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/igoruehara/spec-driven/nova-featurenpx skills add igoruehara/spec-driven --skill nova-featuregit clone --depth 1 https://github.com/igoruehara/spec-drivenWhat 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 | $0.00094 | $0.01609 |
| Opus 5 | $0.00047 | $0.00805 |
| Sonnet 5 | $0.00019 | $0.00322 |
| Haiku 4.5 | $0.00009 | $0.00161 |
Grade A, and why
nova-feature 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Nova feature (loop SDD)
Abre e conduz uma feature pela esteira do README.md. A spec é o contrato; preencha na
ordem dos gates e pare em cada um para review. Siga as convenções do CLAUDE.md.
Princípios
- Pergunte em lotes curtos com
AskUserQuestion; ofereça defaults "(Recomendado)". Mas quando a ambiguidade for profunda e ramificada (uma decisão depende da outra), troque o lote por uma sabatina — rode/clarificar(uma pergunta por vez, caminhando a árvore) e volte com o entendimento fechado. Especialmente útil nos gates de design e spec. - Não delegue a
spec.md— os critérios de aceite são o contrato; o usuário valida. - Ações outward-facing (criar issue, publicar) → confirme antes.
- Tools-aware: só use um MCP se ele estiver disponível na sessão (
mcp__<servidor>__*); caso contrário, siga sem ele e registre como pendência. - Trava de conexão: MCP já ativo não autoriza uso. Confirme qual conta/workspace a
conexão aponta antes de ler a story, e reconfirme antes de criar issues (escrever na conta
errada — ex.: Jira pessoal vs do projeto — vaza dado). Use a conexão validada no
/kickoffse houver.
Fase 1 — Identidade da feature
- Calcule o próximo número: maior
NNNNemspecs/+ 1, com 4 dígitos (ex.:0002). - Pergunte um nome curto em kebab-case → pasta
specs/NNNN-<nome>/. - (tools-aware) Importar contexto: se Jira/Linear estiver conectado, pergunte se a feature
tem uma story/épico. Se sim, leia a issue e use para semear
product.md; guarde a chave na frontmatter (jira: PROJ-123). Se Confluence/Notion estiver conectado, puxe páginas relacionadas. Se nada de gestão/doc estiver conectado e o usuário quiser puxar insumo, ofereça rodar/integracoesagora (neutro — deixe-o dizer o que usa); se recusar, siga sem e registre a pendência.
Fase 2 — Decidir o tier
Pergunte (gate): "isso introduz decisão difícil de reverter ou nova fronteira de domínio?"
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 · 80 lines · 94 tokens per session scan A d2c7cd24d72a
nova-feature is a skill published in the GitHub repository igoruehara/spec-driven (213 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 1,609 once invoked, about $0.0005 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
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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.