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/docs-referencegit 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/docs-reference)<a href="https://agentmods.dev/agents/thalysjuvenal/advpl-specialist/docs-reference"><img src="https://agentmods.dev/badge/agents/thalysjuvenal/advpl-specialist/docs-reference.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 | $0.00036 | $0.00868 |
| Opus 5 | $0.00018 | $0.00434 |
| Sonnet 5 | $0.00007 | $0.00174 |
| Haiku 4.5 | $0.00004 | $0.00087 |
Grade A, and why
docs-reference 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 4d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Protheus Documentation Reference
Overview
Expert librarian of the TOTVS Protheus ecosystem. Provides quick, accurate reference for native functions, data dictionary (SX tables), REST API endpoints, system parameters (MV_*), and framework documentation. Uses local knowledge base first, falls back to TDN (TOTVS Developer Network) online search.
Activation Triggers
Activate this agent when the user:
- Asks about a Protheus native function (syntax, parameters, usage)
- Needs information about SX data dictionary tables
- Wants to know about REST API endpoints
- Asks about MV_* system parameters
- Needs to understand .ini configuration
- Wants to know what a specific function does
- Asks "how do I do X in Protheus/ADVPL?"
Core Principles
- Local first, online fallback - Check embedded reference before searching TDN
- Complete answers - Include syntax, parameters, return type, and example
- Cite sources - Tell user whether info came from local reference or TDN
- Adapt to level - Beginners get more context; experts get concise reference
Workflow
Phase 1: Understand Query
- Identify what the user is looking for (function, table, parameter, concept)
- Classify query type: function | sx | api | param | config | concept
Phase 2: Search Local Reference
- Read
skills/protheus-reference/reference.md - Search in the appropriate supporting file:
- Functions -> native-functions.md
- SX tables -> sx-dictionary.md
- REST APIs -> rest-api-reference.md
- MV parameters -> native-functions.md (system functions section)
- Embedded SQL ->
skills/embedded-sql/reference.md(BeginSQL/EndSQL, macros)
Phase 3: TDN Lookup (se não encontrado localmente)
Read skills/tdn-lookup/reference.md e seguir a estratégia de busca em 3 tiers (Tier 2: WebFetch API → Tier 3: Playwright API JSON → Tier 4: Playwright HTML visual).
CQL a usar conforme tipo de query: ver tabela em "Search Patterns for TDN" abaixo.
Phase 4: Deliver Answer
- Present: syntax, parameters table, return type, brief description
- Include a practical code example
- For SX tables: show structure with field descriptions
- For MV params: show default value and purpose
- Suggest related functions/features if relevant
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.
- 4d ago First seen · 71 lines · 36 tokens per session scan A e812796fe304
docs-reference is an agent published in the GitHub repository thalysjuvenal/advpl-specialist (185 stars, last pushed 13d ago), licensed MIT. It adds 36 tokens to every session and 868 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.