advpl-specialist: Command for Claude Code

.cursor/commands/diagnose.md

diagnose is a command for Claude Code, Cursor from thalysjuvenal/advpl-specialist. It costs 0 tokens per session (494 once invoked), scanned A, original, MIT.

A troubleshooting command for ADVPL and TLPP, programming languages used by the TOTVS Protheus business system. It examines source files, error messages, or log files for compilation, runtime, performance, and locking problems.

In plain words
What is it for?
Investigate code, quoted error messages, or Protheus logs; identify likely causes; and check for missing error handling, inefficient patterns, record locks, and deadlocks.
Why use it?
Protheus errors can involve unfamiliar language rules, database records, or competing locks. This guides diagnosis using reference material for common errors and performance issues.

Command for Claude CodeCursor

Written for Claude Code and Cursor: shipped in a Claude Code plugin, but also installed under .cursor/.

This is thalysjuvenal/advpl-specialist's own configuration. It tells Claude Code and Cursor how to work on advpl-specialist itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything advpl-specialist configures →

Part of the advpl-specialist plugin — 18 skills, 14 commands, 2 hooks shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to thalysjuvenal/advpl-specialist. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/thalysjuvenal/advpl-specialist/main/.cursor/commands/diagnose.md
Clone the repo
git clone --depth 1 https://github.com/thalysjuvenal/advpl-specialist

Made for: Claude Code, Cursor.

Or install advpl-specialist, the plugin that ships this one along with the rest of its 18 skills, 14 commands, 2 hooks.

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 diagnose

README.md
[![agentmods](https://agentmods.dev/badge/commands/thalysjuvenal/advpl-specialist/diagnose/github.svg)](https://agentmods.dev/commands/thalysjuvenal/advpl-specialist/diagnose)
Your own site
<a href="https://agentmods.dev/commands/thalysjuvenal/advpl-specialist/diagnose"><img src="https://agentmods.dev/badge/commands/thalysjuvenal/advpl-specialist/diagnose/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 diagnose

Your own site · 80×15
<a href="https://agentmods.dev/commands/thalysjuvenal/advpl-specialist/diagnose"><img src="https://agentmods.dev/badge/commands/thalysjuvenal/advpl-specialist/diagnose.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 494 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 $0.00000 $0.00494
Opus 5 $0.00000 $0.00247
Sonnet 5 $0.00000 $0.00099
Haiku 4.5 $0.00000 $0.00049

Measured 12d ago against content hash 6c0f61ed073b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

diagnose 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.

.cursor/commands/diagnose.md · 25 lines

How it starts

The opening of the file, as written. The whole thing — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/diagnose — Diagnose compilation, runtime, performance, and log errors in ADVPL/TLPP code

You are an expert ADVPL/TLPP assistant for TOTVS Protheus. This command diagnoses and resolves ADVPL/TLPP errors and problems.

Knowledge to load first

Locate the advpl-specialist skills (installed via npx skills add thalysjuvenal/advpl-specialist; in this repository they live under skills/) and read, in order:

  1. skills/advpl-debugging/reference.md
  2. skills/advpl-debugging/common-errors.md (for error-message diagnosis)
  3. skills/advpl-debugging/performance-tips.md (for performance-related findings)
  4. skills/protheus-locks-deadlocks/reference.md (if the issue involves record locks or deadlocks)

Workflow

  1. Identify the input mode: a source file path, a quoted error message, or --log <path> for a Protheus log file.
  2. For a file: read the code and scan for anti-patterns, missing error handling, and lock issues using common-errors.md and performance-tips.md as checklists.
  3. For an error message: match it against common-errors.md; if not found, apply the TDN lookup strategy from skills/tdn-lookup/reference.md.
  4. For a log file: parse it for ERROR/WARNING patterns and extract stack traces.
  5. Report findings with severity levels (ERROR, WARNING, INFO), a root-cause explanation for each, and a specific fix with a before/after code comparison.
  6. Add preventive advice on how to avoid similar issues in the future.

Output rules

  • Group findings by severity; every finding must cite the exact file/line (or log line) it comes from.
  • Fixes must respect existing project conventions: #include "totvs.ch", Hungarian notation, Embedded SQL only (BeginSQL/EndSQL), proper BEGIN SEQUENCE ... RECOVER ... END SEQUENCE error handling.
  • Never suggest a fix that depends on undocumented or restricted native functions — check skills/protheus-reference/restricted-functions.md when relevant.
  • Compilation must be validated in TDS / VS Code TOTVS extension — never claim the code compiles.

Read the full file on GitHub · 25 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. 12d ago First seen · 25 lines · 0 tokens per session scan A 6c0f61ed073b

Subscribe to this mod's changes

diagnose is a command published in the GitHub repository thalysjuvenal/advpl-specialist (186 stars, last pushed 21d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 494 tokens. 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.