Persist decisions, specs, and architectural constraints across Claude Code sessions as a context companion. Bootstrap canonical OpenSpec by interactively setting product details, discovering codebase modules via Bash, and mining historical sessions into a module registry. Initialize sessions suggesting recent git changes, load or reconcile prior specs, with hooks automating on edits and session events.
Start the Context Companion for this session. Use when the developer runs /companion or wants to load project spec context, start the sidebar, or orient themselves at the beginning of a session.
Bootstrap the Context Companion canonical spec for a product. Use this skill when the developer runs /seed or asks to bootstrap the companion, initialize the spec, seed the project spec, set up the canonical spec, or start the context companion for the first time. Also triggers when developer says things like "build the module registry", "mine my sessions", "bootstrap from existing sessions", or "set up companion for this project". This skill reads the codebase to build a module registry, mines all historical Claude Code sessions for decisions and rules, and produces a canonical OpenSpec that becomes the source of truth for all companion roles.
Modifies files
Hook triggers on file write and edit operations
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimnpx claudepluginhub nraychaudhuri/anchor --plugin anchorPermanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Intelligent prompt optimization: injects the right context at the right moment so Claude lands a better first output. Clarifies vague prompts with research-based questions, plus targeted nudges for approach selection, plan readability, workflow routing, background execution, subagent routing, output readability, user-decision questions, and plan-mode assessment
Semantic search for Claude Code conversations. Remember past discussions, decisions, and patterns.