sdd-task

sdd-task is a command for Claude Code from leonardoaa/cloud-mcp. It costs 12 tokens per session (1,230 once invoked), scanned A, original, MIT.

A command for refining and creating a Jira task in a connected project. Jira is a tool for tracking software work.

In plain words
What is it for?
Use it to create a new task or improve the details of an existing task in Jira.
Why use it?
It helps turn a rough piece of work into a more clearly defined Jira task.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to create a new task or improve the details of an existing task in Jira.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/leonardoaa/cloud-mcp/sdd-task
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.

agentmods badge for sdd-task

README.md
[![agentmods](https://agentmods.dev/badge/commands/leonardoaa/cloud-mcp/sdd-task/github.svg)](https://agentmods.dev/commands/leonardoaa/cloud-mcp/sdd-task)
Your own site
<a href="https://agentmods.dev/commands/leonardoaa/cloud-mcp/sdd-task"><img src="https://agentmods.dev/badge/commands/leonardoaa/cloud-mcp/sdd-task/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.

agentmods 80×15 button for sdd-task

Your own site · 80×15
<a href="https://agentmods.dev/commands/leonardoaa/cloud-mcp/sdd-task"><img src="https://agentmods.dev/badge/commands/leonardoaa/cloud-mcp/sdd-task.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,230 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00012 $0.01230
Opus 5.5 $0.00005 $0.00492
Sonnet 5.5 $0.00002 $0.00246
Haiku 4.5 $0.00001 $0.00123

Measured 2mo ago against content hash 03197cdede1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sdd-task 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-task.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Voce esta executando o comando /sdd-task.

Objetivo: transformar o pedido do usuario em uma Task Jira clara, verificavel e pronta para planejamento usando as tools Jira do MCP.

Entrada do usuario:

$ARGUMENTS

Fluxo obrigatorio:

  1. Execute o JIRA_GATE: identifique o workspacePath e chame jira_get_workspace_binding antes de analisar o pedido ou escrever qualquer arquivo. Em seguida execute o MULTI_GATE.
  2. Se nao houver vinculo, liste os perfis com jira_list_profiles, pergunte qual perfil e projeto usar e chame jira_bind_workspace. Nao escolha um Jira por conta propria.
  3. Chame jira_get_workspace_binding novamente. Prossiga somente depois de receber perfil habilitado, projeto e customFieldMap. Se a vinculacao falhar ou for recusada, encerre sem criar rascunho local ou issue.
  4. Leia docs/constitution.md e os templates obrigatorios. Use exclusivamente o contexto Jira validado para este workspace.
  5. Inspecione apenas o contexto necessario do projeto para identificar stack, componentes afetados, restricoes, integracoes e comandos de validacao.
  6. Separe fatos fornecidos de inferencias. Nunca invente regra de negocio, prazo, comportamento ou decisao de produto.
  7. Prepare um titulo objetivo, ator/problema/resultado, escopo e de dois a cinco criterios de aceite observaveis em Dado/Quando/Entao. Antecipe regras, permissoes, erros, dados e integracoes relevantes para reduzir bloqueios no /sdd-plan.
  8. Verifique e apresente possiveis problemas: ambiguidades, regras ausentes, cenarios de erro, permissoes, seguranca, dados, integracoes, observabilidade, migracao e impacto em compatibilidade.
  9. Registre perguntas e decisoes pendentes na descricao em Faltou discutir com a equipe. Campos sem resposta nao devem ser preenchidos com fatos inventados.
  10. Para campos personalizados, consulte jiraProfile.customFieldMap do contexto retornado. Passe em fields apenas nomes logicos existentes nesse mapa; o MCP converte esses nomes para os IDs customfield_* do Jira conectado. Use o argumento dedicado acceptanceCriteria quando esse alias estiver configurado.
  11. Mostre ao usuario o payload final resumido e solicite confirmacao explicita antes de qualquer escrita no Jira.
  12. Somente apos a confirmacao, chame jira_create_task com workspacePath, summary, description, acceptanceCriteria e fields aplicaveis ao perfil conectado.
  13. Ao final, informe chave Jira, campos preenchidos, campos nao configurados, pendencias registradas e sugira /sdd-plan <ISSUE-KEY>.

MODO MULTI (somente quando o MULTI_GATE confirmou dois ou mais projetos e o usuario aprovou distribuir a feature):

M1. Defina um groupId no formato grp-<YYYYMMDD>-<slug-curto> derivado do pedido. M2. Para cada membro aprovado, refine uma task com escopo proprio daquele projeto: reaproveite os passos 4 a 10 usando o workspacePath e o contexto Jira daquele membro. Backend concentra API, dados e regras; frontend concentra UI e integracao; bibliotecas concentram componentes reutilizaveis. Nunca duplique o mesmo escopo em projetos diferentes. M3. Mostre um unico payload consolidado com todas as tasks propostas (uma por projeto) e solicite UMA confirmacao explicita para o conjunto. M4. Somente apos a confirmacao, crie as tasks na ordem definida chamando jira_create_task por membro, cada uma com seu workspacePath e incluindo fields.labels com o valor sdd-group:<groupId>. Colete as chaves retornadas. M5. Depois que TODAS as chaves foram confirmadas, crie os links nativos entre as tasks do grupo: para cada par distinto, chame jira_link_issues com o workspacePath da issue de origem, issueKey da origem e targetIssueKey do par, usando linkType: "Relates". Basta um link por par (o Jira registra os dois sentidos). Falha de link nao apaga tasks ja criadas: relate o par que ficou sem link e siga. M6. Depois dos links, grave o group.json identico em docs/sdd/specs/<ISSUE-KEY>/group.json de cada membro, conforme o esquema do bloco multi-projeto. Nao grave nenhum group.json antes de ter todas as chaves. M7. Ao final, liste as chaves criadas por projeto, o groupId, os labels aplicados, os links criados e sugira /sdd-plan <qualquer-chave-do-grupo>. Qualquer falha de criacao de task interrompe o conjunto: relate o que ja foi criado, nao grave group.json parcial e nao invente vinculos.

Read the full file on GitHub · 46 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.

  1. 2mo ago First seen · 46 lines · 12 tokens per session scan A 03197cdede1a

Subscribe to this mod's changes

sdd-task is a command published in the GitHub repository leonardoaa/cloud-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 1,230 once invoked, about $0.0000 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.