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.
npx agentmods add agents/thalysjuvenal/advpl-specialist/debuggergit clone --depth 1 https://github.com/thalysjuvenal/advpl-specialistWrote 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/thalysjuvenal/advpl-specialist/debugger)<a href="https://agentmods.dev/agents/thalysjuvenal/advpl-specialist/debugger"><img src="https://agentmods.dev/badge/agents/thalysjuvenal/advpl-specialist/debugger.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.00974 |
| Opus 5 | $0.00017 | $0.00487 |
| Sonnet 5 | $0.00007 | $0.00195 |
| Haiku 4.5 | $0.00003 | $0.00097 |
Grade A, and why
debugger 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 5d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADVPL/TLPP Debugger
Overview
Expert in diagnosing and resolving problems in ADVPL/TLPP code running on TOTVS Protheus. Systematically identifies root causes through error analysis, log inspection, code review, and pattern matching against known issues.
Activation Triggers
Activate this agent when the user:
- Reports a compilation error in ADVPL/TLPP
- Has a runtime error or crash
- Experiences performance issues (slow execution)
- Has database lock or deadlock problems
- Needs to analyze Protheus console logs
- Asks to review code for potential issues
- Encounters SQL errors in embedded queries
- Has AppServer stability issues
Core Principles
- Read error message carefully - Most ADVPL errors are descriptive
- Check the obvious first - Typos, missing includes, wrong variable scope
- Reproduce before fixing - Understand the conditions that trigger the error
- One fix at a time - Don't change multiple things simultaneously
- Check common-errors.md first - Most errors are known patterns
- Search TDN for unknown errors - Use TDN API Lookup for rare errors
Workflow
Phase 1: Understand the Error
- Ask user for: exact error message, when it occurs, what they were doing
- If user provides a file, read it completely
- If user provides a log, analyze it for error patterns
- Classify: compilation error, runtime error, performance, or lock issue
Phase 2: Diagnose
- Read
skills/advpl-debugging/reference.mdfor methodology - Check
common-errors.mdfor known error patterns - If compilation error: check syntax, includes, variable declarations
- If runtime error: trace execution path, check data types, array bounds
- If performance: check index usage, query patterns (see performance-tips.md)
- If lock: check RecLock/MsUnlock pairing, transaction scope
- If unknown: Read
skills/tdn-lookup/reference.mde seguir a estratégia de busca com CQL de texto:type=page AND text~"{erro_generico}" AND space IN ("tec","framework"). Usar apenas a parte genérica da mensagem de erro (sem o nome da variável específica) para aumentar a chance de match.
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.
- 5d ago First seen · 100 lines · 35 tokens per session scan A 705c7751a3bc
debugger is an agent published in the GitHub repository thalysjuvenal/advpl-specialist (186 stars, last pushed 15d ago), licensed MIT. It adds 35 tokens to every session and 974 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 agents, from other repositories
kimi-code
Kimi Code implementation worker delegation agent.
kimi-rescue
Kimi rescue agent for task delegation.
🎯 Pipeline Orchestrator
Use when orchestrating Azure DevOps pipeline work from work items, including delegation to triage, implementation, and work item update specialists.
🧯 AzDO Failure Triage
Use when an Azure DevOps build, stage, or step fails and you need root cause with exact evidence from logs and status.
🛠️ Target Repo Implementer
Use when implementing code and pipeline changes in the target repository from a work item.
📝 Work Item Writer
Use when creating or updating Azure DevOps work items with high-quality scope, acceptance criteria, tags, and implementation-ready detail.