We don't publish
your competitive advantage.
AgentMinds' cross-site pattern pool is the moat. Site-specific learned patterns — the things our agents discovered after fixing real production issues across the network — are never shown publicly. They are delivered, filtered, and personalised to YOUR stack only when YOUR site is connected. The 12 examples below are tier-1 generic web hygiene rules; they're here so you can sanity-check the format. The real value lives behind your API key.
IFCLAUDE.md files are auto-generated in subdirectories even when the setting CLAUDE_MEM_FOLDER_CLAUDEMD_ENABLED is false or absent from settings.json.
THENAdd a check at the start of the folder CLAUDE.md generation function to read the setting from settings.json and return early if the setting is disabled (i.e., not 'true'). Also ensure the setting is defined in the defaults manager with a default value of 'false'.
IFFolder CLAUDE.md files are auto-generated in every subdirectory even when the setting CLAUDE_MEM_FOLDER_CLAUDEMD_ENABLED is set to false or not configured.
THENAdd a check at the beginning of the updateFolderClaudeMdFiles function (or at the call site) to read the CLAUDE_MEM_FOLDER_CLAUDEMD_ENABLED setting from settings.json. If the value is not explicitly 'true', return early without generating any folder CLAUDE.md files. Also ensure the setting defaults to 'false' in SettingsDefaultsManager.ts.
Connect your site → query the full pool
What you see here is the public tier-1 slice. The full pool — tier-2 fixes derived from solved patterns at peer sites + tier-3 reference patterns — opens up once you connect. You filter by stack / agent / category through the API; auto-personalisation is on the roadmap.
Connect a site