Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/ww-w-ai/super-token-saverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/ww-w-ai/super-token-saver/super-token-saver)<a href="https://agentmods.dev/plugins/ww-w-ai/super-token-saver/super-token-saver"><img src="https://agentmods.dev/badge/plugins/ww-w-ai/super-token-saver/super-token-saver/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/ww-w-ai/super-token-saver/super-token-saver"><img src="https://agentmods.dev/badge/plugins/ww-w-ai/super-token-saver/super-token-saver.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
super-token-saver scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 22d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "super-token-saver",
"version": "3.7.5",
"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"
]
}
What it installs
The manifest is a name and a version. 6 skills, 2 hooks travel with it, and installing the plugin installs all of them — 344 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 22d ago Changed 046f68ce4cda
- 25d ago Changed cf7f53f1b4d3
- 1mo ago Changed 41fa3de885a1
- 1mo ago Changed 773176928dda
- 1mo ago Changed 74b76ef101a0
- 1mo ago First seen · 35 lines scan A 577d03015de4
super-token-saver is a plugin published in the GitHub repository ww-w-ai/super-token-saver (35 stars, last pushed 23d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other plugins, from other repositories
hush
Quieter sessions for Claude Code: less narration, shorter tool output and concise answers focused on the result.
beacon
At-a-glance awareness across concurrent Claude Code sessions: a Claude Code status line, a CLI and browser dashboard on any terminal, and painted iTerm2 chrome.
pith
Token optimization for Claude Code. Automatic tool output compression (40-60% reduction), token meter in statusline, auto-compact at 70% context, structured output formats, self-building project wiki, URL ingestion, Karpathy compile pass, and semantic lint.
tools
Session lifecycle management for Claude Code — orient, checkpoint, close out, and never lose the thread between sessions.
ponytail
Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.
i-have-adhd
Shape Claude Code output for an ADHD reader: lead with the next action, number steps, suppress tangents, restate state, make wins visible.