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-doc)<a href="https://agentmods.dev/commands/leonardoaa/cloud-mcp/sdd-doc"><img src="https://agentmods.dev/badge/commands/leonardoaa/cloud-mcp/sdd-doc/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-doc"><img src="https://agentmods.dev/badge/commands/leonardoaa/cloud-mcp/sdd-doc.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 | $0.00020 | $0.00992 |
| Opus 5.5 | $0.00008 | $0.00397 |
| Sonnet 5.5 | $0.00004 | $0.00198 |
| Haiku 4.5 | $0.00002 | $0.00099 |
Grade A, and why
sdd-doc 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.
What it actually says
Voce esta executando /sdd-doc para documentar projetos no Confluence. Entrada: $ARGUMENTS.
Este comando e desacoplado de /sdd-task, /sdd-plan e /sdd-build: nao cria issues, subtarefas, specs, branches nem registra eventos SDD. Ele apenas le o repositorio e grava documentacao no Confluence do mesmo site Atlassian do perfil vinculado.
Regras obrigatorias:
- Execute o
JIRA_GATE: identifique oworkspacePathe chamejira_get_workspace_binding. O binding resolve o perfil e, portanto, o site Confluence (${baseUrl}/wiki). Sem vinculo, liste perfis comjira_list_profiles, pergunte qual perfil usar, vincule comjira_bind_workspacee valide de novo. Sem contexto valido, encerre. - Execute o
MULTI_GATEdo bloco multi-projeto para descobrir quais workspaces vinculados participam. Com 2+ vinculados, confirme com o usuario a lista final de projetos e a ordem. Com 1, siga em modo single. - Confirme com o usuario o nome do produto (titulo da pagina-HUB) e o space Confluence de destino. Chame
confluence_list_spacespara listar as opcoes; aceite tambem uma chave informada diretamente (spaces pessoais tem chave~<accountId>). - AVISO DE SEGREDOS: esta doc grava senhas e chaves em texto claro. Antes de escrever, confirme explicitamente com o usuario que o space escolhido e restrito. Se ele recusar ou o space for aberto, nao grave a secao de segredos.
- Interprete pela frase do usuario se a intencao e criar ou atualizar, mas SEMPRE valide contra o Confluence antes de gravar: chame
confluence_find_page(spaceKey, title)para o HUB e para cada pagina filha. Pagina existente -> atualizar (preservando o que ainda vale e atualizando as secoes); ausente -> criar. Nunca crie cega quando ja existe pagina de mesmo titulo no space. - Trate o HUB primeiro: localize ou crie a pagina-HUB e capture seu
pageId, pois ele e oparentIddas filhas. Monte o HUB conforme o padrao (secao "Pagina-HUB"). - Para cada projeto, na ordem definida, delegue exatamente
subagent_type: "sdd-doc-writer", passando:workspacePathdo projeto,spaceKey,parentId(opageIddo HUB), o titulo da pagina filha, a decisao criar/atualizar ja validada e se a secao de segredos foi autorizada. Nunca usecode,developerou agente generico. Nao userun_in_background. - Depois que todas as filhas existirem, atualize no HUB a tabela "Projetos do produto", a secao "Ambientes" consolidada e o "Indice" com os links das filhas (use
confluence_update_pageno HUB). - Ao final, liste por pagina: titulo, acao (criada/atualizada), URL e projeto correspondente. Relate qualquer projeto pulado e o motivo.
Protocolo de erro: em falha transitoria (timeout, rede, 429, 5xx) repita uma vez a mesma chamada. Em falha definitiva (tool MCP ausente, permissao, input invalido, space nao encontrado), pare e reporte sem gravar paginas parciais. Nunca invente conteudo como fallback.
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 · 32 lines · 20 tokens per session scan A 3bf133d0149a
sdd-doc is a command published in the GitHub repository leonardoaa/cloud-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 992 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.