AgentStack
CodeShuX avatar

CodeShuX

5 listings · 0 installs

Open-source publisher. Listings imported from github.com/CodeShuX — credited to the original author with their license.

↗ github.com/CodeShuX
5 results
Self-run
SKILL

Summary

Aggregate TokenWise routing data over a time window (default: last 7 days). Shows trend, top task classes, and cumulative savings. Use when the user asks "show me my weekly/monthly savings", "how am I doing on tokenwise", or runs /tokenwise:summary.

0
11
Free
Self-run
SKILL

Undo

Restore TokenWise config backups. Lists all .tokenwise-backup-* files found, lets the user pick one to restore in place. Use when the user wants to roll back TokenWise's changes to CLAUDE.md or settings.json, or runs /tokenwise:undo.

0
7
Free
Self-run
SKILL

Ab

Run an A/B test of the same task at multiple model tiers (Haiku, Sonnet, optionally Opus). Captures outputs, computes structural and semantic diffs, scores quality, writes a markdown comparison report. Use when the user wants to validate "is Haiku good enough for this task class?" or runs /tokenwise:ab "<task description>".

0
6
Free
Self-run
SKILL

Report

Print a TokenWise session report — tokens per model, $ saved vs all-Opus baseline, escalations, quality flags. Reads from .tokenwise/log.ndjson filtered to the current session. Use when the user asks "how much did I save", "show me tokenwise stats", or runs /tokenwise:report.

0
11
Free
Self-run
SKILL

Install

Install TokenWise routing rules into the user's Claude Code config (CLAUDE.md and settings.json). Probes the user's Claude Code build for known routing bugs first, shows diffs, backs up originals, asks for per-file confirmation. Supports --guided (default), --manual (print copy-paste only), and --dry-run (preview without writing). Use when the user says "install tokenwise", "set up tokenwise", or…

0
9
Free
You've reached the end · 5 loaded