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/Jimmynycu/token-efficiencyWrote 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/jimmynycu/token-efficiency/token-efficiency-coach)<a href="https://agentmods.dev/plugins/jimmynycu/token-efficiency/token-efficiency-coach"><img src="https://agentmods.dev/badge/plugins/jimmynycu/token-efficiency/token-efficiency-coach/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/jimmynycu/token-efficiency/token-efficiency-coach"><img src="https://agentmods.dev/badge/plugins/jimmynycu/token-efficiency/token-efficiency-coach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
token-efficiency-coach 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 1mo 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
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "token-efficiency-coach",
"displayName": "Token-Efficiency Coach",
"version": "1.0.1",
"description": "Finds where a Claude Code session wasted tokens (uncached context, context bloat, oversized tool output, redundant reads, wrong-tier routing) and coaches the fix. Adds a live cost/context statusline and a non-blocking end-of-session coach.",
"author": { "name": "Jimmy Liu", "email": "[email protected]" },
"homepage": "https://github.com/Jimmynycu/token-efficiency",
"repository": "https://github.com/Jimmynycu/token-efficiency",
"license": "MIT",
"keywords": ["tokens", "cost", "efficiency", "prompt-caching", "context", "coach"]
}
What it installs
The manifest is a name and a version. 1 skill, 2 hooks travel with it, and installing the plugin installs all of them — 62 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.
- 1mo ago First seen · 13 lines scan A e8f50d1fc6f1
token-efficiency-coach is a plugin published in the GitHub repository Jimmynycu/token-efficiency (3 stars, last pushed 4mo ago), licensed MIT. 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 2026-08-31.
Other plugins, from other repositories
telegram-topics
Telegram channel for Claude Code — 1 project = 1 forum topic, with a live working/idle status badge on each topic. Run multiple projects concurrently, get notifications, and drive or approve sessions remotely from your phone. Configure with /telegram-topics:configure.
claude-pet
A desktop companion (Windows) that watches your Claude Code sessions and tells you - with status cards and a soft chime - when Claude is thinking, needs your input, or is done - and flags a card that's still running a background task. Hover a card to see everything.
cc-swiss-knife
Essential commands, skills, and workflows for everyday development.
hermitd-feed
Scheduled briefs for Hermit from sources you choose, with story tracking, weekly summaries, and source-quality checks.
feed-hermit
Scheduled briefs for Hermit from sources you choose, with story tracking, weekly summaries, and source-quality checks.
claude-code-hermit
Your own local Claude Tag, in the Claude app, Discord, Telegram, or a custom Claude Code channel.