A planning command for describing and organizing a Jira issue with agents that follow a specification-driven development process. It plans the work without writing code.

Use it to define requirements, break down a Jira issue, and prepare an implementation plan.

It helps turn a Jira issue into a clearer development plan before implementation begins.

sdd-plan — Command for Claude Code by leonardoaa/cloud-mcp

Install

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.

Clone the repo

git clone --depth 1 https://github.com/leonardoaa/cloud-mcp

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/leonardoaa/cloud-mcp/sdd-plan/github.svg)](https://agentmods.dev/commands/leonardoaa/cloud-mcp/sdd-plan)

Your own site

<a href="https://agentmods.dev/commands/leonardoaa/cloud-mcp/sdd-plan"><img src="https://agentmods.dev/badge/commands/leonardoaa/cloud-mcp/sdd-plan/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/leonardoaa/cloud-mcp/sdd-plan"><img src="https://agentmods.dev/badge/commands/leonardoaa/cloud-mcp/sdd-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,240 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00018	$0.01240
Opus 5.5	$0.00007	$0.00496
Sonnet 5.5	$0.00004	$0.00248
Haiku 4.5	$0.00002	$0.00124

Measured 2mo ago against content hash adcb1d134a1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sdd-plan 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.

resources/sdd/commands/sdd-plan.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Voce esta executando /sdd-plan para planejar uma issue Jira. Entrada: $ARGUMENTS.

Regras obrigatorias:

Extraia exatamente uma chave no formato PROJ-123. Se estiver ausente ou ambigua, pergunte antes de continuar. Antes do JIRA_GATE, execute a descoberta de peers do bloco multi-projeto: se a chave pertencer a um grupo, aplique o FANOUT e planeje cada membro, na order, executando as regras abaixo por completo dentro do workspace de cada membro; caso contrario, siga em MODO SINGLE sem alteracao.
Execute o JIRA_GATE antes de criar ou alterar docs/sdd/specs: chame jira_get_workspace_binding. Se nao houver vinculo, liste perfis, pergunte qual perfil/projeto usar, vincule e valide novamente. Sem contexto Jira valido, encerre sem gerar planejamento local.
Execute o checkpoint inicial na seguinte sequencia: a. Leia a issue com jira_get_issue. Recuse se o projeto nao corresponder ao binding. b. Calcule um hash normalizado dos campos principais da issue. c. Chame jira_record_sdd_event no pai com eventKey: <ISSUE>/plan/<hash12>/started, eventType: PLAN_STARTED, targetStatus: inProgress e o proximo passo. d. Falha neste checkpoint bloqueia o comando. Nao prossiga.
Consulte anexos. Nesta fase, leia os relevantes diretamente do Jira apenas para avaliacao; nao crie diretorio, asset, spec, workflow ou subtarefa.
Leia .claude/agents/sdd-refinement-reviewer.md e delegue usando exatamente subagent_type: "sdd-refinement-reviewer". Nunca use code, developer ou agente generico.
Se o veredito for BLOCKED, registre PLAN_BLOCKED no pai com a mesma revisao, blockers e proximo passo; pare antes de qualquer escrita local ou subtarefa.
Para refinar, colete respostas do usuario e mostre um patch Jira proposto. Somente apos confirmacao explicita use jira_edit_task; depois releia a issue e repita o REFINEMENT_GATE completo. Resposta em chat sem persistencia no Jira nao libera o planejamento.
O gate so passa com zero blockers, zero NEEDS CLARIFICATION, criterios verificaveis e anexos obrigatorios acessiveis. Warnings aceitos devem virar premissas explicitas e reversiveis.
Somente apos REFINEMENT_GATE: PASS, leia os padroes e crie/retome a pasta. Inicialize ou migre workflow.json schema v2 com runId, planRevision, attempts, eventLedger e pendingJiraEvents.
Execute ATTACHMENT_INGEST: baixe todos os anexos listados para assets/. Use <attachmentId>-<nome-saneado>, removendo diretorios, controles e caracteres fora de [A-Za-z0-9._-]; nunca sobrescreva IDs diferentes.
Grave texto em UTF-8 e decodifique binarios Base64 sem imprimir conteudo em logs. Calcule SHA-256 e gere assets/manifest.json com ID, nome original, path relativo, MIME, tamanhos, hash, status e erro seguro. Nunca execute anexos.
Antes dos agentes, delegue exatamente sdd-jira-coordinator para criar/reconciliar [SDD][SPEC] Specification, [SDD][RESEARCH] Technical Research e [SDD][PLAN] Technical Plan.
Leia sdd-orchestrator.md e delegue exatamente sdd-orchestrator em modo PLAN. Para cada agente, o orquestrador deve transicionar/comentar a subtarefa com TASK_STARTED antes da chamada e TASK_COMPLETED somente apos artefato/check aprovado.14. A sequencia exata e sdd-spec-writer, sdd-researcher, sdd-planner; depois sdd-jira-coordinator reconcilia as TASK-* e a subtarefa [SDD][QA] Quality Review, cuja chave confirmada e registrada em qa.issueKey. Spec com NEEDS CLARIFICATION registra falha e volta ao refinement.
Nao edite codigo, nao crie branch e nao invoque implementador ou QA neste comando.
Grave phase: "READY_TO_BUILD" somente com refinement PASS, checklist PASS, documentos completos, hashes consistentes e subtarefas reconciliadas.

Read the full file on GitHub · 40 lines

Changes

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 · 40 lines · 18 tokens per session scan A adcb1d134a1e

Subscribe to this mod's changes

sdd-plan is a command published in the GitHub repository leonardoaa/cloud-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 1,240 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.

Planning Project management

sdd-plan

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

converge

implement

speckit.bug.fix