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-handoffgit 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-handoff)<a href="https://agentmods.dev/skills/senavictors/bootstrap-agent-architecture-plugin/bootstrap-handoff"><img src="https://agentmods.dev/badge/skills/senavictors/bootstrap-agent-architecture-plugin/bootstrap-handoff.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 | $0.00111 | $0.00864 |
| Opus 5 | $0.00056 | $0.00432 |
| Sonnet 5 | $0.00022 | $0.00173 |
| Haiku 4.5 | $0.00011 | $0.00086 |
Grade A, and why
bootstrap-handoff 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 6d 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bootstrap-handoff — pausa e continuidade
O gatilho é sempre manual. Não existe (e não deveria existir) uma forma confiável de a sessão detectar sozinha "meu orçamento de contexto está acabando" e disparar isso — o usuário decide quando pausar, seja por token, por fim de expediente, ou por qualquer outro motivo.
Entrada opcional
O usuário pode passar um comentário livre junto do pedido (ex.: "faz o handoff — falta só o tratamento de erro da API"). Trate isso como o conteúdo mais confiável para a seção "Próximos passos" — mais confiável que qualquer inferência sua a partir do código.
Procedimento
- Identifique a task ativa. Se houver mais de uma em
.agents/tasks/active/, pergunte qual (não assuma a mais recente). - Rode
git statusegit diff(ou equivalente do VCS do projeto) para capturar exatamente o que está modificado na working tree — isso é mais confiável que confiar na sua própria memória da sessão. - Abra o arquivo da task e atualize, sem apagar o que já existia:
- Registro de execução → Alterações realizadas: o que foi de fato concluído nesta sessão, com evidência (arquivo, comando rodado, resultado).
- Próximos passos imediatos: incorporando o comentário do usuário (se houver) e o que o
git diffmostra como código a meio caminho. - Pendências: qualquer coisa que ficou sabidamente quebrada ou incompleta — não esconda isso para a task parecer mais avançada do que está.
- Preencha (ou atualize)
.agents/handoffs/<task-id>-<data>.mda partir deassets/templates/agents-hub/handoffs/_template.md(dobootstrap-init): objetivo, estado atual, concluído, em andamento, próximos passos, arquivos modificados, comandos executados, falhas atuais, decisões tomadas, e "não refazer" — este último campo é o mais fácil de esquecer e o que mais evita retrabalho na próxima sessão. - Vincule o handoff à task — adicione o link no campo "Handoff" da task ativa.
- Se o guardrail anti-vazamento não rodou recentemente, sugira rodar
bootstrap-auditantes de encerrar — um handoff é um bom momento para pegar um segredo colado por engano antes que ele fique registrado num arquivo que sobrevive à sessão.
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.
- 6d ago First seen · 35 lines · 111 tokens per session scan A 0b131f94002d
bootstrap-handoff is a skill published in the GitHub repository Senavictors/bootstrap-agent-architecture-plugin (3 stars, last pushed 6d ago), licensed MIT. It adds 111 tokens to every session and 864 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…
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…
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…
brainstorming-ideas
Brainstorm ideas and stress-test draft plans before coding. Use when brainstorming, exploring approaches, designing a feature/API/flow, grilling or debating a bounded plan, challenging assumptions, or resolving design-blocking terminology. NOT for implementation task breakdown. NOT for generic technology comparisons…