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 aretw0/agents-lab --skill cultivate-primitivegit 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/cultivate-primitive)<a href="https://agentmods.dev/skills/aretw0/agents-lab/cultivate-primitive"><img src="https://agentmods.dev/badge/skills/aretw0/agents-lab/cultivate-primitive/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/aretw0/agents-lab/cultivate-primitive"><img src="https://agentmods.dev/badge/skills/aretw0/agents-lab/cultivate-primitive.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 | $0.00039 | $0.00739 |
| Opus 5 | $0.00019 | $0.00369 |
| Sonnet 5 | $0.00008 | $0.00148 |
| Haiku 4.5 | $0.00004 | $0.00074 |
Grade A, and why
cultivate-primitive 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 10d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cultivar uma Primitiva
Uma primitiva é um bloco reutilizável que resolve um problema recorrente no trabalho com agentes. Este skill guia o processo de identificação, experimentação e formalização.
Quando Usar
- Um padrão aparece em mais de um contexto
- Uma solução ad hoc se repetiu 3+ vezes
- O usuário diz "seria bom se o pi soubesse fazer X sempre"
Processo
1. Nomear e Descrever
Pergunte ao usuário:
- O que esta primitiva resolve?
- Quando ela é necessária?
- Como funciona hoje (de forma manual ou improvisada)?
2. Classificar a Forma
Antes de promover uma forma ampla, aplique reality-check quando a primitiva afetar usuários, governança, segurança, package manager, workers/providers, publicação ou contratos distribuídos.
| Forma | Quando usar |
|---|---|
| Skill | Instruções recorrentes que o agente segue |
| Extension | Hooks, tools, UI ou estado persistente |
| Prompt template | Atalho para prompts frequentes |
| Convenção | Estrutura de diretório, naming, padrão de arquivo |
| Monitor | Comportamento que precisa ser observado e corrigido |
3. Experimentar
Crie um experimento em experiments/YYYYMM-nome-descritivo/:
mkdir -p experiments/$(date +%Y%m)-nome-do-experimento
Documente:
- Hipótese
- Setup
- Resultado
- Decisão (promover, iterar, ou descartar)
4. Formalizar
Se o experimento é positivo:
- Criar o artefato (skill, extensão, etc.) em
packages/ - Adicionar ao
.pi/settings.jsondo projeto - Testar com
/reload - Documentar a proveniência e as decisões no README do pacote
5. Solicitar Feedback
Se a primitiva é para a stack (@aretw0/pi-stack):
- Criar PR com a mudança
- Descrever o problema que resolve
- Incluir antes/depois quando possível
- Solicitar review do maintainer
Anti-padrões
- Primitiva que resolve um problema que só apareceu uma vez
- Abstração prematura — espere pelo terceiro caso
- Skill gigante que mistura várias preocupações
- Extensão onde uma skill bastaria
- Promoção sem prior art, evidência externa/cached ou comparação local quando a decisão afeta superfície distribuída
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.
- 10d ago First seen · 96 lines · 39 tokens per session scan A 230e65b1379d
cultivate-primitive 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 739 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
codex-claude-worker
Translate natural-language user requests into bounded Claude Code worker tasks while Codex or ChatGPT remains the supervisor. Use when the user gives an ordinary prompt and wants Codex to clarify scope, choose a safe work boundary, generate a worker prompt, approve or defer worker execution, read run summaries and…
taiyi-plan
A TaiyiForge planning step that turns a README, product requirements document, or technical plan into a list of separate project changes. Each change includes a suggested work profile, dependencies, and priority.
taiyi-design
A technical-design guide for planning software changes before implementation. It produces a DESIGN.md document comparing at least two approaches and recording the chosen structure and trade-offs.
taiyi-dev
A software-development stage that implements planned tasks using test-driven development, or TDD: write a failing test, make it pass, then improve the code. It checks the task plan, dependencies, file boundaries, and required completion evidence.
taiyi-integration
A project workflow skill for closing a TaiyiForge change and recording it in a CHANGELOG.md file. It checks review results, tests, and the state of the working tree before archiving the change.
taiyi-requirement
A requirements-analysis process that turns a proposed change into a REQUIREMENT.md document. It records user needs, acceptance checks, terminology, triggers, and dependencies, with different levels of detail for different project sizes.