Cursor rule
Multi-agent orchestration plugin for Claude Code — 10 specialized agents, persistent Brain memory, quality gates, continuous QA, wave-based parallel execution, and mechanical enforcement hooks.
Cursor rule
After drafting the implementation plan, apply these five tests to each step. Steps touching 10+ files (filestocreate + filestomodify) MUST pass all five. Steps under 10 files are reviewed at Sarah's judgment but should still pass.
Cursor rule
Eva reads this file at pipeline start alongside pipeline-operations.md to load metric schemas, cost estimation tables, and alert thresholds for telemetry capture.
Cursor rule
JIT-loaded reference. Extracted from pipeline-orchestration.md. Eva loads this file on demand when a pipeline session needs worktree creation, cleanup, or Agent-Teams branching details. The anchor is preserved for downstream references.
Cursor rule
This document defines every XML tag used in atelier-pipeline agent persona files, skill command files, invocation prompts, and shared references. No ad-hoc tags -- if a tag is not listed here, it should not appear in any pipeline file.
Skill Claude CodeCodex
Use when users want to bootstrap the brain with existing project knowledge -- reading ADRs, feature specs, UX docs, commit history, and error patterns to seed institutional memory on a project that already has artifacts on disk. Also use for incremental re-hydration after significant work outside the pipeline.…
Skill Claude CodeCodex
Use when users want to remove or disconnect the mybrain plugin's persistent memory layer. Handles teardown for all database strategies (Docker, local PostgreSQL, remote PostgreSQL), config file removal, and offers a disconnect-only option that preserves the database.
Skill Claude CodeCodex
Use when users want to install or set up the atelier-pipeline multi-agent orchestration system in their project. Bootstraps all agent personas, rules, commands, references, and pipeline state files. Works for new and existing projects.
Skill Claude CodeCodex
Use when users want to remove the atelier-pipeline multi-agent orchestration system from their project. Cleanly removes all installed files, hook registrations, and AGENTS.md pipeline section. Preserves user-created custom agents and retro lessons on request.
Instructions file CodexOpenCode
Instructions for robertsfeir/atelier-pipeline, covering atelier pipeline, tech stack, test commands, source structure and key conventions.
Instructions file
Instructions for robertsfeir/atelier-pipeline, covering atelier pipeline, tech stack, test commands, source structure and key conventions.
Plugin Claude Code
Personal semantic thought storage and retrieval for Claude Code with vector embeddings, ltree scoping, and three-axis scoring.
Plugin Claude Code
Personal semantic thought storage and retrieval with vector embeddings and ltree scoping.
Instructions file
Claude Code instructions for robertsfeir/mybrain, covering mybrain-mcp, project overview, tech stack, source layout and run commands.
Skill Claude CodeCodex
Use when users ask about MyBrain, what it does, how it works, what tools are available, or how to use the personal knowledge base. Covers architecture, tools, deployment modes, and usage.
Skill Claude CodeCodex
Use when users want to install or set up MyBrain -- a personal knowledge base with semantic search. Install is always per-project (local MCP scope); the only user-facing choice is which database backend to connect to (Bundled, Docker, Native, or RDS). Detects and offers to remove deprecated user/project/plugin-scoped…