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.
curl -O https://raw.githubusercontent.com/thalysjuvenal/advpl-specialist/main/AGENTS.mdgit 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/instructions/thalysjuvenal/advpl-specialist/agents-md)<a href="https://agentmods.dev/instructions/thalysjuvenal/advpl-specialist/agents-md"><img src="https://agentmods.dev/badge/instructions/thalysjuvenal/advpl-specialist/agents-md/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/instructions/thalysjuvenal/advpl-specialist/agents-md"><img src="https://agentmods.dev/badge/instructions/thalysjuvenal/advpl-specialist/agents-md.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 | $0.01773 | $0.01773 |
| Opus 5 | $0.00886 | $0.00886 |
| Sonnet 5 | $0.00355 | $0.00355 |
| Haiku 4.5 | $0.00177 | $0.00177 |
Grade A, and why
advpl-specialist AGENTS.md 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 10d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — ADVPL/TLPP (TOTVS Protheus)
This file doubles as a distributable template: copy it to the root of your Protheus source repository so any AI agent follows these standards.
Project context
In this repository (advpl-specialist): this is a knowledge plugin for AI coding agents working with TOTVS Protheus. It ships 14 slash commands (commands/), 4 specialized agents (agents/), and 18 reference skills (skills/<name>/SKILL.md + companion reference files) covering code generation, review, debugging, refactoring, TLPP migration, documentation, SQL, testing, locks, business processes, Smart X, and SX dictionary configuration. There is no application runtime here — the "code" is markdown reference material and prompt instructions.
In a Protheus source repository where this file is copied: the project contains .prw (ADVPL) and/or .tlpp (TLPP) source files that run inside a Protheus AppServer, plus SX dictionary scripts and possibly REST/SOAP services. Apply the standards below to any file with those extensions.
Coding standards
- Includes:
.prwfiles always use#include "totvs.ch"(lowercase). Never use"protheus.ch"— it is obsolete..tlppfiles use dedicated.thincludes (tlpp-core.th,tlpp-rest.th,tlpp-object.th,tlpp-probat.th, etc.). Do not addusing namespace tlpp.*— the.thincludes already bring what is needed. - Naming: Hungarian notation for variables —
c(character),n(numeric),d(date),l(logical),a(array),o(object),b(code block),x(indefinite). User Functions use a module prefix + descriptive name (e.g.FATA001,COMA100); TLPP classes are PascalCase, methods camelCase. - Variable scope: Always prefer
Local. Pass data via parameters, never viaPrivate/Public. AllLocaldeclarations must appear at the top of the function, before any executable statement. - Database access: Use Embedded SQL (
BeginSQL ... EndSQL) with macros —%table:TABLE%,%xFilial:TABLE%,%notDel%,%exp:EXPRESSION%,%Order:TABLE%— instead of raw SQL strings orTCQueryconcatenation. UseTCSqlExecfor DML. Every function that changes the current WorkArea (DbSelectArea,DbSetOrder,DbSeek) must save/restore it withGetArea()/RestArea(). - Locking: Every
RecLockmust have a correspondingMsUnlock, including on error paths. - Automation: Prefer
FWMVCRotAutoto automate MVC routines; useMsExecAutoonly for legacy non-MVC routines. - TLPP namespaces:
custom.<agrupador>.<servico>for customizations,totvs.protheus.<segmento>.<agrupador>for standard TOTVS namespaces — lowercase, dot-separated, no underscores. - Custom fields: Validate existence in SX3 before referencing any custom field. Custom fields follow
<table-prefix>_X*(e.g.A1_XCODIGO). Custom user functions use theU_prefix. - Error handling: Use
BEGIN SEQUENCE ... RECOVER ... END SEQUENCE(ADVPL) orTry/Catch(TLPP), never leave error paths silently swallowed. - Encoding: ADVPL/TLPP source files use Windows-1252 (not UTF-8).
- Documentation: Public functions, methods, and REST endpoints get a Protheus.doc header block (
@type,@param,@return,@author,@since,@version,@history).
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.
- 10d ago First seen · 68 lines · 1,773 tokens per session scan A daa0c52bf60f
advpl-specialist AGENTS.md is an instructions file published in the GitHub repository thalysjuvenal/advpl-specialist (186 stars, last pushed 19d ago), licensed MIT. It adds 1,773 tokens to every session, about $0.0089 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.