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 novo-projetogit 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/novo-projeto)<a href="https://agentmods.dev/skills/felipenalves/invos/novo-projeto"><img src="https://agentmods.dev/badge/skills/felipenalves/invos/novo-projeto/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/novo-projeto"><img src="https://agentmods.dev/badge/skills/felipenalves/invos/novo-projeto.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 | $0.00070 | $0.00819 |
| Opus 5 | $0.00035 | $0.00409 |
| Sonnet 5 | $0.00014 | $0.00164 |
| Haiku 4.5 | $0.00007 | $0.00082 |
Grade A, and why
novo-projeto 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 11d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/novo-projeto — Pasta de projeto novo com contexto dedicado
Quando o usuário começa um projeto novo (cliente, iniciativa, produto), cria uma pasta com AGENTS.md próprio que herda contexto da raiz e adiciona o que é específico do projeto.
Workflow
Passo 1 — Entrevista (4 perguntas)
- "Qual o nome do projeto ou cliente?"
- "É um cliente novo, projeto interno ou iniciativa pessoal?"
- "Qual o objetivo principal? (uma frase)"
- "Que tipo de entrega vai ter? (ex: ads, site, conteúdo, automação, proposta — pode ser mais de uma)"
Passo 2 — Decidir local
Baseado na resposta 2:
- Cliente novo: criar em
clientes/<Nome>/(ou na pasta equivalente do perfil — lerAGENTS.mdda raiz pra confirmar a convenção) - Projeto interno: criar em
projetos/<nome>/(criarprojetos/se não existir) - Iniciativa pessoal: perguntar onde o usuário prefere
Passo 3 — Estrutura básica
Criar a pasta com:
AGENTS.mddo projeto (instruções herdadas + específicas)CLAUDE.mddo projeto com apenas@AGENTS.md(ponteiro multi-harness)briefing.md(com o que foi coletado na entrevista)- Subpastas conforme as entregas mencionadas (ex: se mencionou "ads e conteúdo", criar
ads/econteudo/)
Passo 4 — Conteúdo do AGENTS.md do projeto
Template:
# [Nome do projeto]
> Projeto criado em [data]. Pasta dedicada — instruções aqui sobrescrevem as da raiz quando relevantes.
## Sobre
[Objetivo da resposta 3]
## Tipo
[Cliente novo / Projeto interno / Iniciativa pessoal]
## Entregas previstas
- [entrega 1 da resposta 4]
- [entrega 2 da resposta 4]
- ...
## Onde salvar o que
- Briefings e contexto: nessa pasta na raiz
- Entregas: cada subpasta criada (ads/, conteudo/, site/, etc.)
## Contexto que herda da raiz
Esse projeto herda automaticamente o tom de voz, marca e contexto do negócio definidos em `_memoria/` e `marca/` da raiz. Não duplicar essas informações aqui.
## Específico desse projeto
[Vazio — preencher com regras que valem só pra esse projeto, conforme for descobrindo]
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.
- 11d ago First seen · 95 lines · 70 tokens per session scan A 5da349943818
novo-projeto is a skill published in the GitHub repository felipenalves/InvOS (6 stars, last pushed 8d ago), licensed MIT. It adds 70 tokens to every session and 819 once invoked, about $0.0003 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
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
bazel-build-optimization
Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.
track-management
Use this skill when creating, managing, or working with Conductor tracks - the logical work units for features, bugs, and refactors. Applies to spec.md, plan.md, and track lifecycle operations.
devtu-docs-quality
TOP PRIORITY skill — find and immediately fix or remove every piece of wrong, outdated, or redundant information in ToolUniverse docs. Wrong code, broken links, incorrect counts, and overlapping instructions must be fixed or removed — never left in place. Runs five phases: (D) static method scan, (C) live code…
shiplog
Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.
taskmarket-delegate
Delegate work to the TaskMarket agent-worker market - browse open tasks, create tasks with explicit authorization, and track/submit work, so an agent can outsource instead of burning inference on unreliable or low-confidence work.