plan
Skill0 starsChanged 27 days agoMITView on GitHub
Etapa 2 do Fluxo Smart — gera plano tecnico detalhado baseado na especificacao aprovada
184 other projects use a version of this.
Adopted by
Most recently taken up by
- phuthuycoding/kanban-flowtheir own version, first seen Nov 8, 2026
- PeanutGT/NutsSkillstheir own version, first seen Nov 8, 2026
- domengabrovsek/agent-configtheir own version, first seen Nov 8, 2026
- domengabrovsek/claudetheir own version, first seen Nov 8, 2026
- codewithmukesh/dotnet-claude-kittheir own version, first seen Nov 8, 2026
- joeldevz/skynex-pitheir own version, first seen Nov 8, 2026
Used with
Projects with it also use heartmula, webhook-subscriptions and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
math-incSkillheartmula
Set up and run HeartMuLa, the open-source music generation model family (Suno-like). Generates full songs from lyrics + tags with multilingual support.
Also in 9 projects that use this
Tommy-ywSkillwebhook-subscriptions
Create and manage webhook subscriptions for event-driven agent activation, or for direct push notifications (zero LLM cost). Use when the user wants external services to trigger agent runs OR push notifications to chats.
Also in 5 projects that use this
math-incSkillminecraft-modpack-server
Set up a modded Minecraft server from a CurseForge/Modrinth server pack zip. Covers NeoForge/Forge install, Java version, JVM tuning, firewall, LAN config, backups, and launch scripts.
Also in 5 projects that use this
john-data-chenSkilltouchdesigner-mcp
Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.
Also in 6 projects that use this
gaebalaiSkillcodex-system
PROACTIVELY consult Codex CLI, your highly capable supporter with exceptional reasoning and task completion abilities. Codex is a trusted expert you should ALWAYS consult BEFORE making decisions on: design choices, implementation approaches, debugging strategies, refactoring plans, or any non-trivial problem. When uncertain, consult Codex. Don't hesitate - Codex provides better analysis. Explicit triggers: "think deeper", "analyze", "second opinion", "consult codex".
Also in 3 projects that use this
ibahgatSkillcontext-optimize
Improve context efficiency and cache stability for long or complex sessions.
Also in 3 projects that use this
- +3 more from math-inc
Other versions184 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 184
- Yeachan-Heo/oh-my-codex★ 34ksame name
- crbnos/carbon★ 2.8ksame name
- graphistry/pygraphistry★ 2.6ksame name
- zereight/gitlab-mcp★ 2.1ksame name
- math-inc/OpenGauss★ 1.3ksame name
- kdlbs/kandev★ 1.1ksame name
- suboss87/FDEOps★ 940same name
- codewithmukesh/dotnet-claude-kit★ 808same name
- witnesstodark/mr-mak-workspace★ 718same name
- loongclaw-ai/loongclaw★ 640same name
174 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository28 other files it gives its agents.
- ado-closeSkill
- ado-commentSkill
- ado-getSkill
- ado-refineSkill
- adrSkill
- approve-reviewSkill
- appSkill
- autoSkill
- challenge-specSkill
- completeSkill
- dart-clean-archSkill
- discoverySkill
- fixSkill
- flutter-clean-archSkill
- implementSkill
- jira-refineSkill
- kickoffSkill
- linear-refineSkill
- orcamentoSkill
- post-reviewSkill
- pr-openSkill
- pr-statusSkill
- refineSkill
- reviewSkill
- specifySkill
- statusSkill
- tasksSkill
- verifySkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 167 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 76
Use o workflow tot-plan em vez de planejar sozinho quando qualquer um valer:
“Common” is measured: kept by at least 6 in 10 of the 167 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
1. Detectar projeto
PROJECT_PATH=$(git rev-parse --show-toplevel 2>/dev/null || pwd)
source ~/.claude/bin/get-project.sh
PROJECT_NAME=$(get-project-name)
WF_DIR="$HOME/.claude/workflow/$PROJECT_NAME"2. Verificar pre-requisito
Leia ~/.claude/workflow/$PROJECT_NAME/spec.md. Se nao existir, peca /specify primeiro.
