super-token-saver

v3.3.0

Cut agent-session cost on Claude Code and Codex: cache-expiry prevention, zero-LLM context restore across both tools, cross-tool session handoff, and a real cost dashboard.

CodexClaude Code6 Skills

By taekim34License: Apache-2.031 GitHub starsUpdated 44 minutes ago

Directory evidence

Runtimes: Codex and Claude Code
Parsed components: 6 skill or MCP entries
Source updated: Sep 3, 2026
Manifest status: Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install super-token-saver for Codex and Claude Code

Installs for the current user

codex plugin marketplace add IchenDEV/agent-plugin-mkt
codex plugin marketplace upgrade agent-plugin-marketplace
codex plugin add super-token-saver@agent-plugin-marketplace

Paste and run these commands in a terminal with Codex. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually

$ git clone https://github.com/ww-w-ai/super-token-saver

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.

Plugin files

super-token-saver/

├── .codex-plugin/plugin.json
├── .claude-plugin/plugin.json
├── skills/report-limit/SKILL.md
├── skills/s-compact/SKILL.md
├── skills/s-continue/SKILL.md
├── skills/setup-git-lite/SKILL.md
├── skills/setup-statusline/SKILL.md
└── skills/usage-view/SKILL.md

Included Skills6

report-limitskills/report-limit/SKILL.md

Max plan hit the wall? Report your 5h window data — we're mapping the rate limit formula Anthropic won't publish

s-compactskills/s-compact/SKILL.md

Session handoff for the next session — write-side pair of /s-continue. Triggers on "s-compact", "session handoff", "handoff prompt", "hand off", "wrap up the session", "prep for next session". Distills what /s-continue cannot recover: subagent findings, tool-output numbers, and decisions that never entered the user↔assistant dialogue. Saves to a per-project file /s-continue auto-loads.

s-continueskills/s-continue/SKILL.md

Cheaper and faster than /compact. Restores previous session context from Claude Code AND Codex transcripts by reading them directly — no LLM calls, no token cost. Also auto-loads a handoff written by /s-compact, if one exists. Triggers on "s-continue", "restore context", "what was I doing", "pick up where I left off", "resume work", "previous session", "codex session".

setup-git-liteskills/setup-git-lite/SKILL.md

Disable Claude Code built-in git instructions and inject a curated 280-tok minimum via SessionStart hook. Saves ~2,200 tok/session + ~1,700 tok/call.

setup-statuslineskills/setup-statusline/SKILL.md

Live token counter in your CLI. Shows real-time input/output/cache token counts in the Claude Code status bar

usage-viewskills/usage-view/SKILL.md

Know exactly what you spent (Claude Code) or how much of your Codex limit you have used (Codex). Interactive HTML dashboard with token usage and, on Claude Code, cost breakdown and 5-hour window timeline across all sessions

Plugin manifests2

.codex-plugin/plugin.json

{
  "name": "super-token-saver",
  "version": "3.3.0",
  "description": "Cut agent-session cost on Claude Code and Codex: cache-expiry prevention, zero-LLM context restore across both tools, cross-tool session handoff, and a real cost dashboard.",
  "author": {
    "name": "taekim34"
  },
  "repository": "https://github.com/ww-w-ai/super-token-saver",
  "license": "Apache-2.0",
  "keywords": [
    "token-saver",
    "context-restore",
    "session-handoff",
    "cost-tracking",
    "prompt-cache"
  ],
  "skills": "./skills/",
  "hooks": "./hooks/hooks-codex.json",
  "interface": {
    "displayName": "Token Saver",
    "shortDescription": "Restore context and cut session cost.",
    "longDescription": "Restore prior Claude Code or Codex sessions by reading their transcripts directly — no summarization call — write a cross-tool handoff before clearing, and see where the money actually went.",
    "developerName": "taekim34",
    "category": "Productivity",
    "capabilities": [
      "Interactive",
      "Write"
    ],
    "defaultPrompt": [
      "Restore my previous Claude Code or Codex session.",
      "Write a handoff for the next session.",
      "Show my token usage."
    ]
  }
}

.claude-plugin/plugin.json

{
  "name": "super-token-saver",
  "version": "3.3.0",
  "description": "45% cost reduction measured. Cache expiry prevention, SubTask auto-delegation, zero-cost context restoration, real-time cost dashboard. The only Claude Code plugin built from CC source analysis.",
  "author": {
    "name": "taekim34"
  },
  "repository": "https://github.com/ww-w-ai/super-token-saver",
  "license": "Apache-2.0",
  "keywords": [
    "claude-code",
    "cost-reduction",
    "token-optimization",
    "cache-management",
    "rate-limit",
    "usage-dashboard",
    "context-management",
    "api-cost",
    "billing",
    "analytics",
    "subtask",
    "session-management",
    "prompt-cache",
    "anthropic-api",
    "cost-tracking",
    "upgrader",
    "context-restore",
    "max-plan",
    "pay-per-use",
    "s-continue",
    "s-compact",
    "session-handoff"
  ]
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[super-token-saver on Agent Plugins Marketplace](https://pluginsmp.com/plugins/super-token-saver)