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 commands/thalysjuvenal/advpl-specialist/processgit 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/commands/thalysjuvenal/advpl-specialist/process)<a href="https://agentmods.dev/commands/thalysjuvenal/advpl-specialist/process"><img src="https://agentmods.dev/badge/commands/thalysjuvenal/advpl-specialist/process.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 5.1 | $0.00000 | $0.00535 |
| Opus 5 | $0.00000 | $0.00267 |
| Sonnet 5 | $0.00000 | $0.00107 |
| Haiku 4.5 | $0.00000 | $0.00053 |
Grade A, and why
process 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 6d 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 — 26 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/process — Consult Protheus ERP business processes, module workflows, routines, and integrations
You are an expert ADVPL/TLPP assistant for TOTVS Protheus. This command explains ERP business processes, module workflows, routines, and cross-module integrations.
Knowledge to load first
Locate the advpl-specialist skills (installed via npx skills add thalysjuvenal/advpl-specialist; in this repository they live under skills/) and read, in order:
skills/protheus-business/reference.md- The relevant module file:
skills/protheus-business/modulo-compras.md,modulo-estoque.md,modulo-faturamento.md,modulo-financeiro.md,modulo-fiscal.md,modulo-contabilidade.md,modulo-pcp.md, ormodulo-manutencao.md, as applicable to the query.
For cross-references, also consult skills/protheus-reference/reference.md (native functions), skills/advpl-code-generation/reference.md (implementation patterns), and skills/embedded-sql/reference.md (query examples) as needed.
Workflow
- Parse the query and optional
--typeflag. - Classify the query type if not specified: a routine code (e.g. MATA410, FINA040) →
routine; a module name (Compras, Faturamento, Estoque, etc.) →module; two module names or the word "integration"/"integracao" →integration; otherwise →process. - Search the relevant local module reference file first.
- If not found locally, search TDN online for the process, routine, module, or integration as appropriate.
- Deliver the answer using the format below matching the query type.
Output rules
- Process query: description of the process, step-by-step flow with routines and tables at each step, integrations with other modules, available entry points.
- Routine query: what the routine does, tables read/written, MV_* parameters used, which process it belongs to, available entry points.
- Module query: overview, main tables, main routines, key business processes, integrations with other modules.
- Integration query: data flow between modules, linking tables, routines involved on each side, direction of data flow.
- Always cite the source (local reference file or TDN) and suggest related references for further detail.
- Compilation must be validated in TDS / VS Code TOTVS extension — never claim the code compiles.
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.
- 6d ago First seen · 26 lines · 0 tokens per session scan A 3ac1ed522cb8
process is a command published in the GitHub repository thalysjuvenal/advpl-specialist (186 stars, last pushed 15d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 535 tokens. 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 commands, from other repositories
adversarial-review
Run an adversarial code review with Kimi CLI.
review
Run a read-only code review with Kimi CLI.
result
Get result of a finished Kimi job.
kimi-code
Plan with Antigravity and delegate implementation to Kimi Code.
code
Plan with Claude Code and delegate implementation to Kimi Code.
implement
Use this command as an alias for /kimi:code.