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-install-hooknpx skills add Senavictors/bootstrap-agent-architecture-plugin --skill bootstrap-install-hookgit 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-install-hook)<a href="https://agentmods.dev/skills/senavictors/bootstrap-agent-architecture-plugin/bootstrap-install-hook"><img src="https://agentmods.dev/badge/skills/senavictors/bootstrap-agent-architecture-plugin/bootstrap-install-hook.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 | $0.00138 | $0.01046 |
| Opus 5 | $0.00069 | $0.00523 |
| Sonnet 5 | $0.00028 | $0.00209 |
| Haiku 4.5 | $0.00014 | $0.00105 |
Grade A, and why
bootstrap-install-hook 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bootstrap-install-hook — guardrail anti-vazamento como hook de git real
Diferença central em relação ao guardrail de bootstrap-audit: aquele só bloqueia um commit/handoff que o próprio agente executa dentro da conversa. Este hook roda para qualquer git commit, inclusive um rodado manualmente pelo usuário num terminal separado, fora de qualquer sessão de IA. É por isso que é opt-in — mexe em .git/hooks/, que fica fora do que esta arquitetura normalmente toca.
Antes de instalar — avise o usuário sobre as limitações
Diga isso explicitamente antes de instalar, não depois:
.git/hooks/nunca é versionado pelo Git — mesmo que o script de lógica (.agents/scripts/pre-commit-guardrail.sh) seja commitado e chegue a outro desenvolvedor viagit clone, o hook em si (.git/hooks/pre-commit) não é ativado automaticamente nessa cópia nova. Cada pessoa que clonar o repositório precisa rodar esta skill (ou o passo manual equivalente) uma vez, na própria máquina.- É um filtro por padrões conhecidos via
grep(chave AWS, cabeçalho de chave privada,secret/token/password/api keyatribuídos) — não é uma solução completa de detecção de segredo. Falso negativo é possível para um segredo que não bate nenhum desses padrões; falso positivo é possível (raro, testado contra os casos comuns antes de entregar). git commit --no-verifysempre pula qualquer hook — isso é um comportamento do Git, não uma falha desta implementação. Documente isso para o usuário para que ele saiba que o hook não é uma garantia absoluta.
Procedimento
- Verifique se já existe um hook
pre-commitem.git/hooks/pre-commitno repositório do usuário.- Se não existir: crie
.agents/scripts/pre-commit-guardrail.sh(copiandoassets/pre-commit-guardrail.shdesta skill), dê permissão de execução (chmod +x), e crie.git/hooks/pre-commitcom um shim mínimo:
Dê permissão de execução também no shim.#!/usr/bin/env sh exec .agents/scripts/pre-commit-guardrail.sh - Se já existir (ex.: Husky, ou outro hook do próprio usuário): não sobrescreva. Copie
assets/pre-commit-guardrail.shpara.agents/scripts/pre-commit-guardrail.shmesmo assim, mas mostre ao usuário a linha exata que ele precisa adicionar ao hook existente (.agents/scripts/pre-commit-guardrail.sh || exit 1) e pergunte se quer que você edite o arquivo existente ou prefere fazer isso manualmente.
- Se não existir: crie
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 · 38 lines · 138 tokens per session scan A a025c1363245
bootstrap-install-hook is a skill published in the GitHub repository Senavictors/bootstrap-agent-architecture-plugin (3 stars, last pushed 4d ago), licensed MIT. It adds 138 tokens to every session and 1,046 once invoked, about $0.0007 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
configuring-git-hygiene
Configure safe git workflow hygiene: pre-commit/pre-push hooks, Gitleaks secret scanning, .gitignore rules, local git config, and guardrails. Use when setting up git hooks, gitleaks/git leaks, staged pre-commit checks, pre-push validation, core.hooksPath, .gitignore, or git config best practices. NOT for creating…
committing-code
Create normal git commits with logical grouping. Use when committing, saving changes, creating commits, or grouping work into commits. NOT for amending, rebasing, force-pushing, or rewriting history.
chinese-commit-conventions
中文 commit 与 changelog 配置参考——Conventional Commits 中文适配、commitlint/husky/commitizen 中文模板、conventional-changelog 中文配置。仅在用户显式 /chinese-commit-conventions 时调用，不要根据上下文自动触发。.
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
commit-push-pr
Commit selected local changes, push the branch, and create or update a GitHub pull request with BitFun attribution. Use when the user asks to 提交 PR、提代码、commit and push、开 PR、create a pull request, or wants a Claude Code-like one-command PR publishing flow from BitFun.
commit-push-pr
Commit current changes, push to remote, and create or update a pull request. Use when the user wants to commit and create a PR, push changes and open a pull request, or ship their current work as a PR.