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.
git clone --depth 1 https://github.com/leonardoaa/cloud-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/leonardoaa/cloud-mcp/sdd-build)<a href="https://agentmods.dev/commands/leonardoaa/cloud-mcp/sdd-build"><img src="https://agentmods.dev/badge/commands/leonardoaa/cloud-mcp/sdd-build/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/leonardoaa/cloud-mcp/sdd-build"><img src="https://agentmods.dev/badge/commands/leonardoaa/cloud-mcp/sdd-build.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00017 | $0.01724 |
| Opus 5.5 | $0.00007 | $0.00690 |
| Sonnet 5.5 | $0.00003 | $0.00345 |
| Haiku 4.5 | $0.00002 | $0.00172 |
Grade A, and why
sdd-build 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 2mo 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Voce esta executando /sdd-build para implementar uma issue Jira planejada. Entrada: $ARGUMENTS.
Regras obrigatorias:
-
Extraia exatamente uma chave
PROJ-123. Antes doJIRA_GATE, execute a descoberta de peers do bloco multi-projeto: se a chave pertencer a um grupo, aplique o FANOUT e implemente cada membro, naorder, executando as regras abaixo por completo dentro do workspace de cada membro; caso contrario, siga em MODO SINGLE sem alteracao. Em MODO SINGLE, execute oJIRA_GATEantes de ler ou alterar o workflow: resolva o vinculo; se ausente, permita escolha assistida, vincule e valide novamente. Sem Jira valido, encerre sem executar codigo. -
Leia a issue, confirme o projeto vinculado e somente entao abra constituicao e
docs/sdd/specs/<ISSUE-KEY>/workflow.json. -
Recuse a execucao quando o workflow nao existir, nao registrar
refinement.verdict: "PASS", nao possuir checklist aprovado, contiverNEEDS CLARIFICATION, estiverBLOCKEDou nunca tiver atingidoREADY_TO_BUILD; indique/sdd-plan <ISSUE-KEY>. -
Migre workflow v1 para v2 preservando dados. Antes de trabalhar, descarregue todos os
pendingJiraEvents; falha impede retomada. -
Valide anexos e hashes. Mudanca material exige novo
/sdd-plan. -
Capture
buildStartedAtem ISO-8601 com timezone no momento de inicio real do build, persista noworkflow.jsone registrePHASE_STARTEDno pai com eventKey<ISSUE>/<runId>/r<revision>/build/started,targetStatus: inProgresse o horario de inicio no resumo. -
Delegue exatamente
sdd-orchestratorem modo BUILD. Para cadaTASK-*, use exclusivamentesubagent_type: "sdd-implementer"; para QA,sdd-qa-reviewer; nuncacodeou fallback direto. Apos delegar a fase aosdd-orchestrator, nao escrevaworkflow.jsonate o retorno; a sequencia dos itens 8 a 13 e executada por quem estiver orquestrando. -
Para cada tarefa delegada, siga esta sequencia:
Antes de delegar o agente:
- Capture e persista
startedAtna entrada da tarefa noworkflow.json. - Registre
TASK_STARTEDna subtarefa comtargetStatus: inProgress.
Apos o retorno do agente:
- Capture
finishedAte a observacao final. - Registre
TASK_COMPLETEDcom arquivos, validacoes etargetStatus: donesomente quando tudo passar.
- Capture e persista
-
Tarefas consecutivas do mesmo lote marcadas
[P]emtasks.mdpodem ser delegadas em paralelo, no maximo 3 simultaneas, cada uma em seu proprio worktree: registreTASK_STARTEDestartedAtde todas antes de disparar o lote; integre os worktrees sequencialmente, na ordem das tarefas, somente depois de todo o lote retornar. Conflito de merge registraBUILD_BLOCKEDpreservando os worktrees. Se uma tarefa do lote falhar, aguarde o retorno das demais, registre os resultados individuais e so entao bloqueie. Em duvida sobre o isolamento, execute sequencial. -
Depois de cada retorno, consolide evidencias no
workflow.json, incluindo horarios explicitos por tarefa. Se o agente criou worktree isolado, integre/mergeie as alteracoes aprovadas na branch de trabalho atual antes de marcar a tarefa como concluida. Nao repita tarefa concluida; bloqueios reais devem ser registrados na subtarefa correspondente. -
Em qualquer erro, capture
buildFinishedAtem ISO-8601 com timezone, registreTASK_BLOCKEDouTASK_FAILEDna subtarefa eBUILD_BLOCKEDno pai; mantenha a subtarefa aberta e pare imediatamente. O comentario final doBUILD_BLOCKEDdeve informarInicio do build: <buildStartedAt>eFim do build: <buildFinishedAt>. -
Para QA, capture
qa.startedAt, registreQA_STARTEDna subtarefa e no pai; delegue exclusivamentesdd-qa-reviewer, informando o ciclo atual (qa.attempts + 1de no maximo 3). Ao terminar, persistaqa.finishedAt,qa.attempts, status e observacao. -
Em QA
FAILcom correcoes minimas viaveis e dentro do escopo aprovado, execute um ciclo de correcao — no maximo 3 por build: incremente e persistaqa.attempts; registreTASK_PROGRESSna subtarefa de QA com o cicloN/3e os achados; deleguesdd-implementersomente com as correcoes minimas apontadas pelo QA, com a mesma disciplina de worktree e merge do item 8; repita o QA completo. Esgotados os 3 ciclos comFAIL, ou quando a correcao exigir mudanca de escopo, registreQA_FAILEDna subtarefa eBUILD_BLOCKEDno pai e pare. -
QA_FAILEDmantem cards abertos e bloqueia. SomenteQA_PASSEDconclui a subtask. 14b. Antes deBUILD_COMPLETED, confirme que todas as alteracoes dos worktrees dos agentes foram mergeadas na branch de trabalho atual e remova os worktrees temporarios criados para o build. Se algum worktree tiver alteracao nao consolidada, registreBUILD_BLOCKEDe pare. Depois capturebuildFinishedAtem ISO-8601 com timezone e persista noworkflow.json. -
Registre
BUILD_COMPLETEDseguindo esta sequencia: a. CapturebuildFinishedAtem ISO-8601 com timezone. Persista noworkflow.json. b. Monte o resumo textual com:Inicio do build: <buildStartedAt>eFim do build: <buildFinishedAt>- Uma linha por
TASK-*com status final e observacao curta - Uma linha de QA com status, ciclos executados e observacao
- Validacoes executadas e observacoes gerais
c. Chame
jira_record_sdd_eventno pai comeventType: BUILD_COMPLETED,targetStatus: done, o resumo montado emsummarye as validacoes emvalidations. Nao inclua o camporeport; o resumo em texto e suficiente. d. EmBUILD_BLOCKED, nao monte o resumo completo de build; registre apenas o evento com blockers.
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.
- 2mo ago First seen · 58 lines · 17 tokens per session scan A 8d6907bfdf28
sdd-build is a command published in the GitHub repository leonardoaa/cloud-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 1,724 once invoked, about $0.0001 per session on Opus 5.5. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.