Warden Power — Development skill for Claude Code
Zero-token power planner — from the agent's own recorded run-to-run variance, report the minimum detectable saving (MDS) at each run count and how many runs per side a target saving needs, so a benchm.
How to install Warden Power
Installs to ~/.claude/skills/vukkt-token-warden-warden-power/SKILL.md
mkdir -p ~/.claude/skills/vukkt-token-warden-warden-power && curl -fsSL https://raw.githubusercontent.com/vukkt/token-warden/HEAD/commands/warden-power.md -o ~/.claude/skills/vukkt-token-warden-warden-power/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Warden Power does
description: Zero-token power planner — from the agent's own recorded run-to-run variance, report the minimum detectable saving (MDS) at each run count and how many runs per side a target saving needs, so a benchmark burn is provably adequately powered before it starts. argument-hint: "[--agent ] [--target-saving N] [--rent N] [--runs N] [--json]" disable-model-invocation: true allowed-tools: Bash(cd:*), Bash(npx tsx:*)
Run the token-warden power command:
Alternatives in Development
- Breach Check — HIBP k-anonymity check on a password wordlist 4.5k ★
- Skillcount — Skill Count — 技能数量统计与文档同步 835 ★
- Recent Memories — Display the most recent memories and activity from Claude's persistent storage 332 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Pharn Dev Eval
Run a capability's eval LIVE via claude -p N times into isolated runs/, then COUNT structural pass/fail across
Gain
Show how many context tokens mcp-multiplexer is saving you (startup withholding + on-demand schema serving)
Kdp Build
Typeset the interior PDF at KDP trim, with margins cleared against the gutter minimum and an even page count
Shutter Review
Count how many questions this session asked before showing anything.
Godterm
Run many Claude Code and Grok sessions side by side, each on its own account, and drive them by voice
Heal
Pull the Auto-Healer bug web for the current repo (or all repos) — recurrences, stuck bandaid-risk bugs, and t
Related Agents
Token Tracker
Logs token usage estimates for each agent run to .claude/token-stats.json. Call this after any agent completes
Usage Scout
Read-only scout for session, token, and cost code in this FastAPI tracker. Use when the user asks where usage
Maps Miner
Works Google Maps-type data for the target region — rating and review-count profiles, review-language mix, nei