What is bootstrap-add-role?

A setup tool for adding a new specialist agent role to a project that already uses a shared agent architecture. It copies the role into the configuration folders used by that project's AI coding tools.

Use it to create or update a specialist role, define what it may do, what requires confirmation, and whether it can block certain changes.

It avoids writing and maintaining the same role definition separately for each tool. It also checks for overlapping roles and asks about safeguards for risky work such as database or infrastructure changes.

bootstrap-add-role — Skill for Claude Code by Senavictors

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.

Any agent

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

Clone the repo

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

Made for: Claude Code.

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-add-role.svg)](https://agentmods.dev/skills/senavictors/bootstrap-agent-architecture-plugin/bootstrap-add-role)

Your own site

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

Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,448 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00099	$0.01448
Opus 5	$0.00049	$0.00724
Sonnet 5	$0.00020	$0.00290
Haiku 4.5	$0.00010	$0.00145

Measured 7d ago against content hash 66db9329b1bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

bootstrap-add-role 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 7d 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-add-role/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

bootstrap-add-role — criar ou atualizar um papel especializado

Entradas necessárias

Nome do papel e seu objetivo principal — se o usuário não deu isso pronto, pergunte: "Qual o nome do novo papel e seu objetivo principal?" Peça também, se não estiver implícito: o que esse papel pode fazer sozinho, o que ele deve recusar/perguntar antes de fazer, e se ele tem poder de veto sobre algo específico (comum em papéis de banco de dados/infra).
Quais adaptadores este projeto usa de fato — leia AGENTS.md/CLAUDE.md existentes ou pergunte, se for a primeira vez. Nunca crie .cursor/ ou .codex/ "só para completar" se o projeto não usa essas ferramentas.

Procedimento

Confira duplicidade. Verifique se já existe um papel com responsabilidade sobreposta em .claude/agents/. Papéis demais com fronteiras confusas são piores que poucos papéis bem definidos — se houver sobreposição real, sugira ajustar o papel existente em vez de criar um novo.
Se o papel envolve uma operação de risco (banco de dados, deploy, infraestrutura), pergunte sobre MCP antes de decidir as ferramentas: "Existe um servidor MCP configurado neste ambiente para este recurso (ex.: um MCP de Postgres/MySQL com escopo de leitura de schema)? Se sim, qual?"
- Se sim: liste esse servidor MCP em tools: no lugar de (ou junto com) Bash, e registre como regra obrigatória do papel que operações destrutivas (DROP, DELETE sem WHERE, etc.) devem passar por esse escopo restrito, nunca por um Bash genérico.
- Se não existir ou o usuário não souber: siga com Bash e a lista explícita de "o que não pode fazer sem perguntar antes" (mecanismo padrão desta arquitetura) — não bloqueie a criação do papel por falta de MCP, e não invente um servidor que não existe.
Escreva o conteúdo canônico em .claude/agents/<papel>.md primeiro (é o mais legível para revisar), a partir de assets/templates/claude/agents/_role-template.md (reaproveitado de bootstrap-init, ou o equivalente já usado no projeto). O corpo deve responder:
- Arquitetura confirmada — citando pastas/namespaces/arquivos reais do projeto, nunca em abstrato.
- Regras obrigatórias, numeradas — com o "porquê" quando não for óbvio.
- Referências de código reais — 2-3 exemplos concretos, não pseudocódigo.
- O que pode fazer e o que não pode fazer sem perguntar antes — a segunda lista é a mais importante para prevenir dano; inclua aqui qualquer poder de veto declarado pelo usuário.

Read the full file on GitHub · 57 lines

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.

7d ago First seen · 57 lines · 99 tokens per session scan A 66db9329b1bf

Subscribe to this mod's changes

bootstrap-add-role is a skill published in the GitHub repository Senavictors/bootstrap-agent-architecture-plugin (3 stars, last pushed 7d ago), licensed MIT. It adds 99 tokens to every session and 1,448 once invoked, about $0.0005 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.

Building agents Claude Code ai ai-agents ai-coding 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

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

evolving-config

Audit and improve AI coding-agent configuration. Use when reviewing or changing Claude Code, Pi, Codex, skill, agent, hook, MCP, permission, package, or generated-export setup. Default is review-only; fixes require explicit user approval or --fix. NOT for score-only instruction review or prompt lint; use…

alexei-led/cc-thingz · 92 tokens

fixing-code

Fix code defects with a reproducible feedback loop, root-cause diagnosis, minimal patch, regression test, and clean verification. Use when debugging, diagnosing, or resolving lint/test/build failures. NOT for behavior-preserving refactors (use refactoring-code), test-suite cleanup without a production bug (use…

alexei-led/cc-thingz · 78 tokens

reviewing-instructions

Use when asked to lint, audit, review, or score AI-facing instruction files such as SKILL.md, AGENT.md, AGENTS.md, CLAUDE.md, platform body.md files, prompt files, rules, policies, and agent-facing references. NOT for plugin manifests, application code review, harness configuration review, ordinary docs, tests, or…

alexei-led/cc-thingz · 80 tokens