skills/check-claudemd-size/SKILL.md
This skill should be used when the user says "check claude.md size", "is my claude.md too big", "claude.md token cost", "how big is claude.md", or when triggered automatically on session start to warn about oversized claude.md files.
npx skillsauth add kyuna0312/kyuna_token_saver Check Claude.md SizeInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Measure and report claude.md file sizes. Warn when files exceed optimal token budget. Suggest optimization when needed.
| Size | Status | Action | |------|--------|--------| | < 300 words | Optimal | No action needed | | 300-600 words | Acceptable | Monitor growth | | 600-1,000 words | Bloated | Run optimize-claudemd | | > 1,000 words | Critical | Immediate optimization needed |
# Global
wc -w ~/.claude/CLAUDE.md 2>/dev/null
wc -w ~/.claude/claude.md 2>/dev/null
# Project
wc -w ./CLAUDE.md 2>/dev/null
wc -w ./claude.md 2>/dev/null
CLAUDE.MD SIZE CHECK
====================
Global (~/.claude/CLAUDE.md): [N] words ≈ [N*1.3] tokens [STATUS]
Project (./CLAUDE.md): [N] words ≈ [N*1.3] tokens [STATUS]
Combined constant cost: ~[N] tokens per response
[WARNING if any file is Bloated/Critical]
Run: /context_forge:optimize-claudemd to reduce size
This skill is called by the SessionStart hook. On session start:
Warning format:
⚠ TOKEN SAVER: claude.md is [N] words ([STATUS])
Run /context_forge:optimize-claudemd to reduce by ~[%]%
Common causes of bloat:
references/ filesEmit structured output as LTX rows when reporting file sizes.
@v1:file|words|tokens|level
| Field | Description |
|-------|-------------|
| file | Path to the claude.md file checked |
| words | Raw word count |
| tokens | Estimated tokens (words * 1.3, rounded) |
| level | ok, warn (600–999 words), critical (≥1000 words) |
Example:
@v1:file|words|tokens|level
~/.claude/CLAUDE.md|850|1105|critical
./CLAUDE.md|320|416|ok
tools
This skill should be used when the user asks to "show recent changes", "show forge changelog", "show changelog for <project>", "what did I add this week", "what files did I touch today", "what packages keep recurring", "what drifts from the template", "review template suggestions", "show pending forge suggestions", "sync forge templates", "apply template suggestion", or "compute back-mapping suggestions". Provides read, drift-discovery, and template back-mapping workflows that wrap the `forge-db` MCP tools (`get_changelog`, `compute_suggestions`, `apply_suggestion`).
development
This skill should be used when the user says "build a wiki", "maintain a wiki", "ingest docs into wiki", "query my wiki", "set up llm wiki", "wiki-based knowledge base", "stop re-reading docs every session", "persistent knowledge base", or "compress my docs into wiki pages".
testing
Use this skill when the user says "/task_brain", "break down this task", "plan this", "decompose this problem", or when a task has multiple moving parts, unclear dependencies, or high ambiguity.
tools
This skill should be used when the user says "optimize settings.json", "tune settings for low tokens", "settings.json for performance", "disable auto memory", "configure for token savings", "minimal context window settings", or "settings taking too many tokens".