Agent
Plan Location: plans/0041-limps-improvements/0041-limps-improvements-plan.md.
Agent
Plan Location: plans/0041-limps-improvements/0041-limps-improvements-plan.md.
Agent
Plan Location: plans/0041-limps-improvements/0041-limps-improvements-plan.md.
Agent
Plan Location: plans/0041-limps-improvements/0041-limps-improvements-plan.md.
Agent
This feature has been moved to a separate plan for cleaner scope separation.
Agent
Plan Location: plans/0041-limps-improvements/0041-limps-improvements-plan.md.
Agent
Define entity and relationship types in TypeScript. Implement SQLite storage layer with efficient indexing.
Agent
Extract entities and relationships from markdown using regex patterns and lightweight NLP. No LLM calls.
Agent
Detect duplicate and similar entities across plans using embedding similarity + fuzzy matching. No LLM reasoning.
Agent
Route queries deterministically with regex patterns. Fuse results with RRF. No LLM in the retrieval loop.
Agent
Watch for file changes, auto-index, and surface conflicts proactively. No query needed — system detects problems automatically.
Agent
Build the primary CLI interface. CLI is the source of truth. MCP and Obsidian wrap CLI.
Agent
Create thin MCP wrappers around CLI commands. MCP tools are just exec('limps ...').
Agent
Document the system-intelligent architecture, CLI reference, and integration with Plan 0028 (Obsidian).
Agent
Build the core skill loading infrastructure that reads SKILL.md files from dist/skills/ with progressive disclosure support.
Agent
Implement CLI commands for skill management: list, show, read.
Agent
Export skills to any supported AI agent's directory structure (Claude, Cursor, Codex, etc.).
Agent
Auto-install skills when @sudosandwich/limps is installed via npm.
Agent
Scaffold new skills from templates with limps skill create.
Agent
Create MCP tools that wrap skill CLI commands (CLI-first pattern).
Agent
Define the .limps/ workspace structure and implement initialization.
Agent
Build the context inheritance engine that resolves cascading context from workspace → project → plan → agent.
Agent
Implement persistent memory for agents that survives across sessions.
Agent
Implement plan-level shared memory for cross-agent learnings.
Agent
Detect stale context files and surface freshness warnings.