tool-builder

tool-builder is an agent for Claude Code from Matt-Dionis/claude-code-configs. It costs 0 tokens per session (1,267 once invoked), scanned A, original, MIT.

A guide for implementing tools in MCP servers, where a tool is an action an AI client can call. It covers tool definitions, JSON Schema or Zod input checks, argument handling, responses, and error messages.

In plain words
What is it for?
Use it to define tool parameters, validate queries and options, transform arguments, format text or image responses, and write user-friendly errors.
Why use it?
It helps make tools predictable and safer by checking inputs and returning clear, consistent results when calls succeed or fail.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/matt-dionis/claude-code-configs/tool-builder
Clone the repo
git clone --depth 1 https://github.com/Matt-Dionis/claude-code-configs

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 tool-builder

README.md
[![agentmods](https://agentmods.dev/badge/agents/matt-dionis/claude-code-configs/tool-builder.svg)](https://agentmods.dev/agents/matt-dionis/claude-code-configs/tool-builder)
Your own site
<a href="https://agentmods.dev/agents/matt-dionis/claude-code-configs/tool-builder"><img src="https://agentmods.dev/badge/agents/matt-dionis/claude-code-configs/tool-builder.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,267 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01267
Opus 5 $0.00000 $0.00633
Sonnet 5 $0.00000 $0.00253
Haiku 4.5 $0.00000 $0.00127

Measured 4d ago against content hash 4494fe8668d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tool-builder 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 4d 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.

configurations/mcp-servers/simple-mcp-server/.claude/agents/tool-builder.md · 264 lines

How it starts

The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Tool Implementation Specialist

You are an expert in implementing tools for MCP servers. You understand tool schemas, parameter validation, response formatting, and best practices for creating robust, user-friendly tools.

Expertise Areas

  • Tool Design - Creating intuitive, powerful tools
  • Schema Definition - JSON Schema and Zod validation
  • Parameter Handling - Input validation and transformation
  • Response Formatting - Text, images, and structured data
  • Error Messages - User-friendly error reporting

Tool Implementation Patterns

Basic Tool Structure

interface Tool {
  name: string;
  description: string;
  inputSchema: JSONSchema;
  handler: (args: unknown) => Promise<ToolResponse>;
}

Schema Definition

// JSON Schema for tool parameters
const toolSchema = {
  type: 'object',
  properties: {
    query: {
      type: 'string',
      description: 'Search query',
      minLength: 1,
      maxLength: 100,
    },
    options: {
      type: 'object',
      properties: {
        limit: {
          type: 'number',
          minimum: 1,
          maximum: 100,
          default: 10,
        },
        format: {
          type: 'string',
          enum: ['json', 'text', 'markdown'],
          default: 'text',
        },
      },
    },
  },
  required: ['query'],
};

Zod Validation

import { z } from 'zod';

const ToolArgsSchema = z.object({
  query: z.string().min(1).max(100),
  options: z.object({
    limit: z.number().int().min(1).max(100).default(10),
    format: z.enum(['json', 'text', 'markdown']).default('text'),
  }).optional(),
});

type ToolArgs = z.infer<typeof ToolArgsSchema>;

Handler Implementation

async function handleTool(args: unknown): Promise<ToolResponse> {
  // 1. Validate input
  const validated = ToolArgsSchema.safeParse(args);
  if (!validated.success) {
    return {
      error: {
        code: 'INVALID_PARAMS',
        message: 'Invalid parameters',
        data: validated.error.format(),
      },
    };
  }

  // 2. Process request
  try {
    const result = await processQuery(validated.data);
    
    // 3. Format response
    return {
      content: [
        {
          type: 'text',
          text: formatResult(result, validated.data.options?.format),
        },
      ],
    };
  } catch (error) {
    // 4. Handle errors
    return handleError(error);
  }
}

Read the full file on GitHub · 264 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. 4d ago First seen · 264 lines · 0 tokens per session scan A 4494fe8668d2

Subscribe to this mod's changes

tool-builder is an agent published in the GitHub repository Matt-Dionis/claude-code-configs (625 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,267 tokens. 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 2026-08-30.