A guide for identifying a team's tools, such as Jira, Confluence, Notion, GitHub, cloud systems, and monitoring services, and connecting them through MCP. MCP is a standard way for agents to use external tools.

Surveying team tools, gathering project information, configuring MCP connections, documenting integrations, and preparing approved write workflows.

It helps prevent reading from the wrong account and separates safe reading from actions that create or publish data. It also documents validated connections and integration workflows.

integracoes — Skill for Claude Code and Codex by igoruehara: A guide for identifying a team's tools, such as…

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.

agentmods

npx agentmods add skills/igoruehara/spec-driven/integracoes

Any agent

npx skills add igoruehara/spec-driven --skill integracoes

Clone the repo

git clone --depth 1 https://github.com/igoruehara/spec-driven

Made for: Claude Code, Codex.

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/skills/igoruehara/spec-driven/integracoes.svg)](https://agentmods.dev/skills/igoruehara/spec-driven/integracoes)

Your own site

<a href="https://agentmods.dev/skills/igoruehara/spec-driven/integracoes"><img src="https://agentmods.dev/badge/skills/igoruehara/spec-driven/integracoes.svg" alt="Measured on agentmods" height="20"></a>

Per session 149 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,784 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00149	$0.01784
Opus 5	$0.00075	$0.00892
Sonnet 5	$0.00030	$0.00357
Haiku 4.5	$0.00015	$0.00178

Measured 4d ago against content hash 01746d0b8cfe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

integracoes 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 4d 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.

template/.claude/skills/integracoes/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Integrações e MCPs do time

Esta skill é ortogonal ao kickoff — você nem sempre conhece o ferramental ao iniciar o projeto. Rode quando souber. É idempotente: re-executar atualiza docs/engineering/integrations.md.

Quando rodar:

Antes do /kickoff (ideal): os MCPs de leitura alimentam vision/assessment/context-map com dado real (read-first).
Depois, a qualquer momento: quando o ferramental ficou conhecido, ou para configurar a escrita. Se o kickoff já rodou e você puxar insumos novos aqui, ofereça enriquecer os artefatos existentes (context-map, glossary, assessment), citando a origem.

Princípios

Trava de conexão (MCP): conexão já ativa não autoriza uso. Sempre confirme qual conta/workspace ela aponta antes de ler — e reconfirme antes de qualquer escrita. Usar a conta errada (ex.: Notion pessoal no lugar do business) lê contexto errado e, na escrita, vaza dado do projeto para fora do contexto de trabalho.
Ações outward-facing (conectar, publicar, criar issue) → confirme antes.
Tools-aware: só use um MCP disponível na sessão (mcp__<servidor>__*); senão, documente e siga.

Fase 1 — Levantar as ferramentas do time

Lotes de AskUserQuestion:

Gestão e processo: Jira / Trello / Linear / Azure DevOps (+ Scrum / Kanban / Waterfall).
Documentação: Confluence / Notion / Evernote / Google Docs.
Código e CI: GitHub / GitLab / Bitbucket. Cloud: AWS / GCP / Azure.
Observabilidade e comunicação: Datadog / Sentry / Grafana; Slack / Teams.
Libs/APIs: Context7 (lookup na verificação de conhecimento do CLAUDE.md).

Fase 2 — Conexão de leitura (read-first) + trava de segurança

Para as ferramentas de leitura (Confluence, Jira, Notion, GitHub, cloud), verifique se o MCP já está disponível na sessão (mcp__<servidor>__*):

Já conectado → ⚠️ trava de segurança, NÃO use direto. Pode apontar para a conta errada.
1. Identifique a conta/workspace (se o MCP expõe — ex.: buscar o workspace/usuário atual) e mostre ao usuário. Se não der pra verificar, trate como não confirmado.
2. Pergunte (AskUserQuestion): usar esta conexão (workspace X) · reconectar / trocar de conta (pessoal → business) · usar outra ferramenta · pular esta fonte.
3. Só prossiga após confirmação explícita. Registre a conta/workspace em integrations.md.
Não conectado → pergunte se quer conectar. ⚠️ Adicionar um MCP novo (.mcp.json / claude mcp add) normalmente só passa a valer após reconectar a sessão. Ofereça:
- (a) conectar agora → reabrir a sessão → rodar /integracoes (ou /kickoff) de novo; ou
- (b) seguir sem conectar → vira item do roadmap de adoção. Documente em integrations.md.

Read the full file on GitHub · 87 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.

4d ago First seen · 87 lines · 149 tokens per session scan A 01746d0b8cfe

Subscribe to this mod's changes

integracoes is a skill published in the GitHub repository igoruehara/spec-driven (213 stars, last pushed 1mo ago), licensed MIT. It adds 149 tokens to every session and 1,784 once invoked, about $0.0007 per session on Opus 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 2026-08-30.

Building agents

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens