → Conductor order. The al-spec-create workflow loads the same al-spec-agent contract as direct role invocation. Human material gates and current session authorization govern actions. Plugin installation alone does not authorize compilation, publishing or deployment.
Use discovered project custom agents when available. Otherwise read the selected role as instructions in this session; when independent subagents are required and unavailable, report the affected step as pending. Do not invent a tool name or claim independent review from a sequential role change.
Roles
- al-agent-builder: Agent Toolkit Builder — specialist in designing and coding Business Central agents using the AI Development Toolkit and Agent SDK. Follows the official Agent Template project structure. Handles both Designer (no-code) and SDK (pro-code) paths. Use when building BC agents or agent SDK integrations.
- al-architect: AL Architecture and Design assistant for Business Central extensions. Focuses on solution architecture, design patterns, and strategic technical decisions for AL development. Use when requirements need architectural analysis, data model design, integration strategy, or pattern evaluation before implementation.
- al-conductor: 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.
- al-developer-reviewer: Independent read-only review of an AL increment implemented directly by Developer, without Conductor. Checks acceptance, BCQuality and current validation evidence before human approval.
- al-developer: AL Developer - Tactical implementation specialist for Business Central extensions. Edits AL, builds via the terminal, and validates with tests. Implements features following specifications without making architectural decisions. Use when you need to implement, code, debug, or fix AL code directly.
- al-implement-subagent: TDD Implementation Subagent — Creates AL objects following strict RED→GREEN→REFACTOR cycle. Only invokable by al-conductor via the available native subagent tool.
- al-planning-subagent: AL Planning Subagent - AL-aware research and context gathering for Business Central development. Returns structured findings to Conductor for plan creation.
- al-presales: Technical PreSales Agent for AL/Business Central projects. Specializes in project planning, cost estimation (time & budget), feasibility analysis, SWOT/risk assessment, and technical documentation. Orchestrates AL Architecture & Design Specialist and al-spec-create for comprehensive proposals. CREATES Technical_PreSales folder and documents dynamically on demand. Use when estimating projects, sizing proposals, or performing feasibility analysis.
- al-review-subagent: AL Code Review Subagent - Quality assurance for Business Central AL code. Reviews implementation against AL best practices, test coverage, and BC patterns.
- al-spec-agent: Turn an approved Business Central requirement and architecture into one implementable AL specification. Own technical contracts and acceptance criteria without writing AL implementation or changing architecture.
- al-triage: Reactive support for EXISTING Business Central AL code — reproduce, localize, root-cause, and recommend a minimal fix for bugs, regressions, and incidents. Read-only on code: produces a diagnosis and hands the fix to al-developer. The dynamic counterpart to Dredd (static audit). Use when you start from a symptom ("this throws", "this is slow", "broke after the last change").
- dredd: Independent, on-demand AL codebase auditor for Business Central. Judges the code against BCQuality (citable knowledge) plus native checks for what BCQuality does not reach. Read-only; advisory verdict. Default scope: objects changed vs main; full codebase on request.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/agents/al-agent-builder.md 11 KB
- references/agents/al-architect.md 27 KB
- references/agents/al-conductor.md 43 KB
- references/agents/al-developer-reviewer.md 5.6 KB
- references/agents/al-developer.md 10 KB
- references/agents/al-implement-subagent.md 16 KB
- references/agents/al-planning-subagent.md 15 KB
- references/agents/al-presales.md 30 KB
- references/agents/al-review-subagent.md 5.3 KB
- references/agents/al-spec-agent.md 17 KB
- references/agents/al-triage.md 9.5 KB
- references/agents/dredd.md 15 KB
