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 felipenalves/InvOS --skill salvargit clone --depth 1 https://github.com/felipenalves/InvOSWrote 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/felipenalves/invos/salvar)<a href="https://agentmods.dev/skills/felipenalves/invos/salvar"><img src="https://agentmods.dev/badge/skills/felipenalves/invos/salvar/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/felipenalves/invos/salvar"><img src="https://agentmods.dev/badge/skills/felipenalves/invos/salvar.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00059 | $0.00668 |
| Opus 5.5 | $0.00024 | $0.00267 |
| Sonnet 5.5 | $0.00012 | $0.00134 |
| Haiku 4.5 | $0.00006 | $0.00067 |
Grade A, and why
salvar 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 1mo 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/salvar — Salvar no GitHub
Skill de uma função só: garantir que o trabalho do usuário está no GitHub. Fácil pra quem nunca usou git.
Workflow
Primeira vez (repositório não inicializado)
Detectar com git rev-parse --is-inside-work-tree. Se falhar:
-
Perguntar:
"Esse é o primeiro sync. Você já tem um repositório criado no GitHub pra esse workspace?
- Sim, me passa a URL (ex: https://github.com/usuario/nome.git)
- Não, vou criar agora — me dá um nome pro repositório (ex: meu-invos)"
-
Se opção 1: rodar
git init,git add .,git commit -m "Setup inicial do INVOS",git branch -M main,git remote add origin <URL>,git push -u origin main. -
Se opção 2: verificar se o
ghCLI está instalado (gh --version).- Se sim: rodar
git init, criar commit inicial, egh repo create <nome> --private --source=. --push. - Se não: instruir o usuário a instalar
gh(https://cli.github.com/) ou criar o repo manualmente em github.com/new e voltar com a URL.
- Se sim: rodar
Commits seguintes (já configurado)
-
Rodar
git status. Se não tiver mudanças, responder "Tá tudo sincronizado, sem mudança nova" e parar. -
Mostrar o
git statuscurto pro usuário e perguntar:"Vou comitar tudo isso. Quer descrever a mudança em uma frase ou usa o resumo automático?"
-
Se o usuário fornecer mensagem, usar. Se não, gerar uma mensagem baseada nos arquivos alterados (1 linha, formato: "Atualiza X" ou "Adiciona Y" ou "Cria proposta pra cliente Z").
-
git add .→git commit -m "<mensagem>"→git push. -
Confirmar com link do repositório (extrair de
git remote get-url origin):"Sincronizado. Ver no GitHub: "
Regras
- Nunca usar
--forcesem o usuário pedir explicitamente - Nunca rodar
git reset --hardou outras destrutivas sem confirmação clara - Se o push falhar por divergência (remoto tem commits — inclusive no primeiro push, quando o GitHub criou README/licença), avisar o usuário e oferecer
git pull --rebaseantes de tentar de novo - Se o usuário ainda não tiver
gitconfigurado (user.name/user.email), perguntar e configurar comgit config --globalna primeira vez
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.
- 1mo ago First seen · 50 lines · 59 tokens per session scan A 607db706b4c9
salvar is a skill published in the GitHub repository felipenalves/InvOS (8 stars, last pushed 21d ago), licensed MIT. It adds 59 tokens to every session and 668 once invoked, about $0.0002 per session on Opus 5.5. 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
commit-history
List recent git commits linked to agent sessions, optionally filtered by branch or repo. Use when the user asks "show agent commits", "what has the agent shipped", "list linked commits", or wants commits with their session context.
resolve-publish
Commit the validated fix and follow local-only, workflow-owned, or direct PR publication.
commit-messages
Write git commit messages and pull request titles in the WARP format used by the swarms repo.
feature-publish
Commit the feature, write the PR body, publish in the selected mode, and drive the PR.
devtu-github
GitHub workflow for ToolUniverse - push code safely by moving temp files, activating pre-commit hooks, running tests, and cleaning staged files. Use when pushing to GitHub, fixing CI failures, or cleaning up before commits.
release-notes
Draft a release note section from a commit range, grouped by what the reader gets.