Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/andregusman-raiz/a-gusman-claude/ag-14-data-engine-cli)<a href="https://agentmods.dev/commands/andregusman-raiz/a-gusman-claude/ag-14-data-engine-cli"><img src="https://agentmods.dev/badge/commands/andregusman-raiz/a-gusman-claude/ag-14-data-engine-cli/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/andregusman-raiz/a-gusman-claude/ag-14-data-engine-cli"><img src="https://agentmods.dev/badge/commands/andregusman-raiz/a-gusman-claude/ag-14-data-engine-cli.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 | $0.01175 |
| Opus 5 | $0.00000 | $0.00588 |
| Sonnet 5 | $0.00000 | $0.00235 |
| Haiku 4.5 | $0.00000 | $0.00118 |
Grade A, and why
ag-14-data-engine-cli scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ag-14-data-engine-cli
Use este comando quando uma plataforma, app, agente ou automacao precisar pedir acesso governado a dados/APIs do Data Engine.
Fase -1: Resolver CLI
Antes de concluir que o CLI data-engine nao existe, verifique:
data-engine --help
Se nao estiver no PATH, use o repo local:
cd /Users/andregusmandeoliveira/Claude/GitHub/data-engine-app
uv run data-engine --help
Se a branch local nao tiver raiz_data_engine/cli/main.py, verifique origin/main:
git fetch origin main --prune
git show origin/main:pyproject.toml | rg "data-engine ="
git ls-tree -r --name-only origin/main | rg "^raiz_data_engine/cli/main.py$"
Nunca diga "CLI nao existe" apenas porque o comando nao esta instalado globalmente. Diferencie:
- CLI nao implementado no codigo;
- CLI implementado, checkout antigo;
- CLI implementado, nao instalado no PATH.
Fase 0: Knowledge Gateway obrigatorio
Antes de responder, mapear, sugerir escopo ou abrir pedido, consulte:
GET /v1/knowledge/llm-context
GET /v1/knowledge/index
GET /v1/agent/contract
Para detalhes:
GET /v1/knowledge/resources/{resource_type}/{resource_id}
Tipos validos:
kpi
provider
contract
panel
endpoint
dbt_model
agent_contract
A fonte canonica e o Knowledge Gateway, compilado de OpenAPI, manifests, registries, contracts, providers, dbt e Alembic.
Trate:
known_gapscomo gaps do discovery plane;known_limitationscomo limitacoes declaradas dos recursos.
Ordem preferida
/v1/knowledge/llm-context/v1/knowledge/index/v1/agent/contract/v1/kpis/searchou/v1/kpis/catalog/v1/agg/canonical/{panel_id}/{metric_id}/openapi.jsonapenas para confirmar contrato tecnico
Raw SQL so como fallback, com source="neon", quando rotas canonicas nao resolverem e o motivo estiver documentado.
Fluxo
- Entenda
$ARGUMENTS. - Resolva o runtime do CLI.
- Consulte Knowledge Gateway.
- Prefira rotas canonicas.
- Busque operacao com
uv run data-engine catalog search. - Gere manifesto com
uv run data-engine access draft.- Para LLM, use
--allow-llm, scope especifico comoread:llm, provider/modelo/budget quando disponiveis.
- Para LLM, use
- Valide com
uv run data-engine access validate. - Faca preview com
uv run data-engine access preview. - Abra pedido com
uv run data-engine access request. - Informe request id, status e pendencia de aprovacao.
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 · 163 lines · 0 tokens per session scan A 7256c828dd23
ag-14-data-engine-cli is a command published in the GitHub repository andregusman-raiz/a-gusman-claude (19 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,175 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
flow-test-webhook
Synthesize executable shell trigger scripts (test-webhook.sh) and instructions to trigger webhook routes.
multi-backend
Backend-focused workflow (Research → Ideation → Plan → Execute → Optimize → Review), Codex-led.
workflow-classify
Classify task size (S/M/L/XL) and recommend the appropriate workflow pipeline.
security-review
A security review procedure based on CWE, a list of common software weaknesses, and STRIDE, a method for identifying threats to a system.
slack-gif-creator
Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives. This skill applies when users request animated GIFs or emoji animations for Slack from descriptions like "make me a GIF for Slack of X doing Y".
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.