Cozempic
Skill Verified ActiveAnalyze Claude Code session bloat — shows token count, context usage %, and bloat breakdown. Use when the user asks about session size, context usage, or when you notice the context window is getting full.
Optimize Claude Code sessions by removing bloat, saving tokens, and protecting agent coordination from context loss.
Features
- Session bloat analysis and breakdown
- Automated context window pruning with 18 strategies
- Guard daemon for continuous session monitoring
- Agent Teams state protection during compaction
- Behavioral digest for persistent corrections
- Doctor checks for session corruption diagnosis and fixing
- Token-aware diagnostics and context % bar
- Auto-detection of 200K and 1M context windows
Use Cases
- When asked about session size, context usage, or token counts.
- When noticing the context window is getting full.
- To protect agent coordination state during Claude Code's auto-compaction.
- To extract and persist user corrections to Claude Code's memory.
Non-Goals
- Managing general code quality or linting.
- Performing deployment or infrastructure changes.
- Replacing core Claude Code functionality.
- Operating on data outside of a Claude Code session.
Installation
First, add the marketplace
/plugin marketplace add Ruya-AI/cozempic/plugin install plugin@cozempicQuality Score
VerifiedTrust Signals
Similar Extensions
Guard
100Protect Claude Code sessions from context overflow by running a background daemon that monitors session size and auto-prunes before compaction hits. Use when the user says "guard", "protect session", "context getting long", "prevent compaction", "session management", or is running agent teams that need continuous context protection.
Session Export
100Exports a Claude Code session as a clean, readable markdown transcript. Use when the user wants to export a session, create a transcript, save session history to a file, or says "export this session".
Treat
100Prune bloated session with a prescription. Removes progress ticks, stale reads, duplicate content, and more.
Validate Plugin
100Validate a Claude Code plugin structure, frontmatter, and MCP tool references
Running Claude Code Via Litellm Copilot
100Use when routing Claude Code through a local LiteLLM proxy to GitHub Copilot, reducing direct Anthropic spend, configuring ANTHROPIC_BASE_URL or ANTHROPIC_MODEL overrides, or troubleshooting Copilot proxy setup failures such as model-not-found, no localhost traffic, or GitHub 401/403 auth errors.
Create Command
100Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration