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/commands/javiarmesto/aldc-al-development-collection/al-spec-create)<a href="https://agentmods.dev/commands/javiarmesto/aldc-al-development-collection/al-spec-create"><img src="https://agentmods.dev/badge/commands/javiarmesto/aldc-al-development-collection/al-spec-create/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/commands/javiarmesto/aldc-al-development-collection/al-spec-create"><img src="https://agentmods.dev/badge/commands/javiarmesto/aldc-al-development-collection/al-spec-create.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 | $0.00056 | $0.03137 |
| Opus 5 | $0.00028 | $0.01569 |
| Sonnet 5 | $0.00011 | $0.00627 |
| Haiku 4.5 | $0.00006 | $0.00314 |
Grade A, and why
al-spec-create 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 10d 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 — 409 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AL Technical Specification Workflow
Your goal is to generate a detailed implementable technical specification for ${input:req_name} (complexity: ${input:Complexity}).
This is NOT the architecture phase. This phase produces the implementable blueprint: exact object IDs, field types, procedure signatures, event patterns, and AL code snippets.
Guardrails
- Never create or modify real AL objects during this phase
- Never output to
/specs/— always output to.github/plans/{req_name}/ - If
{req_name}.architecture.mdexists, read it first — the spec must implement what the architect designed - If spec already exists, confirm with user before overwriting
- Complexity drives depth: LOW = lighter spec, MEDIUM/HIGH = full spec with all sections
Step 1 — Read Context
1.1 Read global memory
Read .github/plans/memory.md
Extract: project app ID range, naming conventions (prefix), existing table IDs in use, current extension patterns.
1.2 Read architecture document (if exists)
Read .github/plans/${input:req_name}/${input:req_name}.architecture.md
If it exists: the spec MUST align with the architectural decisions (data flows, chosen patterns, integration points). If it does not exist: proceed — spec will define structure from scratch (typical for LOW complexity).
1.3 Analyze codebase
Search for:
- Existing objects with similar patterns (
Grep/Glob; al-symbols-mcpal_search_objectsfor symbol-level) - Naming conventions in
/src - Available object ID ranges in
app.json - Existing event publishers relevant to this feature
- Existing API pages or codeunits if integration is involved
Verify every base-app event you subscribe to against symbols — this is the spec's job, not the planner's. For each event the feature hooks into, confirm it exists in the current BC version via al-symbols-mcp (
al_search_object_members/al_get_object_definition; download symbols first if absent). Record the verified publisher object + exact event name in §5. If you cannot confirm an event exists, it does not enter the spec as fact — move it to §12 Open Questions. (A wrong or nonexistent event name passed downstream silently becomes a blind search burst in planning and a defect the reviewer must catch. Verify it once, here, at the cheapest point.)
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.
- 10d ago First seen · 409 lines · 56 tokens per session scan A 6165de31ddb4
al-spec-create is a command published in the GitHub repository javiarmesto/ALDC-AL-Development-Collection (103 stars, last pushed 3d ago), licensed MIT. It adds 56 tokens to every session and 3,137 once invoked, about $0.0003 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 commands, from other repositories
ship
Run the Android pre-launch checklist via parallel fan-out to specialist personas, then synthesize a go/no-go decision with rollback and staged rollout plan.
code-simplify
Simplify code incrementally while preserving behavior exactly.
test
Write tests before implementation using Red-Green-Refactor.
spec
Write a structured specification before writing any code.
review-skill
Review one skill for standalone packaging, instruction quality, contradictory guidance, resource correctness, and current best practices.
review-workflow
Review one workflow folder for standalone packaging, Copilot customisation quality, local link correctness, and current best practices.