stack-feedback

A structured way to collect feedback about the @aretw0/pi-stack, including bugs, suggestions, overlaps, and discoveries. A stack is the group of related tools used together.

In plain words
What is it for?
It is for recording what happened, what was expected, how to reproduce a problem, and the package, terminal, operating system, provider, and model involved.
Why use it?
It turns informal reports into consistent information that can be checked and, when appropriate, turned into a repository issue.

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

Made for: Claude Code, Codex.

Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 476 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 $0.00039 $0.00476
Opus 5 $0.00019 $0.00238
Sonnet 5 $0.00008 $0.00095
Haiku 4.5 $0.00004 $0.00048

Measured 2d ago against content hash 96020086bd5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

stack-feedback 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/stack-feedback/SKILL.md · 70 lines

What it actually says

Feedback da Stack

Coleta feedback estruturado sobre o uso da stack @aretw0/pi-stack para orientar a curadoria e priorização do agents-lab.

Quando Usar

  • O usuário encontrou um problema com a stack
  • O usuário tem uma sugestão de melhoria
  • O usuário descobriu um overlap ou conflito entre extensões
  • O usuário quer sugerir uma nova extensão ou skill

Formato

Colete as seguintes informações:

Tipo

  • 🐛 Bug — algo quebrado ou com comportamento inesperado
  • 💡 Sugestão — melhoria ou nova feature
  • 🔄 Overlap — duas extensões/skills fazendo a mesma coisa
  • 📝 Descoberta — padrão, workaround ou insight útil

Contexto

  • Qual pacote/skill/extensão é afetado?
  • Qual terminal e sistema operacional?
  • Qual provider e modelo?

Descrição

O que aconteceu, o que era esperado, o que foi observado.

Reprodução (se bug)

Passos mínimos para reproduzir.

Destino

Após coletar o feedback:

  1. Verificar se já existe issue no repositório:

    gh issue list --repo aretw0/agents-lab --json number,title --jq '.[] | "\(.number): \(.title)"'
    
  2. Se não existe, criar:

    gh issue create --repo aretw0/agents-lab \
      --title "[tipo] descrição curta" \
      --body "conteúdo estruturado"
    
  3. Se é overlap, referenciar as duas partes conflitantes.

Qualidade do Feedback

O feedback deve ser:

  • Específico — não "está estranho", mas "o monitor X não dispara quando Y"
  • Reproduzível — passos claros, não "às vezes acontece"
  • Contextualizado — terminal, OS, provider, modelo
  • Construtivo — problema + sugestão quando possível
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 · 70 lines · 39 tokens per session scan A 96020086bd5e

Subscribe to this mod's changes

stack-feedback is a skill published in the GitHub repository aretw0/agents-lab (11 stars, last pushed 2mo ago), licensed MIT. It adds 39 tokens to every session and 476 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.