agentmods.dev

promptrail-claude-router

A Claude Code add-on that automatically chooses among five levels of AI effort for each task while keeping billing through a claude.ai subscription.

In plain words
What is it for?
It helps route Claude Code tasks to different reasoning-effort levels while using an existing claude.ai subscription.
Why use it?
It removes the need to choose an effort level manually for every request.

Plugin for Claude Code

6 1mo ago A scan tokens not measured original MIT
View the source file PythonIaMath/PromptRail-Plugins
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 PythonIaMath/PromptRail-Plugins
agentmods
npx agentmods add plugins/pythoniamath/promptrail-plugins/promptrail-claude-router
Clone the repo
git clone --depth 1 https://github.com/PythonIaMath/PromptRail-Plugins

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

promptrail-claude-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 2d 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/promptrail-claude-router/.claude-plugin/plugin.json · 14 lines

What it actually says

{
  "name": "promptrail-claude-router",
  "version": "0.1.0",
  "description": "Automatically selects one of five Claude Code effort levels while preserving claude.ai subscription billing. Learn more at https://www.promptrail.ai/plugins",
  "author": {
    "name": "PromptRail",
    "url": "https://promptrail.ai"
  },
  "homepage": "https://promptrail.ai",
  "repository": "https://github.com/PythonIaMath/PromptRail-Plugins",
  "license": "MIT",
  "keywords": ["claude-code", "anthropic", "effort", "routing", "subscription"]
}
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. 2d ago First seen · 14 lines scan A a9ba5ef37869

Subscribe to this mod's changes

promptrail-claude-router is a plugin published in the GitHub repository PythonIaMath/PromptRail-Plugins (6 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.

PlanningReasoningclaude-codecodexplugins
Related

Other plugins, from other repositories

neuroarxiv

Grounds a coding agent's architecture decisions in real arXiv prior art: parallel isolated reads of papers found category-wise (divergence), converged into one recommended path with citations, a first step, and known failure modes to avoid.

UditAkhourii/neuroarxiv · not measured

a11y-audit

Full accessibility audit with WCAG compliance checking.

rohitg00/awesome-claude-code-toolkit · not measured

aws-helper

AWS service configuration and deployment automation.

rohitg00/awesome-claude-code-toolkit · not measured

backend-architect

Backend service architecture design with endpoint scaffolding.

rohitg00/awesome-claude-code-toolkit · not measured

dev-tooling

Three MCP servers for PHP and JavaScript operations plus an optional PHP language server. PHP (php-tooling): PHPStan, ECS, Rector, PHPUnit, PHPUnit coverage gap analysis, Symfony Console. Administration (js-admin-tooling): ESLint, Stylelint, Prettier, Jest, TypeScript, Vite builds. Storefront (js-storefront-tooling)…

shopwareLabs/ai-coding-tools · not measured

bevy-plugin

Bevy game engine development - ECS, rendering, game architecture.

laurigates/claude-plugins · not measured