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/embed-pi-clinpx skills add aretw0/agents-lab --skill embed-pi-cligit clone --depth 1 https://github.com/aretw0/agents-labWhat 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 | $0.00045 | $0.01111 |
| Opus 5 | $0.00023 | $0.00556 |
| Sonnet 5 | $0.00009 | $0.00222 |
| Haiku 4.5 | $0.00005 | $0.00111 |
Grade A, and why
embed-pi-cli 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.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Embed Pi CLI
Use este skill quando o objetivo for tornar um projeto CLI externo capaz de usar as capacidades do pi (orquestração, budget, observabilidade) sem forkar o agents-lab.
Escolha o modelo de integração
Antes de qualquer implementação, identifique qual modelo se aplica:
A — Config embedding (mais simples): o projeto só precisa de uma configuração pré-definida. Distribua .pi/settings.json no repositório.
B — Extension bundle (controle total): o projeto tem comportamentos customizados. Publique um pacote npm com extensões próprias.
C — Subprocess bridge (integração programática): o projeto orquestra pi de fora (CI, pipeline). Invoque pi como subprocesso e consuma sessões JSONL.
D — Message adapter (ex.: Telegram/Matrix/WhatsApp): canal externo envia comandos/steering para o control plane. Trate o canal como UI degradada: ele pode acionar loops, acompanhar checkpoints e receber resumos, mas não é autoridade canônica e não bypassa budget/delivery/verification gates.
Se não tiver certeza, comece com A e evolua para B se precisar de tools/commands próprios.
Referência canônica
Guia completo: docs/guides/pi-embedding-cli.md
Pesquisa técnica: docs/research/pi-embedding-ecosystem-survey.md
Exemplo de extension mínima: packages/pi-stack/extensions/claude-code-adapter.ts
Fluxo recomendado
1) Definir o modelo
Responda:
- O projeto precisa de tools ou commands customizados? → B ou C
- O projeto invoca pi de CI/automação? → C
- Só precisa de configuração? → A
2) Implementar
Para modelo A:
- Criar
.pi/settings.jsoncompackages+ config debudgetPolicyedeliveryPolicy - Documentar no README: pré-requisitos,
pi install, comando de início - Testar com
PI_CODING_AGENT_DIR=/tmp/teste-isolado pi
Para modelo B:
- Criar pacote com estrutura
packages/meu-pi-stack/ - Entry point exporta função
default(pi: ExtensionAPI) - Extensions em
extensions/, skills emskills/ - Publicar como
@meu-org/pi-stacke testar compi install npm:@meu-org/pi-stack
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.
- 2d ago First seen · 104 lines · 45 tokens per session scan A c2b5695d0f24
embed-pi-cli is a skill published in the GitHub repository aretw0/agents-lab (11 stars, last pushed 2mo ago), licensed MIT. It adds 45 tokens to every session and 1,111 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
gpt-control
Use when the user asks to get an independent ChatGPT web review, continue a GPT-Control conversation, inspect a model run, or generate or iterate on an image through a configured browser driver. Not for facts the working tree or a local test can answer directly.
fleet-manager
Use when managing, triaging, restarting, escalating, or summarizing Codewhale Pod runs and workers.
skill-creator
Create or improve codewhale skills. Use when the user wants a new skill, wants to update an existing skill, or needs guidance on when a skill should be a skill versus MCP, hooks, tools, or a plugin scaffold.
mcp-builder
Design, build, configure, or debug Model Context Protocol servers for codewhale, including stdio and HTTP/SSE transports.
extension-creator
Create, scaffold, customize, validate, and locally test Qwen Code extensions. Use when the user wants a new Qwen Code extension, needs help choosing an extension template, wants to add QWEN.md context, commands, skills, agents, MCP servers, settings, hooks, channels, or LSP servers, or asks how to link and test an…
mcp-discovery
Prefer a matching zero-environment local MCP server for specialized tasks, even when built-in shell commands or custom code could also solve them.