How to bring your Claude Code or Cursor agent into team chat

Описание и применение

Кодовые агенты теперь могут получать контекст из командного чата, публиковать сообщения и выполнять задачи автоматически, используя CLI Pachca и токены, а не копировать данные вручную.

Задача

Coding agents need contextual information from team chat (bug reports, decisions, checklists) that is not in the repository.

Результат

Agents can now access real‑time chat data, post updates, and run automated workflows without manual context injection, improving efficiency and reducing errors.

Рабочий процесс

• Install Pachca CLI (Node.js 20+).
• Sign in with pachca auth login to obtain a short‑lived token stored in the OS keychain.
• Use CLI commands like pachca api ls, pachca api POST /messages --describe, pachca api POST /messages --docs to explore the API.
• Ask the agent to perform tasks such as reading recent messages, summarizing threads, or posting release notes using commands like pachca messages create.
• Optionally add Agent Skills with npx skills add pachca/openapi to pre‑configure common workflows.
• For CI or headless agents, create a bot token and use PACHCA_TOKEN=$PACHCA_SECRET pachca messages create --no-input to avoid interactive login.

Доказательства

Coding agents have become good at reading code, running commands and opening pull requests. But most of the context they need doesn't live in the repository.

Источник

The Pachca CLI needs Node.js 20 or later. You can run it without installing, which works well for agents with temporary environments:

Источник

On your own machine, sign in through the browser: pachca auth login

Источник

Now ask your agent to do something real. It doesn't need instructions on the API, because it can look things up itself:

Источник

For CI and headless mode, create a token in Pachca in advance and pass it through an environment variable from your secrets:

Источник