agent-tools

agent-tools is a skill for Claude Code, Codex from NicolaiLassen/orxhestra. It costs 34 tokens per session (672 once invoked), scanned A, original, Apache-2.0.

A guide to building tools that AI agents can call, including Python functions, other agents, handoffs between agents, and controls for ending loops.

In plain words
What is it for?
Use it to wrap functions as tools, let one agent call another, transfer requests between agents, connect MCP tools, and stop repeated agent loops.
Why use it?
It helps divide an agent system into smaller tasks and route work to the right agent instead of putting every action in one agent.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to wrap functions as tools, let one agent call another, transfer requests between agents, connect MCP tools, and stop repeated agent loops.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nicolailassen/orxhestra/agent-tools
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.

Any agent
npx skills add NicolaiLassen/orxhestra --skill agent-tools
Clone the repo
git clone --depth 1 https://github.com/NicolaiLassen/orxhestra

Made for: Claude Code, Codex.

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-tools

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/nicolailassen/orxhestra/agent-tools"><img src="https://agentmods.dev/badge/skills/nicolailassen/orxhestra/agent-tools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 672 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 $0.00034 $0.00672
Opus 5 $0.00017 $0.00336
Sonnet 5 $0.00007 $0.00134
Haiku 4.5 $0.00003 $0.00067

Measured 10d ago against content hash 41898051afa4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

agent-tools 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.

docs/skills/agent-tools/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Tools

function_tool — Wrap Python functions

from orxhestra.tools import function_tool

@function_tool
async def search_web(query: str) -> str:
    """Search the web for information."""
    return f"Results for: {query}"

# Or with custom name
@function_tool(name="web_search", description="Search the internet")
async def search(query: str) -> str:
    return f"Results for: {query}"

AgentTool — Agent as a callable tool

Make any agent callable as a tool by a parent agent.

from orxhestra.tools import AgentTool

researcher = LlmAgent(name="researcher", model=model, description="Research topics.", instructions="...")

# Parent agent can call researcher as a tool
manager = LlmAgent(
    name="manager",
    model=model,
    tools=[AgentTool(agent=researcher)],
    instructions="Use the researcher tool when you need information.",
)

make_transfer_tool — Agent handoff

from orxhestra.tools import make_transfer_tool

transfer = make_transfer_tool([sales_agent, support_agent])
triage = LlmAgent(name="triage", model=model, tools=[transfer], instructions="Route requests.")

exit_loop_tool — Break out of LoopAgent

from orxhestra.tools import exit_loop_tool

reviewer = LlmAgent(
    name="reviewer",
    model=model,
    tools=[exit_loop_tool],
    instructions="Call exit_loop when the draft is approved.",
)

CallContext — Access state inside tools

from orxhestra.tools import CallContext

class MyTool(BaseTool):
    name = "my_tool"
    description = "Does something"

    async def _arun(self, input: str, **kwargs) -> str:
        ctx: CallContext = kwargs.get("tool_context")
        if ctx:
            ctx.state["last_query"] = input  # write to shared state
            session_id = ctx.session_id
        return f"Processed: {input}"

MCPToolAdapter — Connect MCP servers

from orxhestra.integrations.mcp import MCPClient, MCPToolAdapter

# HTTP MCP server
client = MCPClient("http://localhost:8001/mcp")
adapter = MCPToolAdapter(client)
tools = await adapter.load_tools()

agent = LlmAgent(name="agent", model=model, tools=tools)

# In-memory FastMCP server
from mcp_server import mcp  # FastMCP instance
client = MCPClient(mcp)
tools = await MCPToolAdapter(client).load_tools()

Read the full file on GitHub · 111 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 · 111 lines · 34 tokens per session scan A 41898051afa4

Subscribe to this mod's changes

agent-tools is a skill published in the GitHub repository NicolaiLassen/orxhestra (21 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 672 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

ampersend

Give an agent a way to pay for things on the internet. Use when the user wants the agent to be able to pay for things online, when an HTTP call returns 402 Payment Required, when calling an endpoint that charges per request, when the user names a capability they want without a specific URL in mind, or when the user is…

edgeandnode/ampersend-sdk · 80 tokens

unit-converter

Converts values between metric and imperial units, using the project's agreed factors.

polymind-inc/agent-framework-js · 19 tokens

agent-framework-py-release

Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…

microsoft/agent-framework · 103 tokens

foundry-hosted-agent-validation

Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.

microsoft/agent-framework · 82 tokens

build-and-test

How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.

microsoft/agent-framework · 26 tokens

python-feature-lifecycle

Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.

microsoft/agent-framework · 43 tokens