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.
/plugin marketplace add Senavictors/bootstrap-agent-architecture-pluginnpx agentmods add plugins/senavictors/bootstrap-agent-architecture-plugin/plugingit clone --depth 1 https://github.com/Senavictors/bootstrap-agent-architecture-pluginGrade A, and why
bootstrap-agent-architecture 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 yesterday.
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.
What it actually says
{
"$schema": "https://json.schemastore.org/claude-code-plugin.json",
"name": "bootstrap-agent-architecture",
"description": "Orquestrador de arquitetura de agentes de IA para Claude Code, Cursor e Codex — bootstrap de projeto, papéis especializados (com MCP opcional para operações de risco), planejamento e geração de tasks, handoff entre sessões/ferramentas, checagem de Definition of Done com documentação viva (docs/ com estado planejado/real/divergente, atualizada a cada task), auditoria local, triagem assistida de skills externas, e guardrail anti-vazamento como hook de pre-commit real (opcional).",
"version": "2.3.0",
"author": {
"name": "Victor Sena"
},
"homepage": "https://github.com/Senavictors/bootstrap-agent-architecture-plugin",
"repository": "https://github.com/Senavictors/bootstrap-agent-architecture-plugin",
"license": "MIT",
"keywords": [
"agents",
"architecture",
"adr",
"documentation",
"governance",
"claude-code",
"cursor",
"codex"
]
}
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.
- yesterday First seen · 23 lines scan A edee7589c3fe
bootstrap-agent-architecture is a plugin published in the GitHub repository Senavictors/bootstrap-agent-architecture-plugin (2 stars, last pushed 5d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.
Other plugins, from other repositories
backend-architecture
Small, opinionated architecture guide for production backend services across languages and frameworks.
backend-validator
Backend API and WebSocket validation via Hurl, websocat, and oauth2c with OIDC token caching.
code-cleanup
Evidence-first cleanup of agent trajectory residue, dead islands, split-brain authority, stale dependencies, and unnecessary code across repositories.
esp32-cpp
Evidence-first ESP32 firmware guidance for hardware, FreeRTOS, memory, peripherals, and field failures.
peekaboo-macos-validator
Runtime observation, interaction, and visual critique for native macOS interfaces via Peekaboo.
seam-probe
Generic NDJSON probe for embedded-runtime FFI dylibs and Unix-domain sockets.