Leia ~/.claude/workflow/$PROJECT_NAME/current.json para contexto do ciclo.
3. Marcar spec como aprovada e capturar metricas
Atualize status para "spec_approved" no current.json (a aprovação da spec é o gate spec do /challenge-spec, ou a invocação direta do /plan).
bash ~/.claude/bin/capture-metrics.sh start plan "$PROJECT_NAME" "$PROJECT_PATH"Guarde o output como STEP_START_TS.
Relatório: início da etapa
python3 ~/.claude/bin/wf-report.py stage-start plan --workflow-dir "$WF_DIR" ${CLAUDE_FLOW_SESSION_ID:+--session "$CLAUDE_FLOW_SESSION_ID"} || true4. Reconhecimento do codebase (OBRIGATORIO)
Antes de planejar, explore o codigo real. Nao planeje no vacuo.
- Convencoes do projeto: leia
CLAUDE.mddo projeto (se existir) eDESIGN.md(se existir). Esses documentos definem padroes obrigatorios. Mapa da org: se existir.map/index.mdno repo ou numa pasta acima (nunca procure abaixo), leia o índice e as notas/gerados relevantes antes de grep/Explore. Nota marcada STALE não é confiável: confira as âncoras. O mapa descreveorigin/development; confira o diff da branch por cima. - Arquitetura existente: explore os diretorios e arquivos mencionados na secao "Estado atual" da spec. Leia os arquivos-chave para entender patterns, abstracoes e convencoes do codebase.
- Componentes reutilizaveis: antes de propor criar algo novo, busque se ja existe componente similar no projeto (grep por nomes, patterns, widgets, services). Liste o que pode ser reutilizado.
- Contratos existentes: se a feature toca APIs, models, ou interfaces existentes, leia-os para entender os contratos atuais.
- Rules e ADRs: leia
.claude/rules/do repo (as que casam com os paths prováveis) e rodepython3 ~/.claude/bin/adr-index.py match "$PROJECT_PATH" <arquivos prováveis>. ADRacceptedé restrição do plano; contrariar um exige propor supersede (/adr supersede), não ignorar.
O plano deve ser fundamentado no codigo real, nao em suposicoes.
5. Consultar lessons learned
Se ~/.claude/projects/$PROJECT_NAME/lessons.md existir, leia-o e aplique as regras como constraints do plano. Erros documentados nao devem ser repetidos.
Lessons sao cross-cycle (propriedade do projeto, nao do ciclo). Por isso vivem em
projects/, nao emworkflow/— sobrevivem aoarchive-cycle.sh.
6. Verificar coerencia com a spec (backtrack check)
Apos explorar o codebase, verifique se a spec ainda faz sentido:
- A spec assume algo que nao existe no codigo? (ex: menciona um componente que foi removido)
- Faltam regras de negocio que ficaram evidentes ao ler o codigo?
- Algum criterio de aceite e inviavel dado o estado atual?
Se encontrar gaps:
- Liste os gaps encontrados claramente
- Proponha as correcoes necessarias na spec
- Pergunte: "Encontrei gaps na spec apos analisar o codebase. Posso atualizar a spec com as correcoes acima antes de prosseguir?"
- Se aprovado, atualize
spec.mde continue - Se rejeitado, siga com a spec original
Se a spec foi atualizada por gaps do código, registre quais. Registre como decisão do orquestrador (best-effort): escreva o texto com Write em $WF_DIR/.decision.md e rode (acrescente --mistake se for um erro seu):
python3 ~/.claude/bin/wf-report.py decision plan --workflow-dir "$WF_DIR" --by orchestrator --text-file "$WF_DIR/.decision.md" || true6b. Modo ToT (Tree of Thoughts orquestrado)
Use o workflow tot-plan em vez de planejar sozinho quando qualquer um valer:
- usuário passou
--tot; - mudança de contrato (API, gRPC, WebSocket, schema, evento) ou novo módulo/package;
- estimativa > 8 arquivos impactados;
- a spec pede uma decisão estrutural que merece ADR (estado, cache, sincronização real-time, navegação).
