What is bootstrap-init?

A project setup tool that creates a shared structure for AI coding agents, including instructions, specialist roles, project state, decisions, tasks, and handoffs. A monorepo means one repository containing multiple related projects, and this tool checks whether the project uses that or another structure.

Use it when starting the agent architecture in a new project or initializing an existing project that has not been set up yet.

It gives agents a common place to read instructions and record work, reducing conflicting assumptions between sessions and tools. It also checks the existing project before creating files and asks before replacing an earlier setup.

bootstrap-init — Skill for Claude Code and Codex by Senavictors: A project setup tool that creates a shared structure…

Install

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.

agentmods

npx agentmods add skills/senavictors/bootstrap-agent-architecture-plugin/bootstrap-init

Any agent

npx skills add Senavictors/bootstrap-agent-architecture-plugin --skill bootstrap-init

Clone the repo

git clone --depth 1 https://github.com/Senavictors/bootstrap-agent-architecture-plugin

Made for: Claude Code, Codex.

Or install bootstrap-agent-architecture, the plugin that ships this one along with the rest of its 9 skills, 1 agent.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/senavictors/bootstrap-agent-architecture-plugin/bootstrap-init.svg)](https://agentmods.dev/skills/senavictors/bootstrap-agent-architecture-plugin/bootstrap-init)

Your own site

<a href="https://agentmods.dev/skills/senavictors/bootstrap-agent-architecture-plugin/bootstrap-init"><img src="https://agentmods.dev/badge/skills/senavictors/bootstrap-agent-architecture-plugin/bootstrap-init.svg" alt="Measured on agentmods" height="20"></a>

Per session 181 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,585 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00181	$0.02585
Opus 5	$0.00090	$0.01293
Sonnet 5	$0.00036	$0.00517
Haiku 4.5	$0.00018	$0.00259

Measured 4d ago against content hash 82fa8dd969cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bootstrap-init 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 4d 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.

plugin/skills/bootstrap-init/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

bootstrap-init — inicialização do projeto

Esta skill monta, uma única vez por projeto, o esqueleto completo da arquitetura de agentes de IA: roteadores, hub de estado (.agents/), constituição/teste de sanidade, e — se decidido — documentação de arquitetura do produto (docs/). Papéis especializados individuais são criados chamando o mesmo procedimento descrito na skill bootstrap-add-role, uma vez por papel — esta skill não duplica aquela lógica, só a invoca em sequência.

Se o projeto já tiver sido inicializado antes (já existe AGENTS.md/.agents/), confirme com o usuário antes de sobrescrever qualquer coisa — esta skill é para o dia zero, não para reprocessar um projeto em andamento.

Passo 1 — Explorar o projeto de verdade

Antes de escrever qualquer arquivo:

ls/find na raiz para entender a estrutura real (linguagens, monorepo ou não).
Leia o .gitignore atual.
Verifique se já existe .claude/, .cursor/, .codex/, .agents/, docs/, e se algo já está rastreado no Git por acidente: git ls-files | grep -iE "\.claude|\.cursor|\.codex|\.agents|CLAUDE\.md|AGENTS\.md".
Identifique os comandos reais de build/test/lint (leia package.json/*.sln/Makefile/Cargo.toml/pyproject.toml/etc. — nunca invente um comando). Se um comando não faz o que o nome sugere (ex.: npm test só roda typecheck), registre essa ressalva explicitamente para usar no passo 4.

Passo 2 — Perguntar ao usuário (não assuma)

Use uma ferramenta de pergunta estruturada se disponível; senão, pergunte em texto e espere a resposta. Três perguntas, sempre, mesmo que o usuário já tenha respondido em outro projeto:

Escopo de versionamento: "Deseja versionar o estado das tarefas (.agents/), a documentação (docs/) e as decisões (.agents/decisions/) no Git, ou mantê-los apenas locais (.gitignore)?" — a resposta pode ser diferente por categoria (ex.: .agents/ local, docs/ versionado); pergunte com essa granularidade se o usuário quiser diferenciar.
Constituição: "Quais são as restrições inegociáveis (Constituição) deste projeto que eu devo sempre respeitar?" — colete quantas o usuário quiser declarar agora; deixe claro que mais podem ser adicionadas depois (bootstrap-audit não invalida isso por estar incompleto no dia 1).
Ferramentas de IA usadas de fato: "Quais ferramentas de IA você usa neste projeto — Claude Code, Cursor, Codex, alguma outra?" — só crie o adaptador das que a resposta confirmar.

Read the full file on GitHub · 87 lines

Files

What ships with it

31 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

4d ago First seen · 87 lines · 181 tokens per session scan A 82fa8dd969cd

Subscribe to this mod's changes

bootstrap-init is a skill published in the GitHub repository Senavictors/bootstrap-agent-architecture-plugin (3 stars, last pushed 3d ago), licensed MIT. It adds 181 tokens to every session and 2,585 once invoked, about $0.0009 per session on Opus 5. 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.

ai ai-agents ai-coding claude-code claude-code-cli claude-code-marketplace

peekaboo

Provides runtime observation and interaction for native macOS interfaces through accessibility state and screenshots. Use when the task depends on visible or interactive state in a running SwiftUI/AppKit app: what is rendered, focused, selected, enabled, reachable through menus/windows/dialogs, or experienced across a…

johnkozaris/jko-claude-plugins · 104 tokens

seam-probe

This skill should be used when testing or debugging an embedded-runtime boundary exposed through a dynamically loaded C-ABI library or Unix-domain socket, including requests to inspect exports, exercise FFI callbacks, send framed messages, reproduce seam crashes or hangs, fuzz a boundary, or correlate probe output…

johnkozaris/jko-claude-plugins · 82 tokens

improving-tests

Improve test design, speed, and coverage with behavior-focused tests, useful seams, characterization tests, TDD, and test refactoring. Use when improving tests, optimizing slow suites, adding coverage, refactoring brittle tests, removing test waste, or working test-first. NOT for fixing production bugs (use…

alexei-led/cc-thingz · 89 tokens

reviewing-code

Use when reviewing changed code, PRs, diffs, or specific files. Finds evidence-backed defects in security, correctness, tests, reliability, performance, maintainability, and docs. Supports quick, standard, deep, team, and external-review modes. NOT for repo-wide architecture review, general codebase exploration…

alexei-led/cc-thingz · 95 tokens

electron-playwright-validator

This skill should be used when a user asks to launch, inspect, automate, test, validate, or debug an Electron desktop UI through Playwright/CDP, including blank renderers, runtime import failures, accessibility snapshots, layout defects, click-through flows, or post-change checks. Not for native macOS or mobile apps…

johnkozaris/jko-claude-plugins · 90 tokens

mobile-flows-maestro

This skill should be used when Maestro is explicitly requested or already present and the task is to author, run, or debug iOS/Android Maestro flows; use Maestro MCP; or handle Maestro selectors, system UI, permissions, Keychain, JavaScript, waits, device state, flakiness, or CI. Evidence includes a .maestro directory…

johnkozaris/jko-claude-plugins · 102 tokens