token-check
Use when the user asks about token usage, session cost, or wants to check optimization effectiveness.
Profile →npx skills add majiayu000/claude-skill-registry --skill token-check --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
Analyze the current Claude Code session for token efficiency: ## Check These 1. **Context loaded**: What CLAUDE.md, rules, and skills are currently loaded? 2. **MCP servers**: How many tool definitions are in context? 3. **Conversation length**: How many turns deep are we? 4. **File reads**: Have we read the same file multiple times? ## Suggest - Whether to `/compact` the conversation - Whether to `/clear` and start fresh - Which MCP servers to disable if unused - Whether CLAUDE.md is too large - Whether rules files should use path-scoping ## Output ``` Session Health Report ───────────────────── Context usage: [estimate] Conversation turns: [count] Suggested action: [compact / clear / continue] Optimization tips: [specific suggestions] ``` <!-- Skill by Huzefa Nalkheda Wala | claude-code-optimizer -->
- Check These
- Suggest
- Output
What does the token-check skill do?
Use when the user asks about token usage, session cost, or wants to check optimization effectiveness.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill token-check --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.