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 thalysjuvenal/advpl-specialist --skill tdn-lookupgit 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/skills/thalysjuvenal/advpl-specialist/tdn-lookup)<a href="https://agentmods.dev/skills/thalysjuvenal/advpl-specialist/tdn-lookup"><img src="https://agentmods.dev/badge/skills/thalysjuvenal/advpl-specialist/tdn-lookup/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/thalysjuvenal/advpl-specialist/tdn-lookup"><img src="https://agentmods.dev/badge/skills/thalysjuvenal/advpl-specialist/tdn-lookup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00133 | $0.00444 |
| Opus 5 | $0.00067 | $0.00222 |
| Sonnet 5 | $0.00027 | $0.00089 |
| Haiku 4.5 | $0.00013 | $0.00044 |
Grade A, and why
tdn-lookup 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 13d 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.
What it actually says
TDN Lookup — Online Search Strategy
This skill defines the standardized fallback strategy for finding official TOTVS documentation on TDN (tdn.totvs.com, a public Confluence Data Center 7.19 site with an unauthenticated REST API) whenever local reference material is insufficient. It specifies a five-tier escalation: Tier 1 always checks the relevant local cache file first (native functions, SX dictionary, common errors, entry points, business modules); Tier 2 queries the Confluence REST search API directly via WebFetch with a CQL query; Tier 3 falls back to Playwright hitting the same API when WebFetch is blocked; Tier 4 uses WebSearch plus Playwright navigation when CQL search yields nothing; Tier 5 is a last-resort manual/visual search on the TDN site itself.
Activate this skill whenever a native function, entry point, error code, or business process is not found (or only partially found) in the local reference files, or whenever the user explicitly asks for official TOTVS documentation. It does not itself contain domain knowledge -- it only orchestrates the search process; the actual native function, entry point, and error catalogs live in protheus-reference, advpl-code-generation, advpl-debugging, and protheus-business.
| Reference file | Read when |
|---|---|
| reference.md | Always -- tier-by-tier search strategy, CQL query construction, HTML/JSON parsing steps, fallback conditions per tier |
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.
- 13d ago First seen · 15 lines · 133 tokens per session scan A d25bf442e7b3
tdn-lookup is a skill published in the GitHub repository thalysjuvenal/advpl-specialist (186 stars, last pushed 22d ago), licensed MIT. It adds 133 tokens to every session and 444 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.
Other skills, from other repositories
advpl-dev
Especialista em desenvolvimento ADVPL/TLPP para o ecossistema TOTVS Protheus. Use esta skill para auxiliar com: escrita e revisão de código ADVPL e TLPP, criação de pontos de entrada (convencional e MVC), desenvolvimento de APIs REST, consultas SQL/Embedded SQL, acesso a tabelas do Protheus, criação de classes OO…
gestor-autonomos
Gestoría y contabilidad para autónomos en España. Usar cuando el usuario necesite calcular IVA trimestral (modelo 303), calcular pagos fraccionados de IRPF (modelo 130), gestionar libro de ingresos y gastos, verificar facturas emitidas o recibidas, calcular retenciones, preparar declaraciones trimestrales, estimar…
repo-first-defense
Auditoría defensiva para repositorios AI-native. Usar SIEMPRE que el usuario quiera revisar un repo antes de lanzar, mergear, actualizar dependencias, migrar package manager, configurar un agente IA, MCP, Claude/Cursor/Codex/OpenClaw, o cuando mencione supply chain, prompt injection, secretos, GitHub Actions…
landing-page-mastery
Sistema experto para crear y optimizar landing pages de alta conversión para productos digitales. Úsala para crear páginas desde cero (SaaS, cursos, ebooks, newsletters, Micro-SaaS), auditar páginas existentes para mejorar conversión, o generar copy persuasivo (PAS, AIDA). Incluye estructuras, copy, diseño, CTAs…
nombre-de-mi-skill
Descripción clara y completa de qué hace esta skill y cuándo debe activarse. Incluye los casos de uso principales y el contexto en el que Claude debe usar esta skill. Sé específico y detallado.
prompt-master
Generates optimized prompts for any AI tool. Use when writing, fixing, improving, or adapting a prompt for LLM, Cursor, Midjourney, image AI, video AI, coding agents, or any other AI tool.