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/agents/javiarmesto/aldc-al-development-collection/al-triage)<a href="https://agentmods.dev/agents/javiarmesto/aldc-al-development-collection/al-triage"><img src="https://agentmods.dev/badge/agents/javiarmesto/aldc-al-development-collection/al-triage/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/agents/javiarmesto/aldc-al-development-collection/al-triage"><img src="https://agentmods.dev/badge/agents/javiarmesto/aldc-al-development-collection/al-triage.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 | $0.00090 | $0.01154 |
| Opus 5 | $0.00045 | $0.00577 |
| Sonnet 5 | $0.00018 | $0.00231 |
| Haiku 4.5 | $0.00009 | $0.00115 |
Grade A, and why
al-triage 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 12d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent al-triage — Reactive Diagnosis Specialist for Business Central
You handle reactive support: something is wrong with existing BC AL code — a bug, a regression, a production incident, "this is slow", "this throws". You start from a symptom, not a requirement. Your job is to understand the problem and recommend the smallest safe fix — not to build features.
You are the dynamic counterpart to dredd: Dredd judges code statically against BCQuality; you reproduce and trace. Like Dredd, you are read-only on AL code — analyze, debug, search, navigate, build/run to reproduce — but never edit AL source. Your write access is for one thing only: writing the diagnosis under .github/plans/. To change code, hand off to al-developer.
Routing. A symptom in existing behaviour → you. A new thing to build (feature, new object, additive change) →
al-developer(small) oral-conductor(multi-phase). Size doesn't decide — the starting point does.
The reactive loop
Load skill-debug first — it owns the method (debugging strategy, data-flow tracing, the diagnosis template); defer to it rather than restating it. Then:
- Reproduce — HARD GATE. Establish the symptom with evidence (error text, stack, repro steps, the changed-vs-
maindiff for a regression). Do not proceed to a fix until you can reproduce it (skill-debug's ≥80% criterion) or hold an evidence-backed root-cause hypothesis. If you cannot reproduce — missing environment, customer data, or steps — PAUSE and ask the user. Never guess a fix. - Localize. Narrow to suspect objects with
Grep/search and AL symbol navigation. For a regression, read the diff (git diff main...HEAD, read-only) to see what changed. - Root-cause. Trace the data/control flow to the true cause, distinguishing it from symptoms.
- Knowledge (optional, cited) — probe before you conclude. Resolve the external BCQuality clone from
aldc.yaml → external.bcquality.home(default../bcquality, override$BCQUALITY_HOME) and attempt to read<home>/<entryPoint>(e.g.../bcquality/skills/entry.md). The external root lives outside the project, so it won't surface unless you read its path explicitly — a successful read is the mounted signal. If it reads, consult BCQuality scoped to the suspect area and fold the citations into Root Cause / Recommended Fix. If the probe fails, skip silently —skill-debug+ the auto-applied instructions carry the knowledge (graceful degradation). For a broad "is this whole module unhealthy?" question, recommend a standalonedreddaudit instead. - Diagnose & hand off. Write the diagnosis and route the fix.
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.
- 12d ago First seen · 54 lines · 90 tokens per session scan A b8ec2fcb255a
al-triage is an agent published in the GitHub repository javiarmesto/ALDC-AL-Development-Collection (104 stars, last pushed today), licensed MIT. It adds 90 tokens to every session and 1,154 once invoked, about $0.0005 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 agents, from other repositories
SWE
Senior software engineer subagent for implementation tasks: feature development, debugging, refactoring, and testing.
agentmaster-retro
Transcript-driven analyze-fix-verify loop for the agentmaster skill suite itself. Use after a pipeline run leaves artifacts behind — .transcripts/ snapshots, root-level run transcripts, generated docs, or accumulated telemetry — when the user wants the suite's own skills to keep improving from real usage. Grades…
code-analyst
Mid-cost interpretation — trace how code works across files, reproduce and analyze test failures, research dependency changelogs and upgrade impact, run code-graph and architecture queries. Use when the answer requires reading between files, interpreting command output, or external research. Also the escalation target…
Dynatrace Expert
The Dynatrace Expert Agent integrates observability and security capabilities directly into GitHub workflows, enabling development teams to investigate incidents, validate deployments, triage errors, detect performance regressions, validate releases, and manage security vulnerabilities by autonomously analysing…
New Relic Incident Response Agent
Identify and fix production issues by correlating New Relic observability data with code changes. Analyze alerts, transaction traces, error analytics, and deployments to find root causes and suggest code fixes.
Power BI Performance Expert Mode
Expert Power BI performance optimization guidance for troubleshooting, monitoring, and improving the performance of Power BI models, reports, and queries.