al-agent-instructions-create

al-agent-instructions-create is a command for Claude Code from javiarmesto/ALDC-AL-Development-Collection. It costs 36 tokens per session (564 once invoked), scanned A, original, MIT.

A template for writing instructions for Microsoft Dynamics 365 Business Central agents. It organizes the text into responsibilities, rules, and step-by-step actions for either the Agent Designer or SDK.

In plain words
What is it for?
Use it to create paste-ready Designer instructions or an `InstructionsV1.txt` resource for an SDK-based Business Central agent.
Why use it?
It turns vague agent behavior into explicit navigation, decisions, field changes, and user-intervention rules.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the aldc plugin — 10 commands, 1 hook shipped together

Good fit Use it to create paste-ready Designer instructions or an InstructionsV1.txt resource for an SDK-based Business Central agent.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/javiarmesto/aldc-al-development-collection/al-agent-instructions-create
Install

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.

Clone the repo
git clone --depth 1 https://github.com/javiarmesto/ALDC-AL-Development-Collection

Made for: Claude Code.

Or install aldc, the plugin that ships this one along with the rest of its 10 commands, 1 hook.

Wrote 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.

agentmods badge for al-agent-instructions-create

README.md
[![agentmods](https://agentmods.dev/badge/commands/javiarmesto/aldc-al-development-collection/al-agent-instructions-create/github.svg)](https://agentmods.dev/commands/javiarmesto/aldc-al-development-collection/al-agent-instructions-create)
Your own site
<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.

agentmods 80×15 button for al-agent-instructions-create

Your own site · 80×15
<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>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 564 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 11d ago against content hash 65650d574332, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

claude-plugin/commands/al-agent-instructions-create.md · 66 lines

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 via NavApp.GetResourceAsText() returning SecretText, applied via Agent.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)

Read the full file on GitHub · 66 lines

Changes

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.

  1. 11d ago First seen · 66 lines · 36 tokens per session scan A 65650d574332

Subscribe to this mod's changes

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.