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/nerfaslol/nib-release/setupnpx skills add nerfaslol/nib-release --skill setupgit clone --depth 1 https://github.com/nerfaslol/nib-releaseWhat 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 | $0.00028 | $0.00652 |
| Opus 5 | $0.00014 | $0.00326 |
| Sonnet 5 | $0.00006 | $0.00130 |
| Haiku 4.5 | $0.00003 | $0.00065 |
Grade A, and why
setup 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup do Nerf
Você está preparando um clone novo deste repositório. Execute os passos na ordem e relate o que aconteceu de verdade — se um passo falhar, pare nele e diga qual foi o erro em vez de seguir em frente.
1. A versão do Node
node -v
O projeto exige ^20.19.0 ou >=22.12.0 (o Vite 8 não roda em versões mais antigas). Se a versão for menor, pare aqui e diga à pessoa que ela precisa atualizar o Node — nenhum dos passos seguintes vai funcionar, e o erro que eles dão não menciona a versão.
2. Instalar
npm install
O .npmrc liga engine-strict, então uma versão errada de Node falha aqui, com a mensagem certa, em vez de explodir no build depois.
3. Provar que o servidor MCP funciona
npm run mcp:test
São 20 verificações ponta a ponta, contra um diagrama descartável — nada toca o canvas de ninguém. A saída tem que terminar com 20 verificações passaram. Se não terminar, relate a falha e pare.
4. Ligar o MCP
O .mcp.json na raiz já registra o servidor nib. Diga à pessoa, com estas palavras:
O servidor MCP já está registrado. Para as ferramentas aparecerem, reinicie o Claude Code — recarregar não basta. Depois, confira com
/mcp: você deve ver o servidornibconectado, com 18 ferramentas (get_diagram,add_node,batch_apply…).
Se ela usa Claude Desktop em vez do Claude Code, aponte para a seção "Ligar no Claude Desktop" do README.md: o Desktop não lê o .mcp.json e precisa de um caminho absoluto no arquivo de config dele.
5. Dizer o que fazer agora
Feche relatando o que você viu, não o que deveria acontecer. Depois, ofereça:
npm run devsobe o canvas (o app e a API no mesmo processo — não há backend separado para subir).- Não existe
diagram.jsonainda, e isso é o certo: o canvas começa vazio e o arquivo nasce no primeiro traço, ou no primeiroadd_nodeque o agente fizer. - Duas regras ao desenhar pelo MCP, e elas existem porque o arquivo é last-write-wins: passe sempre
expectedVersion, e prefira umbatch_applya N chamadas. A skillnib-canvasdeste repo tem o resto.
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 · 51 lines · 28 tokens per session scan A 737ab962dcb0
setup is a skill published in the GitHub repository nerfaslol/nib-release (0 stars, last pushed 11d ago), licensed MIT. It adds 28 tokens to every session and 652 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…