agent-tool-routing

agent-tool-routing is a skill for Claude Code from latestaiagents/agent-skills. It costs 53 tokens per session (2,811 once invoked), scanned A, original, MIT.

A guide for making AI agents choose among available tools and external services. It covers matching a task to tool capabilities, using MCP integrations, and planning fallbacks.

In plain words
What is it for?
Use it to build dynamic tool selection, connect MCP servers, route requests to external APIs, and weigh cost or response time.
Why use it?
It helps agents avoid choosing unsuitable tools when several options are available or when a tool fails.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/dev/projects.

Part of the agent-architect plugin — 13 skills, 1 command, 5 MCP servers shipped together

Good fit Use it to build dynamic tool selection, connect MCP servers, route requests to external APIs, and weigh cost or response time.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add latestaiagents/agent-skills
Claude Code
/plugin install agent-architect

Made for: Claude Code.

Or install agent-architect, the plugin that ships this one along with the rest of its 13 skills, 1 command, 5 MCP servers.

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 agent-tool-routing

README.md
[![agentmods](https://agentmods.dev/badge/skills/latestaiagents/agent-skills/agent-tool-routing/github.svg)](https://agentmods.dev/skills/latestaiagents/agent-skills/agent-tool-routing)
Your own site
<a href="https://agentmods.dev/skills/latestaiagents/agent-skills/agent-tool-routing"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/agent-tool-routing/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.

agentmods 80×15 button for agent-tool-routing

Your own site · 80×15
<a href="https://agentmods.dev/skills/latestaiagents/agent-skills/agent-tool-routing"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/agent-tool-routing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,811 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00053 $0.02811
Opus 5 $0.00026 $0.01406
Sonnet 5 $0.00011 $0.00562
Haiku 4.5 $0.00005 $0.00281

Measured 10d ago against content hash 9c65126d2da6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

agent-tool-routing 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 10d 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/agent-architect/skills/patterns/agent-tool-routing/SKILL.md · 463 lines

How it starts

The opening of the file, as written. The whole thing — 463 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Tool Routing

Design intelligent systems for agents to select and use the right tools at the right time.

When to Use

  • Agents need to choose between multiple tools
  • Implementing MCP (Model Context Protocol) integrations
  • Building agents with external API access
  • Designing tool fallback strategies
  • Optimizing tool usage for cost/performance

Tool Architecture

┌─────────────────────────────────────────────────────────────┐
│                         AGENT                                │
└─────────────────────────────────────────────────────────────┘
                              │
                              ▼
┌─────────────────────────────────────────────────────────────┐
│                     TOOL ROUTER                              │
│  ┌─────────────┐  ┌──────────────┐  ┌────────────────────┐ │
│  │ Classifier  │  │ Capabilities │  │ Cost/Latency       │ │
│  │             │  │ Matcher      │  │ Optimizer          │ │
│  └─────────────┘  └──────────────┘  └────────────────────┘ │
└─────────────────────────────────────────────────────────────┘
                              │
        ┌─────────────────────┼─────────────────────┐
        ▼                     ▼                     ▼
   ┌─────────┐          ┌─────────┐          ┌─────────┐
   │ Tool A  │          │ Tool B  │          │ Tool C  │
   │ (Local) │          │  (API)  │          │  (MCP)  │
   └─────────┘          └─────────┘          └─────────┘

Tool Definition

interface Tool {
  name: string;
  description: string;
  category: string;

  // Schema
  inputSchema: JSONSchema;
  outputSchema: JSONSchema;

  // Capabilities
  capabilities: string[];
  limitations: string[];

  // Execution
  execute: (input: unknown) => Promise<ToolResult>;

  // Metadata
  metadata: {
    costPerCall?: number;
    avgLatencyMs?: number;
    rateLimit?: RateLimit;
    requiresAuth?: boolean;
    supportsBatching?: boolean;
  };
}

interface ToolResult {
  success: boolean;
  data?: unknown;
  error?: {
    code: string;
    message: string;
    retryable: boolean;
  };
  metadata: {
    durationMs: number;
    tokensUsed?: number;
  };
}

Read the full file on GitHub · 463 lines

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. 10d ago First seen · 463 lines · 53 tokens per session scan A 9c65126d2da6

Subscribe to this mod's changes

agent-tool-routing is a skill published in the GitHub repository latestaiagents/agent-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 53 tokens to every session and 2,811 once invoked, about $0.0003 per session on Opus 5. 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.