By gramatr
Real-time intelligent context engineering that makes every prompt cheaper, faster, and context-aware.
Install or refresh the versioned grāmatr block in CLAUDE.md. Shows a diff and requires explicit user confirmation before writing.
Dispatch verbs — status, update, handoff save|load, project, statusline, help. Single entry point for grāmatr client-side actions.
Real-time intelligent context engineering, in Claude Code.
Inside any Claude Code session, run:
/plugin marketplace add gramatr/claude-plugin
/plugin install gramatr@gramatr-claude-plugin
Restart Claude Code when prompted. OAuth sign-in is handled automatically by Claude Code's connector flow on first use — no API keys, no config files to edit.
That's it. Every prompt from now on is pre-classified, loaded with relevant context from past sessions, and gated with quality criteria before the model responds.
The result: less re-explaining, less drift, more shipped — consistent, auditable AI across every session, tool, and teammate.
A hermetic mirror of the grāmatr Claude Code plugin, regenerated on every release from github.com/gramatr/gramatr. Source of truth is the monorepo; this repo exists so /plugin marketplace add gramatr/claude-plugin resolves cleanly without dragging in the npm postinstall path.
0.22.6
External network access
Connects to servers outside your machine
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 claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub gramatr/claude-plugin --plugin gramatr-headlessMemory compression system for Claude Code - persist context across sessions
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Write feature specs, plan roadmaps, and synthesize user research faster. Keep stakeholders updated and stay ahead of the competitive landscape.
Unified status line for Claude Code with multi-CLI (Claude, Codex, Gemini, z.ai) usage monitoring, context, rate limits, and cost tracking