- references/al-tooling.md 14 KB
- references/commands/al-agent-build-instructions.md 5.3 KB
- references/commands/al-agent-create.md 8.5 KB
- references/commands/al-agent-instructions.md 5.3 KB
- references/commands/al-agent-task.md 5.4 KB
- references/commands/al-agent-test.md 7.7 KB
- references/commands/al-build.md 4.8 KB
- references/commands/al-context-create.md 12 KB
- references/commands/al-initialize.md 19 KB
- references/commands/al-memory-create.md 13 KB
- references/commands/al-pr-prepare.md 9.0 KB
- references/commands/al-spec-create.md 3.5 KB
- references/doctor.md 8.4 KB
- references/mcp-setup.md 4.2 KB
- references/rules/al-agent-toolkit.md 4.6 KB
- references/rules/al-code-style.md 712 B
- references/rules/al-error-handling.md 1.5 KB
- references/rules/al-events.md 898 B
- references/rules/al-guidelines.md 1022 B
- references/rules/al-naming-conventions.md 1006 B
- references/rules/al-performance.md 996 B
- references/rules/al-testing.md 1004 B
- references/skills/skill-agent-instructions/examples/agent-advanced-instructions.txt 4.4 KB
- references/skills/skill-agent-instructions/examples/agent-simple-instructions.txt 1.8 KB
- references/skills/skill-agent-instructions/GUIDE.md 11 KB
- references/skills/skill-agent-instructions/references/agent-keywords-reference.md 4.1 KB
- references/skills/skill-agent-task-patterns/examples/lead-handoff-with-attachment.md 2.0 KB
- references/skills/skill-agent-task-patterns/examples/session-events-binding.md 2.1 KB
- references/skills/skill-agent-task-patterns/GUIDE.md 17 KB
- references/skills/skill-agent-toolkit/GUIDE.md 17 KB
- references/skills/skill-al-review-pipeline/GUIDE.md 7.3 KB
- references/skills/skill-api/GUIDE.md 14 KB
- references/skills/skill-api/references/api-advanced-patterns.md 4.2 KB
- references/skills/skill-contribution-assistant/AUTHORS.md 425 B
- references/skills/skill-contribution-assistant/CHANGELOG.md 456 B
- references/skills/skill-contribution-assistant/GUIDE.md 5.2 KB
- references/skills/skill-contribution-assistant/references/onboarding-questionnaire.md 853 B
- references/skills/skill-contribution-assistant/references/opportunity-detection.md 663 B
- references/skills/skill-contribution-assistant/references/pr-readiness-checklist.md 651 B
- references/skills/skill-contribution-assistant/references/quality-gate.md 718 B
- references/skills/skill-copilot/GUIDE.md 14 KB
- references/skills/skill-copilot/references/copilot-ai-generation.md 7.9 KB
- references/skills/skill-copilot/references/copilot-testing.md 6.2 KB
- references/skills/skill-debug/GUIDE.md 10 KB
- references/skills/skill-estimation/GUIDE.md 9.1 KB
- references/skills/skill-events/GUIDE.md 10 KB
- references/skills/skill-migrate/GUIDE.md 12 KB
- references/skills/skill-migrate/references/al18-capabilities.md 5.4 KB
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.
- 26d ago Changed · +2 lines e62c55f3eece
- 1mo ago Changed · +2 lines d7367c303f5c
- 1mo ago First seen · 48 lines · 27 tokens per session scan A 5d9ae07a6f1a
aldc is a skill published in the GitHub repository javiarmesto/ALDC-AL-Development-Collection (109 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 1,663 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 2026-09-15.
Other skills, from other repositories
test-driven-development
Use when implementing new features or fixing bugs. Write tests before implementation following Red-Green-Refactor. Covers JUnit5, MockK, Compose test rules, and the Prove-It pattern for bugs.
test-strategy
Produces a test strategy document defining what to test, at which layer, with which tools, and to what coverage standard. It applies the test pyramid model, surfaces coverage gaps in existing codebases, and produces a concrete plan — not a generic "write more tests" recommendation.
behavior-contract
Bug condition/postcondition formalization as testable Behavior Contracts. Defines invariants that must be preserved across fixes.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
test-driven-development
Strict RED-GREEN-REFACTOR cycle enforcement. Tests are never skipped or deferred. Run mode only, never watch mode. Exit code evidence mandatory.
tdd-enforcement
Red-Green-Refactor TDD methodology with mandatory failing tests, minimal implementation, quality refactoring, and 80% coverage gating.