sdd-state
Skill0 starsChanged 54 days agoMITView on GitHub
Manages the project's single execution state and lock. Auto-use when starting, pausing, resuming or finishing SDD work, when the user says "onde paramos", "retomar", "status", "trava", "lock", "o que está rodando", or when any SDD skill needs to know what is in progress. Reads/updates state.md and .sdd/lock and enforces one active feature at a time.
In this repository9 other files it gives its agents.
- sdd-acceptanceSkill
- sdd-analyzeSkill
- sdd-backlogSkill
- sdd-constitutionSkill
- sdd-deliverySkill
- sdd-designSkill
- sdd-discoverySkill
- sdd-reportSkill
- sdd-requirementsSkill
The file
Files
sdd-state
Mantém a fonte única de execução do projeto: state.md (dashboard + histórico, na raiz) e
.sdd/lock (trava reforçada pelo hook sdd-lock). É o que responde "onde paramos" e impede duas
janelas de contexto de se sobrescreverem.
Ações
- status / onde paramos: ler
state.md; dizer feature, etapa, branch, status e a próxima ação. - acquire (iniciar): só se
Status: free(ou lock ausente/expirado). Escrever.sdd/lock(JSON:feature,branch,owner,tsepoch) e o bloco LOCK dostate.mdcomoin_progress; registrariniciado. Se já houver outra featurein_progress, parar e avisar — não começar. - update: avançar etapa/task no bloco LOCK e
Atualizado; registrar a transição no histórico. - pause / block: mudar
Statuse registrar o motivo (não libera o lock). - release (concluir/liberar):
Status: free, limpar o bloco LOCK, remover.sdd/lock, registrarconcluído/liberado.
Regras
- Uma feature ativa por vez. Nada começa enquanto outra estiver
in_progress. state.mde.sdd/locksão a verdade entre janelas — releia sempre antes de agir.- Lock com
ts> 8h pode estar expirado; confirmar com o humano antes de sobrescrever. - Criar
state.mda partir de${CLAUDE_PLUGIN_ROOT}/sdd/templates/state.mdse não existir. - A trava é reforçada pelo hook
sdd-lock(nega Edit/Write fora da branch dona). Edições astate.mde.sdd/seguem liberadas para permitir gestão/override.
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.

