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-task)<a href="https://agentmods.dev/commands/javiarmesto/aldc-al-development-collection/al-agent-task"><img src="https://agentmods.dev/badge/commands/javiarmesto/aldc-al-development-collection/al-agent-task/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-task"><img src="https://agentmods.dev/badge/commands/javiarmesto/aldc-al-development-collection/al-agent-task.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 | $0.00040 | $0.00619 |
| Opus 5 | $0.00020 | $0.00309 |
| Sonnet 5 | $0.00008 | $0.00124 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
al-agent-task 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 9d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow: Generate Agent Task Integration Code
You are an expert AL developer. Generate production-ready AL code for agent task integration.
The skill bc-agent-task-patterns provides the 8 integration patterns and SDK codeunit reference. Use it as your knowledge base.
Step 1 — Gather Context
Before generating code, determine:
- Agent name and prefix: Read from
app.jsonor ask the developer - Object ID range: Check existing objects in
app/to find the next available IDs - Which pattern(s): Ask the developer or infer from their request:
- "I need a Public API" → Pattern A
- "Add a button to send work to the agent" → Pattern B (calls A)
- "Trigger agent on posting/releasing" → Pattern C (calls A)
- "Agent needs to process files" → Pattern D (combine with A/B/C)
- "Continue an existing task" → Pattern E
- "Run code only in agent context" → Pattern G/H
- ExternalId format: Convention is
{PREFIX}-{No.}(e.g.,LEAD-001,SO-1001) - Target page/table: Which page extension or event subscriber is needed?
Step 2 — Generate Code
For each requested pattern:
- Search the codebase for existing agent objects (Setup table, Public API, enums) to reuse
- Generate the AL objects following the pattern from the skill, substituting:
{Agent}→ actual agent name/prefix{id}→ actual object IDs- Record names, field names, enum values → actual project values
- Place files in the correct project structure folder:
- Public API + Impl →
app/Example/ - Page extensions →
app/Example/ - Session events →
app/Setup/TaskExecution/
- Public API + Impl →
- Verify generated code references correct enum values and codeunit names from the project
Step 3 — Validate
- All generated codeunits compile (correct parameter types, return types)
- Public API has
Access = Public, Implementation hasAccess = Internal - Event-driven task creation uses
[TryFunction] - Business conditions checked BEFORE task creation
- Failures logged via
Session.LogMessage - ExternalId follows the agreed format convention
- Page extensions use
AgentSetup.OpenAgentLookup()for agent selection
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.
- 9d ago First seen · 57 lines · 40 tokens per session scan A 261442f6cc16
al-agent-task is a command published in the GitHub repository javiarmesto/ALDC-AL-Development-Collection (103 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 619 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
toh-connect
Connect app to Supabase backend with schema and RLS policies.
views
Create Django views with proper structure and best practices.
middleware
Create Express middleware for $ARGUMENTS following project conventions.
route
Create API routes for $ARGUMENTS following project conventions.
api-endpoint
Generate a complete API endpoint for $ARGUMENTS following project conventions.
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.