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/aretw0/agents-lab/create-pi-skillnpx skills add aretw0/agents-lab --skill create-pi-skillgit clone --depth 1 https://github.com/aretw0/agents-labWrote 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/aretw0/agents-lab/create-pi-skill)<a href="https://agentmods.dev/skills/aretw0/agents-lab/create-pi-skill"><img src="https://agentmods.dev/badge/skills/aretw0/agents-lab/create-pi-skill.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 | $0.00031 | $0.00826 |
| Opus 5 | $0.00015 | $0.00413 |
| Sonnet 5 | $0.00006 | $0.00165 |
| Haiku 4.5 | $0.00003 | $0.00083 |
Grade A, and why
create-pi-skill 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 4d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Criando uma Skill Pi
Skills são o caminho mais leve para customizar o comportamento do pi. Se o problema é instrução recorrente, comece com skill. Se precisa de hooks, tools, UI ou persistência, vá de extensão.
Estrutura Mínima
skills/minha-skill/
└── SKILL.md
O SKILL.md é obrigatório. Scripts auxiliares são opcionais.
Frontmatter
---
name: minha-skill
description: >
Descrição curta do que a skill faz. Aparece no prompt do pi como contexto
disponível — só a descrição, não o conteúdo completo.
---
name— identificador único, usado no comando/skill:namedescription— o que o pi mostra no system prompt para decidir quando carregar
Conteúdo
O corpo do SKILL.md são as instruções completas. O pi carrega sob demanda quando a tarefa casa com a descrição. Escreva como se estivesse instruindo o agente diretamente:
- Explique quando usar a skill
- Dê exemplos com blocos de código executáveis
- Use comandos bash que o agente pode rodar via
bashtool - Aponte para scripts relativos quando necessário
Com Scripts Auxiliares
skills/minha-skill/
├── SKILL.md
└── scripts/
├── setup.sh
└── validate.mjs
No SKILL.md, referencie scripts com caminhos relativos:
## Setup
\`\`\`bash
./scripts/setup.sh
\`\`\`
Se os scripts têm dependências npm, inclua package.json na pasta de scripts.
Onde Colocar
| Escopo | Localização |
|---|---|
| Projeto | .pi/skills/minha-skill/SKILL.md |
| Global | ~/.pi/agent/skills/minha-skill/SKILL.md |
| Pacote | skills/minha-skill/SKILL.md (com pi.skills no package.json) |
Empacotando como npm
{
"name": "@aretw0/minha-skill",
"keywords": ["pi-package"],
"pi": {
"skills": ["./skills"]
}
}
Publicar:
npm publish --access public
Instalar:
pi install npm:@aretw0/minha-skill
Heurística: Skill vs Extension
| Precisa de... | Use |
|---|---|
| Instruções recorrentes | Skill |
| Exemplos de uso de CLI | Skill |
| Templates de código | Skill |
| Hooks no ciclo de vida do pi | Extension |
| Tools customizadas para o LLM | Extension |
| UI no TUI (widgets, footers) | Extension |
| Persistência de estado | Extension |
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.
- 4d ago First seen · 125 lines · 31 tokens per session scan A 340631ac2ccf
create-pi-skill is a skill published in the GitHub repository aretw0/agents-lab (11 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 826 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.
Other skills, from other repositories
mcp-scripting
Write mcpScript JavaScript for discovering, inspecting, and calling MCP tools.
tmux-manual-qa
Run a single manual tmux-based QA scenario for the todo continuation feature against the real CLI (./pi-test.sh) in an interactive TUI. Captures scrollback, asserts deterministic pass/fail count markers, and cleans up test fixtures. Use only for the manual-qa milestone features.
merge-upstream
Sync a fork branch with an upstream remote using a history-preserving merge. Use this whenever the user says /merge-upstream, merge upstream, sync upstream, sync fork, or wants upstream changes integrated without rebasing or force-pushing.
gpt-image-gen
MUST read before generating images. Detailed prompt-crafting guide for gpt-image models, covering tool routing (native imagegeneration server tool vs the generateimage tool), prompt structure from subject to background, verbatim text rendering, anti-patterns, and the revisedprompt feedback loop for iteration.
pi-package-sandbox-test
Use when verifying that published Pi packages install and load for normal users, including pi.dev package compatibility checks, release validation, Daytona sandbox tests, and package installability audits.
pi-observability-local-dev
Use when developing or reviewing packages/pi-observability dashboard/server changes locally, especially rebuilding dist, restarting the 43190 server, validating UI behavior, or keeping the local dashboard in sync with source edits.