Sem gatilho, siga para a seção 7. Com gatilho, anuncie em 1 linha ("Plano via ToT: <motivo>") e chame a ferramenta Workflow com name: "tot-plan" e args:
{ "project_path": "<PROJECT_PATH>", "spec_path": "<WF_DIR>/spec.md", "plan_path": "<WF_DIR>/plan.md",
"rules_dir": ".claude/rules", "adr_dir": "docs/adr", "lessons_path": "<se existir>" }Ao receber o resultado: grave-o em $WF_DIR/tot-plan.json (o /complete usa os adr_candidates), mostre vencedor + placar + enxertos em 3 linhas, confira que o plan.md segue o template abaixo e pule para a seção 8.
7. Gerar plano tecnico
Crie ~/.claude/workflow/$PROJECT_NAME/plan.md com exatamente este formato — seja conciso, max 5 items por secao:
# Plano: <Nome da Feature>
## Visao geral
<1-2 frases sobre abordagem>
## Componentes reutilizados
- <componente existente> — <como sera usado>
- <ou "Nenhum — tudo sera criado do zero">
## Arquivos impactados
| Arquivo | Acao | Motivo |
|---------|------|--------|
| path/arquivo.ts | criar/editar/remover | motivo |
## Mudancas de contrato
- <APIs, schemas, tipos alterados — ou "Nenhum">
## Breaking changes
- <ou "Nenhum">
## Ordem de execucao
1. <passo>
## Riscos
- <risco>: <mitigacao>
## Estrategia de testes (TDD)
| Criterio de aceite | Teste | Arquivo |
|--------------------|-------|---------|
| <da spec> | <describe/it> | <path> |
## Decisoes
- <decisao> — segue [[NNNN-adr]] | nova (candidata a ADR): <alternativas descartadas>
- <ou "Nenhuma decisao estrutural">Os paths da "Estrategia de testes" viram o campo tests das tasks e são executados literalmente pelo G0 — use caminhos reais relativos ao repo.
8. Capturar metricas finais — EXECUTE AGORA (obrigatorio)
bash ~/.claude/bin/capture-metrics.sh end plan "$PROJECT_NAME" "$PROJECT_PATH"Relatório: fim da etapa. Escreva com Write um resumo de 3 a 10 linhas em $WF_DIR/.stage-summary.md (nunca interpole texto em shell) e rode:
python3 ~/.claude/bin/wf-report.py stage-end plan --workflow-dir "$WF_DIR" --summary-file "$WF_DIR/.stage-summary.md" || true9. Gate plan
Apresente o resumo do plano em 3-5 linhas.
Gate plan (decisão determinística; nunca leia gates.json):
python3 ~/.claude/bin/wf-report.py gate planskip: atualizestatuspara"plan_approved"nocurrent.json, informe em 1 linha e execute/tasks.ask: ostage-endacima já rodou; faça umAskUserQuestion("Plano aprovado para gerar as tasks?") com as opções:- Aprovar (Recommended): atualize
statuspara"plan_approved"nocurrent.json, execute/tasksna mesma sessão. - Ajustar: o usuário escreve o ajuste em Other; aplique o texto e repita este mesmo gate.
- Rejeitar: rode
stage-end plan --status blocked(mesmo--summary-file), mantenha ostatusdocurrent.jsone encerre o turno.
- Aprovar (Recommended): atualize
- A resposta do usuário vira decisão: escreva-a com Write em
$WF_DIR/.decision.mde rodepython3 ~/.claude/bin/wf-report.py decision plan --workflow-dir "$WF_DIR" --by user --text-file "$WF_DIR/.decision.md" || true.
Nota: quando o usuario aprovar o plano (confirmando ou executando
/tasks), o/tasksdeve setarstatuspara"plan_approved"antes de iniciar.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

