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/q1343135559/ClaudeMeterWrote 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/q1343135559/claudemeter/plugin)<a href="https://agentmods.dev/plugins/q1343135559/claudemeter/plugin"><img src="https://agentmods.dev/badge/plugins/q1343135559/claudemeter/plugin/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/q1343135559/claudemeter/plugin"><img src="https://agentmods.dev/badge/plugins/q1343135559/claudemeter/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
claudemeter 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
{
"name": "claudemeter",
"displayName": "ClaudeMeter",
"description": "Statusline showing context, 5-hour, weekly, and per-model (Fable) usage — reads only local files, no network, no credentials",
"version": "0.3.0",
"author": {
"name": "huangjiajun",
"url": "https://github.com/q1343135559"
},
"homepage": "https://github.com/q1343135559/ClaudeMeter",
"repository": "https://github.com/q1343135559/ClaudeMeter",
"license": "MIT",
"keywords": [
"statusline",
"usage",
"rate-limit",
"fable",
"context",
"monitoring"
],
"commands": [
"./commands/setup.md",
"./commands/configure.md"
]
}
What it installs
The manifest is a name and a version. 2 commands travel with it, and installing the plugin installs all of them — 18 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 Changed 201569015a31
- 1mo ago First seen · 26 lines scan A 72ca7835812d
claudemeter is a plugin published in the GitHub repository q1343135559/ClaudeMeter (1 stars, last pushed 1mo 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
rate-limit-monitor
Statusline segment + prompt-submit guard for Claude Code's 5-hour and 7-day usage limits. Shows live usage %, and at a configurable threshold it blocks new prompts (with an override) so a long token-heavy task doesn't get cut off mid-run.
ttyl
TTYL ("Talk To You Later") — floating always-on-top timer that flashes when Claude finishes a turn, plus a prompt-cache TTL countdown for your status line. Tracks multiple parallel Claude sessions and click-to-focuses the owning VSCode window.
claude-code-statusline
Statusline with real 5h/7d remaining quota display.
recall
Durable, fully-local project memory for Claude Code. Logs every session to .recall/history.md and condenses it into .recall/context.md with a local Python summarizer (TF-IDF + TextRank) — no API key, no external model, nothing leaves your machine. New sessions resume from the saved context.
statusline-for-claude-code
A dependency-free Node.js status line for Claude Code: model and effort, live git state, context window, prompt-cache state and rate limits on one color-coded line.
orchestrator
Token-frugal multi-agent orchestration for Claude Code, built for a Claude Fable 5 chair: Fable plans and decides, Sonnet 5 carries the volume, Opus 5 takes the hard slices and escalations, each worker's effort sized by the chair. Delegation is the DEFAULT, not the escalation — and a solo guard watches the chair…