ゆる草
@yurukusa
Indie games + Claude Code tooling. Spell Cascade / Azure Flame Dungeon creator. cc-safe-setup (910 safety hooks). Non-engineer shipping with AI.
33
Published Tools
57
Total Stars
3
Weekly Downloads
31
GitHub Followers
630
Public Repos
89/100
Avg Security
Published Tools
2 MCP Servers30 Skills1 Agentacross 3 categoriesyurukusa
One command to make Claude Code safe. Prevents rm -rf disasters, secret leaks, broken deployments. 695 hooks · 9,200+ tests · Built from 800hrs of autonomous operation. Token optimization: token-book.html
...moreyurukusa
GitHub-style AI activity heatmap from Claude Code proof-log files
yurukusa
Watch your active Claude Code session in real-time. Token usage, cache efficiency, burn rate, and cost estimate. Zero dependencies.
...moreyurukusa
MCP server: Japanese law, corporations & statistics as English metadata for AI agents. Live: japan-data-mcp.netlify.app/mcp
...moreyurukusa
See how much of your Claude Code time is YOU vs AI autonomous subagents.
yurukusa
Streak risk notifier for Claude Code — cron-friendly warning before your streak dies
yurukusa
Compare two time periods of Claude Code activity — week over week, month over month
yurukusa
AI activity report for your Claude Code Ghost Days. Shows what your AI did while you were offline.
yurukusa
CLI diagnostic for your Claude Code setup. 20 checks across 6 dimensions.
yurukusa
MCP server for cc-toolkit — gives Claude real-time access to your Claude Code usage stats
yurukusa
Forecast your Claude Code usage — projected month-end hours, ghost days, and streak
yurukusa
Time spent per project in Claude Code — ranked by hours, you vs AI
yurukusa
ASCII receipt of your AI's daily work from Claude Code proof-log. The AI never clocks out.
yurukusa
How does Claude Code recover from errors? 99% self-recover rate. Track retry, investigate, fix, rollback, and pivot patterns across all your sessions.
...moreyurukusa
Show files changed by AI that need human review — reads activity-log.jsonl from Claude Code
yurukusa
Your Claude Code AI Productivity Score — a single 0-100 number you can share
yurukusa
Generate a Claude Code stats badge for your GitHub README — streak, hours, autonomy ratio
yurukusa
Generate a weekly AI activity report from Claude Code proof-log files.
yurukusa
How long can Claude Code go without an error? Median 12 successful tool calls between errors. Longest streak: 829. Bash breaks 52% of streaks.
...moreyurukusa
Discover your Claude Code developer archetype. Diagnoses your coding style from real usage patterns.
yurukusa
One command to make Claude Code safe for autonomous operation. 8 hooks: destructive blocker, branch guard, force-push protection, secret leak prevention, syntax checks, and more.
...moreyurukusa
Audit your Claude Code skills: token overhead, usage frequency, prune candidates
yurukusa
See what your AI did while you were gone. Shows git commits from Ghost Days — days AI ran Claude Code autonomously while you were offline.
...moreyurukusa
How fast does Claude Code actually work? Tool execution rate (tools/hour), pace tiers, and burst session analysis.
yurukusa
Does Claude Code warm up or fade? Tool execution rate progression within sessions — early, mid, and late phase analysis.
yurukusa
What's the rhythm of a Claude Code session? Intra-session timing gap distribution — instant bursts, quick cycles, deliberate pauses.
...moreyurukusa
Analyze which Claude Code tools appear together in the same session — co-occurrence and affinity matrix
yurukusa
Which files does Claude Code touch the most? Ranks files by Edit/Write/Read frequency across all sessions.
yurukusa
How does Claude's context window grow within a session? Context window usage analysis — size tiers, growth patterns, and compaction pressure.
...moreyurukusa
See how full your Claude Code context window is — reads token usage from session transcripts
yurukusa
Analyze Claude Code tool burst patterns — how many consecutive calls does each tool make?