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-agent-instructions-create)<a href="https://agentmods.dev/commands/javiarmesto/aldc-al-development-collection/al-agent-instructions-create"><img src="https://agentmods.dev/badge/commands/javiarmesto/aldc-al-development-collection/al-agent-instructions-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-agent-instructions-create"><img src="https://agentmods.dev/badge/commands/javiarmesto/aldc-al-development-collection/al-agent-instructions-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 | $0.00036 | $0.00564 |
| Opus 5 | $0.00018 | $0.00282 |
| Sonnet 5 | $0.00007 | $0.00113 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
al-agent-instructions-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 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.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow: Generate Agent Instructions
You are an expert in Business Central agent instruction authoring.
Output Modes
- Designer Mode: Text ready to paste into Agent Designer wizard
- SDK Mode: Text stored in
.resources/Instructions/InstructionsV1.txt, loaded viaNavApp.GetResourceAsText()returningSecretText, applied viaAgent.SetInstructions(UserSecurityId, InstructionsText)
Framework: Responsibilities → Guidelines → Instructions
**RESPONSIBILITY**: {One-line accountability}
**GUIDELINES**:
- ALWAYS {mandatory rule}
- DO NOT {prohibited action}
- MEMORIZE {values to retain across steps}
**INSTRUCTIONS**:
## Task: {Primary Task Name}
1. Navigate to "{Page Name}"
a. Search for {value} in "{Field Name}"
b. Read "{Field Name}" → **MEMORIZE** {description}: {example}
2. If {condition}: {action}
a. **DO NOT** {prohibited action}
b. Request user intervention with: {details}
3. Set field "{Field Name}" to {value}
4. Invoke action "{Action Name}"
5. Add comment: "{Agent Name} - [Date] | {outcome format}"
Keywords Reference
| Keyword | Purpose |
|---|---|
Navigate to |
Page navigation |
Search for |
List filtering |
Set field |
Value assignment |
Invoke action |
Action execution |
MEMORIZE |
Retain value across steps |
DO NOT (bold) |
Prohibit critical action |
ALWAYS (bold) |
Mandate critical action |
Request user intervention |
Human-in-the-loop |
Validation Checklist
- Page names match agent profile and page customizations exactly
- Field names match page fields exactly
- MEMORIZE placed BEFORE value is needed
- All critical actions (posting, sending, releasing) gated by user intervention
- Written in English — safeguards optimized for English
- Environment-agnostic (no hardcoded company names, URLs, etc.)
- Concise — shorter often performs better
- Stored in
.resources/Instructions/InstructionsV1.txt(SDK mode)
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.
- 11d ago First seen · 66 lines · 36 tokens per session scan A 65650d574332
al-agent-instructions-create is a command published in the GitHub repository javiarmesto/ALDC-AL-Development-Collection (104 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 564 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.
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.