effort-router

effort-router is a plugin for Claude Code from arpan1221/claude-effort-router. Its manifest loads nothing; the 1 skill, 2 hooks it bundles cost 65 tokens per session together, scanned A, original, MIT.

A Claude Code plugin that adjusts how much effort Claude uses for each turn based on your remaining subscription usage limit.

In plain words
What is it for?
Use it to set effort thresholds and automatically choose thorough, normal, or conserving work as your Claude usage changes.
Why use it?
It helps balance thorough answers against a shrinking usage allowance, so you can conserve usage when your limit is running low.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest.

Install

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.

Claude Code
/plugin marketplace add arpan1221/claude-effort-router
agentmods
npx agentmods add plugins/arpan1221/claude-effort-router/effort-router
Clone the repo
git clone --depth 1 https://github.com/arpan1221/claude-effort-router

Made for: Claude Code.

Wrote 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.

agentmods badge for effort-router

README.md
[![agentmods](https://agentmods.dev/badge/plugins/arpan1221/claude-effort-router/effort-router.svg)](https://agentmods.dev/plugins/arpan1221/claude-effort-router/effort-router)
Your own site
<a href="https://agentmods.dev/plugins/arpan1221/claude-effort-router/effort-router"><img src="https://agentmods.dev/badge/plugins/arpan1221/claude-effort-router/effort-router.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 1 skill, 2 hooks cost 65 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

effort-router 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 5d 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.

plugins/effort-router/.claude-plugin/plugin.json · 46 lines

What it actually says

{
  "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
  "name": "effort-router",
  "displayName": "Effort Router",
  "version": "0.1.0",
  "description": "Routes each turn to an effort level based on your real Claude subscription usage limits — go deep while budget is cheap, conserve as it runs down.",
  "author": {
    "name": "Arpan Nookala"
  },
  "repository": "https://github.com/arpan1221/claude-effort-router",
  "license": "MIT",
  "keywords": ["usage", "rate-limits", "effort", "budget", "hooks", "productivity"],
  "userConfig": {
    "threshold_high": {
      "type": "number",
      "title": "High-effort threshold (%)",
      "description": "Below this percentage of your usage limit, Claude is told to work thoroughly.",
      "default": 35,
      "min": 0,
      "max": 100
    },
    "threshold_normal": {
      "type": "number",
      "title": "Normal-effort threshold (%)",
      "description": "Below this percentage, Claude works at normal depth.",
      "default": 70,
      "min": 0,
      "max": 100
    },
    "threshold_conserve": {
      "type": "number",
      "title": "Conserve threshold (%)",
      "description": "Below this, Claude conserves; at or above it, Claude spends minimally.",
      "default": 88,
      "min": 0,
      "max": 100
    },
    "quiet_setup_nudge": {
      "type": "boolean",
      "title": "Suppress the setup reminder",
      "description": "By default, sessions warn once when the statusline bridge is not wired and real usage limits are unavailable. Enable to silence it.",
      "default": false
    }
  }
}
Contents

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 — 65 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Changes

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.

  1. 5d ago First seen · 46 lines scan A b437ff49657a

Subscribe to this mod's changes

effort-router is a plugin published in the GitHub repository arpan1221/claude-effort-router (2 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.