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/evaluate-extensionnpx 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.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 | $0.00533 |
| Opus 5 | $0.00015 | $0.00267 |
| Sonnet 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 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.
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.
- 4d 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 2mo ago), licensed MIT. It adds 31 tokens to every session and 533 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
optimization
Use when improving performance, latency, throughput, memory usage, or general efficiency. Start by defining target metrics, measuring comprehensively, attributing bottlenecks, validating with static analysis, and prioritizing macro-optimizations before micro-optimizations.
mcp-scripting
Write mcpScript JavaScript for discovering, inspecting, and calling MCP tools.
senpi-qa
Manual QA harness for the senpi coding agent itself. MUST USE after changing packages/ai, packages/agent, packages/coding-agent, or packages/tui — a green typecheck and npm test are NOT QA. Drives the real CLI from source in an isolated sandbox (never touches /.senpi or real credentials) across four channels: remote…
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.
release-publish
Release, publish, CalVer tag push, npm publish, 배포, 릴리즈 for senpi. Use for the canonical release flow, GitHub tag/release publication, and npm publishing.