agent-tool-builder

agent-tool-builder is a skill for Claude Code, Codex from Ghosteken/agent-harness. It costs 57 tokens per session (4,507 once invoked), scanned A, a copy of agent-tool-builder, MIT.

Guidance for designing the tools that AI agents use to interact with software and services. It covers the tool's input and output descriptions, checks, errors, and the MCP standard for connecting AI tools.

In plain words
What is it for?
Designing tool schemas, writing descriptions for AI models, validating inputs, handling errors, and testing tools with an AI agent.
Why use it?
Poorly described or unchecked tools can make an agent misunderstand requests, fail without explanation, or waste tokens. This helps make tool behavior clearer and failures explicit.

Skill for Claude CodeCodex

Part of the agent-harness plugin — 173 skills, 11 commands, 12 agents shipped together

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 skills/ghosteken/agent-harness/agent-tool-builder
Any agent
npx skills add Ghosteken/agent-harness --skill agent-tool-builder
Clone the repo
git clone --depth 1 https://github.com/Ghosteken/agent-harness

Made for: Claude Code, Codex.

Or install agent-harness, the plugin that ships this one along with the rest of its 173 skills, 11 commands, 12 agents.

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-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/ghosteken/agent-harness/agent-tool-builder.svg)](https://agentmods.dev/skills/ghosteken/agent-harness/agent-tool-builder)
Your own site
<a href="https://agentmods.dev/skills/ghosteken/agent-harness/agent-tool-builder"><img src="https://agentmods.dev/badge/skills/ghosteken/agent-harness/agent-tool-builder.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,507 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin 98% copy Near-identical to another mod 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 $0.00057 $0.04507
Opus 5 $0.00028 $0.02253
Sonnet 5 $0.00011 $0.00901
Haiku 4.5 $0.00006 $0.00451

Measured 4d ago against content hash d32f031ee373, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-tool-builder scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

data = weather_api.fetch(location)
Origin

This is a copy

98% identical to agent-tool-builder — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

archive/skills-community/agent-tool-builder/SKILL.md · 715 lines

How it starts

The opening of the file, as written. The whole thing — 715 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Tool Builder

Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary.

This skill covers tool design from schema to error handling. JSON Schema best practices, description writing that actually helps the LLM, validation, and the emerging MCP standard that's becoming the lingua franca for AI tools.

Key insight: Tool descriptions are more important than tool implementations. The LLM never sees your code - it only sees the schema and description.

Principles

  • Description quality > implementation quality for LLM accuracy
  • Aim for fewer than 20 tools - more causes confusion
  • Every tool needs explicit error handling - silent failures poison agents
  • Return strings, not objects - LLMs process text
  • Validation gates before execution - reject, fix, or escalate, never silent fail
  • Test tools with the LLM, not just unit tests

Capabilities

  • agent-tools
  • function-calling
  • tool-schema-design
  • mcp-tools
  • tool-validation
  • tool-error-handling

Scope

  • multi-agent-coordination → multi-agent-orchestration
  • agent-memory → agent-memory-systems
  • api-design → api-designer
  • llm-prompting → prompt-engineering

Tooling

Standards

  • JSON Schema - When: All tool definitions Note: The universal format for tool schemas
  • MCP (Model Context Protocol) - When: Building reusable, cross-platform tools Note: Anthropic's open standard, widely adopted

Frameworks

  • Anthropic SDK - When: Claude-based agents Note: Beta tool runner handles most complexity
  • OpenAI Functions - When: OpenAI-based agents Note: Use strict mode for guaranteed schema compliance
  • Vercel AI SDK - When: Multi-provider tool handling Note: Abstracts differences between providers
  • LangChain Tools - When: LangChain-based agents Note: Converts MCP tools to LangChain format

Patterns

Tool Schema Design

Creating clear, unambiguous JSON Schema for tools

Read the full file on GitHub · 715 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 · 715 lines · 57 tokens per session scan A d32f031ee373

Subscribe to this mod's changes

agent-tool-builder is a skill published in the GitHub repository Ghosteken/agent-harness (2 stars, last pushed 2d ago), licensed MIT. It adds 57 tokens to every session and 4,507 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 98% identical to agent-tool-builder, differing in 2 lines, and is treated as a copy.

Related

Other skills, from other repositories

regex-mastery

Use this skill when writing regular expressions, debugging pattern matching,optimizing regex performance, or implementing text validation. Triggers on regex, regular expressions, pattern matching, lookahead, lookbehind, named groups, capture groups, backreferences, and any task requiring text pattern matching.

alibaba/anolisa · 60 tokens

beevibe-team-mesh-negotiation

Multi-round negotiation protocol — covers both initiator and peer roles. Use when about to call negotiate(), when receiving a intent block as a peer, or when receiving an 'escalated' sentinel from a blocked respondnegotiate. Covers proposal crafting, counter-strategy, deadlock detection, when to accept early…

beevibe-ai/beevibe · 112 tokens

suede-aso

Suede-owned app-store optimization discipline for keyword fields, titles, subtitles, descriptions, screenshots, ratings context, and competitor listing audits. Use when improving App Store or Google Play visibility or listing conversion from a live app URL and current console evidence. NOT FOR: building or releasing…

JasonColapietro/suede-creator-skills · 146 tokens

copywriting

When the user wants to write, rewrite, or improve marketing copy for any page — including homepage, landing pages, pricing pages, feature pages, about pages, or product pages. Also use when the user says "write copy for," "improve this copy," "rewrite this page," "marketing copy," "headline help," "CTA copy," "value…

stagewise-io/stagewise · 174 tokens

crest

Building engineer self-branding by turning technical contributions into a professional brand. Use for GitHub/LinkedIn/blog/conference positioning or content strategy.

simota/agent-skills · 31 tokens

refocusing

Use when a long-running agent may have lost the product outcome, when context was compacted, when work has crossed a major boundary, or when a fresh path-based trace is needed before the next consequential action. Not for fresh-session orientation, waking an idle seat, or checkpoints.

mvschwarz/openrig · 59 tokens