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 evaluate-extensiongit 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/evaluate-extension)<a href="https://agentmods.dev/skills/aretw0/agents-lab/evaluate-extension"><img src="https://agentmods.dev/badge/skills/aretw0/agents-lab/evaluate-extension/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/evaluate-extension"><img src="https://agentmods.dev/badge/skills/aretw0/agents-lab/evaluate-extension.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 | $0.00031 | $0.00533 |
| Opus 5.5 | $0.00012 | $0.00213 |
| Sonnet 5.5 | $0.00006 | $0.00107 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade A, and why
evaluate-extension 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 1mo 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.
What it actually says
Avaliar Extensão / Skill Pi
Use este skill para produzir uma avaliação estruturada de qualquer pacote pi — extensão, skill, tema ou prompt.
Quando Usar
- Usuário encontrou um pacote novo e quer saber se vale incluir na stack
- Curadoria ativa: comparando duas soluções que resolvem o mesmo problema
- Preparando uma migração de terceiro para first-party
Processo
1. Coletar Informações
# Ver package.json e manifesto pi
npm view <pacote> --json | head -50
# Clonar ou cachear para leitura
gh repo view <owner/repo> --json description,url
# Ver estrutura
find . -not -path '*/node_modules/*' | head -40
2. Avaliar com Critérios
Produzir avaliação com este scorecard:
| Critério | Score (1-5) | Observação |
|---|---|---|
| Utilidade — resolve um problema real? | ||
| Sobreposição — tem overlap com algo que já temos? | ||
| Qualidade — código limpo, sem hacks? | ||
| Manutenção — commits recentes, issues tratados? | ||
| Composição — funciona bem com o resto da stack? | ||
| Licença — compatível (MIT, Apache)? | ||
| Plataforma — funciona no Windows? |
3. Classificar
- Incluir na stack — adicionar ao pi-stack como dependência
- Referência — manter como inspiração, não incluir diretamente
- Migrar — bom o suficiente para virar first-party
- Rejeitar — overlap sem valor incremental, ou qualidade insuficiente
4. Documentar
Resultado vai para docs/research/pi-extension-scorecard.md ou como issue no repositório.
Aviso sobre Slop
Extensões de baixa qualidade existem no ecossistema. Sinais de alerta:
- Sem README ou com README genérico
- Sem testes ou CI
- Código gerado por LLM sem curadoria visível de pessoas
- Registra tools genéricas demais (ex.: "do anything")
- Conflita com ferramentas built-in sem motivo claro
- Sem licença explícita
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.
- 1mo ago First seen · 68 lines · 31 tokens per session scan A bbe9d8ca750d
evaluate-extension is a skill published in the GitHub repository aretw0/agents-lab (11 stars, last pushed 3mo ago), licensed MIT. It adds 31 tokens to every session and 533 once invoked, about $0.0001 per session on Opus 5.5. 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
Read before writing mcpScript code. Covers tool discovery, the shape of call results (including JSON returned as text), and script limits.
gpt-image-gen
MUST read before generating images. Prompt-crafting guide for gpt-image-2.5 covering tool routing (native imagegeneration server tool vs the generateimage tool), model and quality selection, prompt structure, exact text rendering, reference-image editing, transparent assets, output formats, and multi-turn refinement.
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.
release-notes
Write release notes for a tagged release — a business-impact summary of what changed for the user, plus a thanks section naming every contributor whose commits are in the release. Short by construction.
review-this-branch
Run the nohuman review gate (fresh-session adversarial reviewer + tamper guard) over the current branch or a GitHub pull request, with no server, no database, and no onboarding, and relay the pass/fail checklist.
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.