agent-tools

Name: agent-tools
Availability: InStock
Author: TauriTavern

Document TauriTavern Agent built-in tool contracts, naming, and error semantics.

6|17|Updated Apr 6, 2026

Search Tags:#error handling #tool calling #skill management #agent tools #workspace files #worldinfo

Ready to run

npx skills add https://github.com/TauriTavern/tauritavern.github.io --skill agent-tools-tauritavern

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: agent-tools
Source: https://github.com/TauriTavern/tauritavern.github.io/tree/main/docs/api
Command: npx skills add https://github.com/TauriTavern/tauritavern.github.io --skill agent-tools-tauritavern

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a structured, tool-by-tool reference so you can correctly use TauriTavern Agent built-in tools, understand their inputs/outputs, and avoid common runtime mistakes.

Core Features & Use Cases

Tool catalog for Skills: Covers tool naming (canonical vs model-facing alias), visibility rules, and how tool calls behave during an Agent run.
Detailed I/O contracts: Documents required and optional parameters for tools like skill.list/search/read, workspace list/search/read/write/apply_patch/commit/finish, and worldinfo.read_activated.
Operational constraints & error semantics: Explains read budgets, max limits, checkpoint creation, and how recoverable vs fatal tool errors should be handled.

Quick Start

Ask your agent to use skill.search to locate the relevant section in a specific Skill, then follow up with skill.read to retrieve the exact file or text range you need.

Frequently Asked Questions about agent-tools

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I use TauriTavern Agent built-in tools for workspace and skill management?▼

TauriTavern Agent built-in tools for workspace and skill management are used by following structured tool contracts that specify canonical naming, parameter schemas, and visibility rules to ensure compliant interaction. The reference covers tool calls like skill.list, search, and read.

What is the correct parameter schema for workspace tool calling in TauriTavern?▼

The correct parameter schema for workspace tool calling in TauriTavern requires matching the documented input and output contracts for list, search, read, write, apply_patch, and commit operations. Required and optional parameters must be passed exactly as specified to avoid runtime mistakes.

How are recoverable versus fatal tool errors handled during agent execution?▼

Recoverable versus fatal tool errors during agent execution are handled by applying specific error semantics that define whether a run continues or stops. The operational constraints distinguish recoverable errors, which allow retry, from fatal errors that terminate the constrained agent run.

What are the read budgets and max limits for worldinfo and skill search?▼

Read budgets and max limits for worldinfo and skill search define the operational constraints for tool calls, restricting how much data can be retrieved per run. These limits apply to worldinfo.read_activated and skill.search to enforce deterministic input and output boundaries.

Does the TauriTavern agent use canonical tool names or model-facing aliases?▼

The TauriTavern agent uses both canonical tool names and model-facing aliases, which are documented in the tool catalog. Understanding these visibility rules and naming conventions is necessary to ensure correct tool behavior and profile permissions during an agent run.

Why do tool calls fail when writing to workspace files in a constrained agent run?▼

Tool calls fail when writing to workspace files in a constrained agent run due to exceeding read budgets, violating read and write boundaries, or passing incorrect parameter schemas. Following the documented tool contracts and operational constraints prevents these runtime mistakes.