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/kickoffnpx skills add igoruehara/spec-driven --skill kickoffgit 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 | $0.00195 | $0.02680 |
| Opus 5 | $0.00097 | $0.01340 |
| Sonnet 5 | $0.00039 | $0.00536 |
| Haiku 4.5 | $0.00019 | $0.00268 |
Grade A, and why
kickoff 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Kickoff de projeto (Lean Inception + SDD)
Você vai entrevistar, mapear, propor e gerar um roadmap. A primeira decisão é o modo: o trabalho para um projeto que está começando é diferente do de um projeto que já roda.
Princípios de condução
- Pergunte em lotes curtos com
AskUserQuestion(máx. 4 perguntas, 2-4 opções cada). Ofereça sempre um default "(Recomendado)" como primeira opção; aceite "Other" livre. Quando um eixo abrir uma decisão ramificada (escolhas que dependem umas das outras — ex.: arquitetura → bounded contexts → infra), troque o lote por uma sabatina: rode/clarificar. - Não invente decisões de arquitetura. Você propõe opções com trade-offs; quem decide é o usuário.
- Não levante nem proponha ferramentas aqui — isso é a skill
/integracoes. O kickoff só faz a oferta neutra (Fase 0.5) de conectar. Se a/integracoesjá rodou, aproveite os insumos puxados; senão, siga sem e deixe/integracoescomo item do roadmap. - Confirme um resumo antes de gerar arquivos. Gere tudo de uma vez no fim.
- O objetivo final dos dois caminhos é o mesmo: a constituição do projeto + um roadmap acionável para rodar com o time.
Fase 0 — Detectar o modo
- Inspecione o diretório: manifests (
package.json,pyproject.toml,go.mod…),src/com código real, histórico git, docs já preenchidos.- Só o boilerplate / repo vazio → provável greenfield.
- Código de produto existente → provável brownfield.
- Confirme com
AskUserQuestion: Greenfield (começando) · Brownfield (já rodando) · Híbrido (base existe, mas vamos repensar). Roteie conforme a resposta. - Leia
README.mdeCLAUDE.mdpara alinhar com a esteira SDD.
Fase 0.5 — Oferta de integração (neutra)
Conectar MCPs é ortogonal ao kickoff e é trabalho da skill /integracoes. Aqui você faz só
uma oferta neutra — não liste nem proponha ferramentas (quem levanta o ferramental é a
/integracoes; deixe o usuário dizer o que usa de fato lá).
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 · 138 lines · 195 tokens per session scan A 2a81e99be52c
kickoff is a skill published in the GitHub repository igoruehara/spec-driven (213 stars, last pushed 1mo ago), licensed MIT. It adds 195 tokens to every session and 2,680 once invoked, about $0.0010 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.
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…