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.
npx agentmods add skills/senavictors/bootstrap-agent-architecture-plugin/bootstrap-plannpx skills add Senavictors/bootstrap-agent-architecture-plugin --skill bootstrap-plangit clone --depth 1 https://github.com/Senavictors/bootstrap-agent-architecture-pluginWrote 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/skills/senavictors/bootstrap-agent-architecture-plugin/bootstrap-plan)<a href="https://agentmods.dev/skills/senavictors/bootstrap-agent-architecture-plugin/bootstrap-plan"><img src="https://agentmods.dev/badge/skills/senavictors/bootstrap-agent-architecture-plugin/bootstrap-plan.svg" alt="Measured on agentmods" 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 | $0.00127 | $0.01121 |
| Opus 5 | $0.00063 | $0.00561 |
| Sonnet 5 | $0.00025 | $0.00224 |
| Haiku 4.5 | $0.00013 | $0.00112 |
Grade A, and why
bootstrap-plan 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 5d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bootstrap-plan — ingestão, decisão de arquitetura e geração de tasks
Esta skill cobre o início do ciclo de vida de uma feature/problema: da entrada crua até tasks prontas em .agents/tasks/backlog/, com a decisão de arquitetura registrada como ADR. Não decide sozinha — toda escolha de opção é do usuário.
Passo 1 — Ingestão
Fonte primária (opcional): GitHub Projects. Se o usuário pedir para puxar de lá e o ambiente tiver gh autenticado (gh auth status) ou um MCP do GitHub conectado, use-o para trazer o texto do item (título, descrição, comentários relevantes). Se gh não estiver disponível ou não autenticado, não trave o fluxo — diga isso ao usuário e peça o texto colado diretamente.
Fonte de fallback (sempre disponível): texto colado manualmente. É a entrada padrão quando não há GitHub Projects configurado — trate como cidadã de primeira classe, não como modo degradado.
Releia .agents/context/CONTEXT.md e .agents/test-onboarding.md (Constituição) antes de propor qualquer coisa — a proposta não pode contradizer uma restrição já registrada sem sinalizar isso explicitamente.
Passo 2 — Propor 3 opções de solução
Cada opção precisa ter, no mínimo:
- Abordagem — 2-3 frases, concreta o suficiente para ser implementável, não um rótulo genérico ("opção conservadora" sem conteúdo).
- Trade-offs — o que se ganha e o que se perde, especificamente para este projeto (citando papéis/camadas reais do
AGENTS.md), não trade-offs genéricos de livro-texto. - Impacto estimado — que papéis (
.claude/agents/) seriam envolvidos, e se toca alguma restrição da Constituição.
Apresente as 3 lado a lado e peça a decisão do usuário. Se nenhuma opção servir, é um sinal válido — pergunte o que está faltando e refaça, não force uma escolha entre 3 ruins.
Passo 3 — Gerar o ADR da decisão
A partir de assets/templates/agents-hub/decisions/_template.md (do bootstrap-init) ou o equivalente já usado no projeto: preencha contexto (o problema original), decisão (a opção escolhida), alternativas consideradas (as outras 2 opções, com o motivo de não terem sido escolhidas), consequências, e plano de adoção. Numere o ADR seguindo o próximo ID disponível em .agents/decisions/. Depois de salvar, rode a regeneração do índice (mesma lógica da checagem 4 de bootstrap-audit) para o README.md de .agents/decisions/ já refletir a nova entrada.
What ships with it
1 file 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.
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.
- 5d ago First seen · 45 lines · 127 tokens per session scan A dcf7a1bcbfba
bootstrap-plan is a skill published in the GitHub repository Senavictors/bootstrap-agent-architecture-plugin (3 stars, last pushed 4d ago), licensed MIT. It adds 127 tokens to every session and 1,121 once invoked, about $0.0006 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.
Other skills, from other repositories
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…
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…
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…
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…
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…
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…