From tac
Reports Claude context window token utilization, consumption breakdown, health status, and optimization recommendations. Use before complex tasks to ensure headroom.
How this skill is triggered — by the user, by Claude, or both
Slash command
/tac:context-statusThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Show current context window state and consumption analysis.
Show current context window state and consumption analysis.
You are analyzing the current context window state.
Use the /context command to get current context window state.
Report the metrics:
Break down what's consuming context:
Assess context health:
| Utilization | Status | Recommendation |
|---|---|---|
| <50% | Healthy | Continue working |
| 50-70% | Watch | Monitor for bloat |
| 70-85% | Caution | Consider delegation or fresh instance |
| >85% | Action Required | Start fresh instance |
Provide status report:
## Context Status Report
**Utilization:** XX% (XXXXXX / XXXXXX tokens)
**Status:** [Healthy/Watch/Caution/Action Required]
### Consumption Breakdown
- System + Tools: ~XX%
- Conversation: ~XX%
- Files Read: ~XX%
- Tool Results: ~XX%
### Recommendations
- [Specific recommendations based on state]
### Context Health Indicators
- [ ] Fresh instance (low history)
- [ ] Focused context (relevant files only)
- [ ] Controlled outputs (minimal verbosity)
npx claudepluginhub melodic-software/claude-code-plugins --plugin tacAnalyzes Claude Code context window token usage, assesses health via thresholds (HEALTHY to CRITICAL), and recommends optimizations like /compact or /clear.
Shows context token savings, consumption ratio, and per-tool breakdown from context-mode. Displays read-only stats for the session, with no reset capability.
Audits session context weight in Claude Code — estimates tokens from CLAUDE.md, agents, MCP descriptions, rules, skills, and conversation history, reports headroom, and alerts on overflow.