菜单
Maquina autonoma de seguranca, load testing e LGPD. 6 dimensoes, modo hybrid, convergencia SSS >= 80. Security Certificate + Load Report + Fix PR.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/aibot88/sec_skill_store --skill ag-sentinel命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Guides the creation of agile user stories and Gherkin feature files. Use when the user wants to create a user story, write acceptance criteria, define Gherkin scenarios, or author BDD feature files. This should trigger for requests such as Create a user story; Write a user story; I need to write a user story. Part of cursor-rules-java project
Guía técnica completa para integrar 250+ servicios externos con agentes IA usando Composio. Cubre instalación, autenticación OAuth, gestión de herramientas, triggers y flujos multi-servicio.
Facilitates conversational discovery to create Architectural Decision Records (ADRs) for non-functional requirements using the ISO/IEC 25010:2023 quality model. Use when the user wants to document quality attributes, NFR decisions, security/performance/scalability architecture, or design systems with measurable quality criteria. This should trigger for requests such as Create ADR for Non-functional requirements; Document Non-functional requirements; Capture Non-functional requirements; Generate Non-functional requirements in an ADR. Part of cursor-rules-java project
基于 SOC 职业分类
正在显示 SKILL.md
| name | ag-sentinel |
| description | Maquina autonoma de seguranca, load testing e LGPD. 6 dimensoes, modo hybrid, convergencia SSS >= 80. Security Certificate + Load Report + Fix PR. |
| model | opus |
| context | fork |
| argument-hint | [URL ou path] [--threshold N] [--audit-only] [--resume] [--mode defensive|hybrid|offensive] |
| allowed-tools | Read, Write, Edit, Glob, Grep, Bash, Agent, TaskCreate, TaskUpdate, TaskList, TeamCreate, TeamDelete, SendMessage |
| metadata | {"filePattern":"sentinel-*.json,sentinel-*.md","bashPattern":"sentinel","priority":95} |
/sentinel https://app.example.com # Producao (DEFENSIVE auto)
/sentinel ~/Claude/GitHub/raiz-platform # Local (OFFENSIVE auto)
/sentinel https://preview-xyz.vercel.app # Staging (HYBRID auto)
/sentinel ~/Claude/GitHub/fgts-platform --threshold 90
/sentinel https://app.example.com --audit-only
/sentinel --resume
/sentinel ~/Claude/GitHub/raiz-platform --mode defensive # Override modo
Executa security + performance + compliance AUTONOMO em 5 fases:
| Ambiente | Modo | Payloads | Load Test |
|---|---|---|---|
| Producao | DEFENSIVE | Nenhum | Smoke (5 VUs) |
| Staging | HYBRID | Leves | Load (50 VUs) |
| Local | OFFENSIVE | Completos | Full (200 VUs) |
Agent({
subagent_type: "ag-sentinel",
prompt: "{input do usuario}",
run_in_background: true,
mode: "auto"
})
| Ferramenta | Proposito | Install |
|---|---|---|
| k6 | Load testing | brew install k6 |
| trufflehog | Secrets em git | brew install trufflehog |
| semgrep | SAST analysis | pip3 install semgrep |
Se ausentes: degraded mode (grep manual) ou SKIP da dimensao.
| Artefato | Arquivo |
|---|---|
| Security Certificate | docs/sentinel-certificate-YYYY-MM-DD.md |
| Load Test Report | docs/sentinel-load-report-YYYY-MM-DD.md |
| Fix PR | GitHub PR com hardening |
| Baselines | sentinel-baselines.json |
| State (recovery) | sentinel-state.json |
| KB Update | ~/.claude/shared/sentinel-kb/ |
| Issues backlog | GitHub Issues label sentinel-finding |