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 skills add totvs/engpro-advpl-tlpp-skills --skill advpl-tlpp-compilegit clone --depth 1 https://github.com/totvs/engpro-advpl-tlpp-skillsWrote 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/skills/totvs/engpro-advpl-tlpp-skills/advpl-tlpp-compile)<a href="https://agentmods.dev/skills/totvs/engpro-advpl-tlpp-skills/advpl-tlpp-compile"><img src="https://agentmods.dev/badge/skills/totvs/engpro-advpl-tlpp-skills/advpl-tlpp-compile/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/skills/totvs/engpro-advpl-tlpp-skills/advpl-tlpp-compile"><img src="https://agentmods.dev/badge/skills/totvs/engpro-advpl-tlpp-skills/advpl-tlpp-compile.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 208 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00214 | $0.03655 |
| Opus 5 | $0.00107 | $0.01827 |
| Sonnet 5 | $0.00043 | $0.00731 |
| Haiku 4.5 | $0.00021 | $0.00365 |
Grade A, and why
advpl-tlpp-compile 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AdvPL/TLPP Compile (tds-vscode)
Overview
Compile AdvPL and TLPP source files from inside VS Code using the TOTVS Developer Studio for VSCode extension (TOTVS.tds-vscode). Compilation in the Protheus ecosystem requires a connected and authenticated AppServer: the extension reads its connection registry from servers.json, sends the source to the server's RPO (Repository of Programs/Objects), and returns the compilation result.
This skill orchestrates the complete path so a single "compile" request works end-to-end even on a fresh machine:
- Ensure the extension is installed (install it if missing).
- Ensure a server is configured in
servers.json(configure it with the user if missing). - Pick the target server (ask the user when more than one exists).
- Connect and authenticate (the user types the password — it is never exposed to the agent).
- Open the target source in the editor (required before a file-scope compile).
- Run the build/rebuild command for the file, folder, or workspace.
- Report the result and surface any compilation errors.
When to Use
Use this skill when:
- The user asks to compile or recompile an AdvPL/TLPP source (
compile,recompile,build,compilar,enviar para o RPO). - A code-generation, migration, or refactoring skill just produced/changed
.prw,.prg,.prx,.tlpp,.ppx,.ppp,.apw,.aph,.apl, or.ahufiles that must be sent to the AppServer. - The user wants to validate that a source compiles cleanly against a server.
- The tds-vscode extension is not yet installed or configured and the user wants to start compiling.
Do NOT use when:
- The user only wants static analysis / linting without sending to the RPO.
- The target language is not AdvPL/TLPP/4GL.
- The user explicitly wants a command-line (
tds-cli/advpls) build outside VS Code.
CRITICAL — Agent Execution Rules
These rules are MANDATORY.
- NEVER ask for, read, store, echo, or write the AppServer password. Authentication is interactive: the user types the password directly in the VS Code connection prompt. If a step needs the password, instruct the user to type it in the prompt and wait — do not collect it with any tool.
- ALWAYS use the extension UI to register and connect servers. Never edit
servers.jsonby hand. Server registration goes through the Add Server assistant and connection goes through the connection prompt, so the extension validates the data and fills generated fields (id,buildVersion,secure,token) itself. - NEVER write
token,savedTokens, orauthorizationtokenvalues intoservers.json. Those are generated by the extension after a successful connection. The agent does not write toservers.jsonat all — it only reads it to detect existing servers. - Ensure the source is CP1252 before compiling. The Protheus compiler only accepts Windows-1252 files. If the file was created/edited by an AI agent (UTF-8), run the
utf8-to-cp1252-conversionskill first, otherwise compilation fails with garbled characters. - Always confirm the target server with the user when more than one is registered. Never guess.
- When this skill runs as a follow-up to code generation/migration/refactoring, ASK the user whether they want to compile before starting. Do not auto-compile silently after another skill produced code.
- Read the result before declaring success. A command running without error is NOT proof of a successful compile — check the compilation output/Problems for errors and warnings.
What ships with it
1 file 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.
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 · 215 lines · 214 tokens per session scan A 0fdbb276fe4e
advpl-tlpp-compile is a skill published in the GitHub repository totvs/engpro-advpl-tlpp-skills (131 stars, last pushed 28d ago), licensed MIT. It adds 214 tokens to every session and 3,655 once invoked, about $0.0011 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…