This project uses Opensquad, a multi-agent orchestration framework.
Type /opensquad to open the main menu, or use any of these commands:
/opensquad create— Create a new squad/opensquad run <name>— Run a squad/opensquad help— See all commands
_opensquad/— Opensquad core files (do not modify manually)_opensquad/_memory/— Persistent memory (company context, preferences)skills/— Installed skills (integrations, scripts, prompts)squads/— User-created squadssquads/{name}/_investigations/— Sherlock content investigations (profile analyses)squads/{name}/output/— Generated content and files_opensquad/_browser_profile/— Persistent browser sessions (login cookies, localStorage)
- The
/opensquadskill is the entry point for all interactions - The Architect agent creates and modifies squads
- During squad creation, the Sherlock investigator can analyze reference profiles (Instagram, YouTube, Twitter/X, LinkedIn) to extract real content patterns
- The Pipeline Runner executes squads automatically
- Agents communicate via persona switching (inline) or subagents (background)
- Checkpoints pause execution for user input/approval
- Always use
/opensquadcommands to interact with the system - Do not manually edit files in
_opensquad/core/unless you know what you're doing - Squad YAML files can be edited manually if needed, but prefer using
/opensquad edit - Company context in
_opensquad/_memory/company.mdis loaded for every squad run
Opensquad uses a persistent Playwright browser profile to keep you logged into social media platforms.
- Sessions are stored in
_opensquad/_browser_profile/(gitignored, private to you) - First time accessing a platform, you'll log in manually once
- Subsequent runs will reuse your saved session
- Important: The native Claude Code Playwright plugin must be disabled. Opensquad uses its own
@playwright/mcpserver configured in.mcp.json.