cross-stack-intake

A project-starting guide that sorts a new code project into a light, medium, or heavy category and chooses a small first step.

In plain words
What is it for?
Use it to start work on notes, scripts, web or API apps, and large monorepos—a repository containing several related projects—with a focused check and a rollback plan.
Why use it?
It avoids spending too much time exploring an unfamiliar project before knowing what matters. Each first step is meant to be safe to check and undo.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/aretw0/agents-lab/cross-stack-intake
Any agent
npx skills add aretw0/agents-lab --skill cross-stack-intake
Clone the repo
git clone --depth 1 https://github.com/aretw0/agents-lab

Made for: Claude Code, Codex.

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 435 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00036 $0.00435
Opus 5 $0.00018 $0.00217
Sonnet 5 $0.00007 $0.00087
Haiku 4.5 $0.00004 $0.00044

Measured 2d ago against content hash 63c3955d9a52, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cross-stack-intake 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 2d 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.

packages/lab-skills/skills/cross-stack-intake/SKILL.md · 50 lines

What it actually says

Cross-stack intake skill

Use esta skill quando o usuário chegar com um projeto novo (de notas simples até monorepo pesado) e você precisar iniciar com fluidez, baixo custo de token e governança.

Paridade guide-skill

Guide canônico: docs/primitives/project-intake.md Paridade mínima: classificação leve/médio/pesado; primeira fatia local-safe; validação focal + rollback; sem protected auto-selection Última revisão de paridade: 2026-05-01

Receita curta (4 passos)

  1. Classificar o jardim
    • light-notes: markdown/scripts pequenos sem build pesado.
    • app-medium: app API/web com testes e build padrão.
    • monorepo-heavy: múltiplos módulos, CI pesada, acoplamento alto.
  2. Propor primeira fatia
    • uma ação pequena, reversível e audítavel.
  3. Definir gate focal
    • marker-check, leitura estruturada ou teste focal curto.
  4. Definir rollback
    • padrão: git revert commit.

Trilha por perfil

light-notes

  • objetivo: clareza rápida de estrutura e próximo passo útil.
  • saída mínima: 1 melhoria de baixo atrito + validação simples.

app-medium

  • objetivo: escolher comando de validação focal e escopo de arquivo curto.
  • saída mínima: 1 micro-slice com teste focal conhecido.

monorepo-heavy

  • objetivo: isolar 1 módulo/pacote antes de qualquer alteração ampla.
  • saída mínima: 1 micro-slice reversível sem tocar CI/protected scope.

Hard stops

  • não inferir escopo protegido por conveniência;
  • não abrir macro-plano sem primeira fatia executável;
  • não trocar governança por texto longo; manter recommendation/nextAction explícitos.
Changes

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.

  1. 2d ago First seen · 50 lines · 36 tokens per session scan A 63c3955d9a52

Subscribe to this mod's changes

cross-stack-intake is a skill published in the GitHub repository aretw0/agents-lab (11 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 435 once invoked, about $0.0002 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 2026-08-30.