advpl-code-review

advpl-code-review is a skill for Claude Code from thalysjuvenal/advpl-specialist. It costs 139 tokens per session (558 once invoked), scanned A, original, MIT.

A structured reviewer for ADVPL and TLPP code used with TOTVS Protheus. It checks coding practices, performance, security and modernization concerns, then reports each finding with a severity and rule code.

In plain words
What is it for?
Use it to audit existing .prw or .tlpp files, prepare code for a merge or deployment, and assess readiness for moving from ADVPL to TLPP.
Why use it?
It provides a consistent review before code is merged or deployed, including checks for database locking, variable scope, error handling, inefficient code, SQL injection and exposed credentials.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

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

Good fit Use it to audit existing .prw or .tlpp files, prepare code for a merge or deployment, and assess readiness for moving from ADVPL to TLPP.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/thalysjuvenal/advpl-specialist/advpl-code-review
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.

Any agent
npx skills add thalysjuvenal/advpl-specialist --skill advpl-code-review
Clone the repo
git clone --depth 1 https://github.com/thalysjuvenal/advpl-specialist

Made for: Claude Code.

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 advpl-code-review

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/thalysjuvenal/advpl-specialist/advpl-code-review"><img src="https://agentmods.dev/badge/skills/thalysjuvenal/advpl-specialist/advpl-code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 139 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 558 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00139 $0.00558
Opus 5 $0.00069 $0.00279
Sonnet 5 $0.00028 $0.00112
Haiku 4.5 $0.00014 $0.00056

Measured 11d ago against content hash e1d5358bda29, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

advpl-code-review 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.

skills/advpl-code-review/SKILL.md · 20 lines

What it actually says

ADVPL/TLPP Code Review

This skill provides a systematic code review methodology for existing ADVPL/TLPP code, producing findings tagged with a rule ID (BP-*, PERF-*, SEC-*, MOD-*), a severity (CRITICAL/WARNING/INFO), the file/line, the issue, and the fix. It covers four review categories: best practices, performance, security, and modernization, and can map findings to the official TOTVS SonarQube quality gate.

Activate this skill when the user wants existing code inspected for quality, compliance, security, or performance issues -- e.g. before a merge, before a deploy, during an onboarding audit, or when assessing migration readiness from .prw to .tlpp. It does not cover generating new code (see advpl-code-generation), diagnosing a specific runtime/compilation error (see advpl-debugging), restructuring code without adding features (see advpl-refactoring), or performing the actual .prw to .tlpp conversion (see advpl-to-tlpp-migration).

Reference file Read when
reference.md Always -- review categories, output format, severity levels, review process, rule ID prefixes
rules-best-practices.md Checking RecLock/MsUnlock pairing, variable scope, area management, error handling, documentation (BP-* rules)
rules-performance.md Checking Embedded SQL efficiency, loop efficiency, string operations, index usage (PERF-* rules)
rules-security.md Checking SQL injection, input validation, credential exposure, sensitive data logging (SEC-* rules)
rules-modernization.md Checking TLPP migration candidates, namespace usage, OOP patterns, modern UI frameworks (MOD-* rules)
sonarqube-rules-catalog.md Aligning findings with the official TOTVS SonarQube ruleset (groups G1-G5, CA/BG/CS codes)
Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 20 lines · 139 tokens per session scan A e1d5358bda29

Subscribe to this mod's changes

advpl-code-review is a skill published in the GitHub repository thalysjuvenal/advpl-specialist (186 stars, last pushed 20d ago), licensed MIT. It adds 139 tokens to every session and 558 once invoked, about $0.0007 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.