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 skills add Senavictors/bootstrap-agent-architecture-plugin --skill bootstrap-quarantinegit 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-quarantine)<a href="https://agentmods.dev/skills/senavictors/bootstrap-agent-architecture-plugin/bootstrap-quarantine"><img src="https://agentmods.dev/badge/skills/senavictors/bootstrap-agent-architecture-plugin/bootstrap-quarantine.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 | $0.00129 | $0.01022 |
| Opus 5 | $0.00064 | $0.00511 |
| Sonnet 5 | $0.00026 | $0.00204 |
| Haiku 4.5 | $0.00013 | $0.00102 |
Grade A, and why
bootstrap-quarantine 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 8d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bootstrap-quarantine — triagem assistida de skills externas
O risco que esta skill existe para evitar: uma skill de terceiros carrega convenções testadas pelo autor original, que podem contradizer uma decisão já tomada neste projeto sem que ninguém perceba até o código já ter mudado. A mitigação não é reescrever a skill sozinha — é comparar, relatar, e deixar a decisão final com o usuário.
Entrada
O usuário coloca (ou pede para você colocar) o arquivo original em .agents/quarantine/<nome-da-skill>/SKILL.md.original. Nunca comece a análise a partir de um arquivo já dentro de .claude/skills/ — se ele já estiver lá, pergunte se foi colocado por engano antes de prosseguir.
Procedimento
-
Leia a skill importada inteira — frontmatter e corpo. Identifique, de forma objetiva: que convenções técnicas ela assume (ex.: "usa migrations automáticas", "assume ORM X", "sempre cria um branch por task"), e que sequência de passos ela impõe.
-
Leia as fontes de verdade do projeto:
.agents/test-onboarding.md(seção Constituição) e todos os ADRs comstatus: acceptedem.agents/decisions/. Ignore ADRssuperseded/deprecatedpara fins de conflito (mas cite se a skill importada contradiz algo que já foi superado — pode ser sinal de que a skill é antiga, não necessariamente errada). -
Compare e liste conflitos reais, não hipotéticos — só liste algo se a skill importada de fato assume ou instrui algo que contradiz uma linha específica da Constituição ou de um ADR. Para cada conflito, cite a linha/trecho da skill importada e o ADR ou item da Constituição que ele contradiz.
-
Gere
.agents/quarantine/<nome-da-skill>/relatorio-aderencia.mda partir deassets/templates/agents-hub/quarantine/README.md(modelo de relatório, dobootstrap-init):- Conflitos encontrados — a lista do passo 3. Se não houver nenhum, diga isso explicitamente ("nenhum conflito encontrado contra a Constituição e os ADRs aceitos") em vez de omitir a seção.
- Recomendação — sua sugestão (aprovar sem alteração / aprovar com ajustes / rejeitar), com justificativa objetiva. É uma recomendação, não uma decisão.
- Ajustes propostos — se houver conflito e ele for corrigível com uma edição pontual (não uma reescrita ampla), proponha o trecho específico e a mudança — como um diff pequeno, não um arquivo reescrito inteiro.
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.
- 8d ago First seen · 39 lines · 129 tokens per session scan A f73adb92fd8b
bootstrap-quarantine is a skill published in the GitHub repository Senavictors/bootstrap-agent-architecture-plugin (3 stars, last pushed 7d ago), licensed MIT. It adds 129 tokens to every session and 1,022 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…
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…
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…
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-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…