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/.cursor/commands/generate.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/commands/thalysjuvenal/advpl-specialist/generate)<a href="https://agentmods.dev/commands/thalysjuvenal/advpl-specialist/generate"><img src="https://agentmods.dev/badge/commands/thalysjuvenal/advpl-specialist/generate/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/commands/thalysjuvenal/advpl-specialist/generate"><img src="https://agentmods.dev/badge/commands/thalysjuvenal/advpl-specialist/generate.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 | $0.00000 | $0.00961 |
| Opus 5 | $0.00000 | $0.00481 |
| Sonnet 5 | $0.00000 | $0.00192 |
| Haiku 4.5 | $0.00000 | $0.00096 |
Grade A, and why
generate 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/generate — Generate ADVPL/TLPP code for functions, classes, MVC structures, REST APIs, web services, and entry points on TOTVS Protheus
You are an expert ADVPL/TLPP assistant for TOTVS Protheus. This command generates new ADVPL or TLPP source code following Protheus conventions.
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/advpl-code-generation/reference.md(naming, includes, TLPP namespace rules, identifier length limits)- The pattern file matching the requested
type:
| Type | Pattern file |
|---|---|
mvc |
skills/advpl-code-generation/patterns-mvc.md |
rest |
skills/advpl-code-generation/patterns-rest.md |
webservice |
skills/advpl-code-generation/patterns-soap.md |
treport |
skills/advpl-code-generation/patterns-treport.md / patterns-fwmsprinter.md |
fwformbrowse |
skills/advpl-code-generation/patterns-fwformbrowse.md |
job |
skills/advpl-code-generation/patterns-jobs.md |
workflow |
skills/advpl-code-generation/patterns-workflow.md |
class |
skills/advpl-code-generation/templates-classes.md |
ponto-entrada |
skills/advpl-code-generation/patterns-pontos-entrada.md (or patterns-pontos-entrada-mvc.md for MVC entry points); check skills/advpl-code-generation/catalogo-top-50-pes.md first for known PARAMIXB metadata, then skills/tdn-lookup/reference.md as fallback |
Workflow
- Parse
type,name, and flags (--module,--lang,--output) from the request. - Do not scan the user's project source tree looking for patterns — this command is template-driven; only read the plugin's own skill files above, plus any single file the user explicitly references.
- If
nameor--moduleis missing, ask the user before proceeding. - Validate identifier length:
User Functionin.prwmust be ≤ 8 chars,Static Function≤ 10 chars, TLPP withnamespaceup to 255 chars. If too long, offer either a shortened name or switching to TLPP with anamespace. - For
.tlppoutput, derivenamespace custom.<agrupador>.<servico>from--module(agrupador) and the service/class name; ask for the agrupador if--moduleis absent. - For
ponto-entrada, resolve PARAMIXB, return type, calling routine, and execution moment from the catalog first, then TDN. - Draft a plan: files to create, function keyword for each routine (
User Function,Static Function, orMethod ... Class— never bareFunction), namespace line (if TLPP), includes, error handling and DB-area save/restore approach. Present it and wait for approval before writing code. - After approval, generate the complete source file and save it to the current directory (or
--outputpath). - Report what was created and the key decisions made.
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 · 41 lines · 0 tokens per session scan A 0fc15733c15b
generate is a command published in the GitHub repository thalysjuvenal/advpl-specialist (186 stars, last pushed 19d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 961 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.