Agent skill

Ag2 Add Custom Tool

by ag2ai in ag2ai/build-with-ag2

Add a custom Python tool to an AG2 beta Agent using the @tool decorator.

Apache-2.0Auto-check passedDevelopment

Install Ag2 Add Custom Tool

skills CLI
$ npx skills add ag2ai/build-with-ag2 --skill ag2-add-custom-tool -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ag2ai/build-with-ag2 ag2-add-custom-tool --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ag2ai/build-with-ag2.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/ag2-add-custom-tool .claude/skills/ag2-add-custom-tool && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ag2-add-custom-tool
GitHub stars
252
Token cost
~1.9k tokens
SKILL.md length
495 words
Files
2 (incl. references)
Skills in repo
16
Repo updated
First seen
Licence
Apache-2.0

At a glance

Add a custom Python tool to an AG2 beta Agent using the @tool decorator.

  • The user wants to give an Agent a new capability backed by Python code (API calls
  • SKILL.md covers When to use, 60-second recipe, Sync vs async and Validating inputs with…, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Tasks that involve Design patterns

What it does

Ag2 Add Custom Tool is an agent skill from ag2ai/build-with-ag2. Add a custom Python tool to an AG2 beta Agent using the @tool decorator. Use when the user wants to give an Agent a new capability backed by Python code (API calls, DB queries, computations, file ops). Covers sync and async tools, parameter typing, Pydantic schema customisation, returning typed Input / ToolResult (text / data / images / binary), final=True early-exit, and dependency injection via Context / Inject / Variable / Depends.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/dependency_injection.md`).

It sits in Development, covering Design patterns. It works with Python and Pydantic. The repository describes itself as: Sample code and application showcases to get you going with AG2 (formally AutoGen). The licence is Apache-2.0.

When your agent uses it

  • The user wants to give an Agent a new capability backed by Python code (API calls
  • Tasks that involve Design patterns

Example prompts

  • “/ag2-add-custom-tool”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 29eeac3. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ag2 Add Custom Tool loads about 1.9k tokens when it runs, and up to ~3.2k if it reads all its reference files. Until then it costs about 119 tokens; SKILL.md has 495 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~119
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ag2ai/build-with-ag2 at commit 29eeac3, republished under its Apache-2.0 licence (© ag2ai). 495 words, ~1,863 tokens.

Download SKILL.mdSave it as .claude/skills/ag2-add-custom-tool/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
ag2-add-custom-tool
description
Add a custom Python tool to an AG2 beta `Agent` using the `@tool` decorator. Use when the user wants to give an Agent a new capability backed by Python code (API calls, DB queries, computations, file ops). Covers sync and async tools, parameter typing, Pydantic schema customisation, returning typed `Input` / `ToolResult` (text / data / images / binary), `final=True` early-exit, and dependency injection via `Context` / `Inject` / `Variable` / `Depends`.
license
Apache-2.0

Add a custom Python tool

When to use

The user wants their Agent to take a real-world action: hit an API, query a database, compute something, return an image. If they want shipped tools (web search, code exec, shell), see ag2-use-builtin-tools and ag2-shell-tool instead.

60-second recipe

python
from autogen.beta import Agent, tool
from autogen.beta.config import OpenAIConfig

@tool
def calculate_shipping_cost(destination: str, weight_kg: float) -> str:
    """Calculates shipping cost for a package to a destination."""
    return "$15.00"

agent = Agent(
    "shipping",
    prompt="Use tools when helpful.",
    config=OpenAIConfig(model="gpt-4o-mini"),
    tools=[calculate_shipping_cost],
)

The @tool decorator generates the LLM-facing schema from the function signature, type hints, and docstring. The docstring is the description the LLM sees — write it for an LLM reader, not just a human.

You can also pass plain undecorated functions in tools=[...] and AG2 wraps them automatically:

python
def get_weather(location: str) -> str:
    """Returns the current weather for a given location."""
    return "Sunny, 22°C"

agent = Agent("weather", tools=[get_weather])

Or attach a tool to an existing agent with @agent.tool:

python
agent = Agent("calc")

@agent.tool
def multiply(a: int, b: int) -> int:
    """Multiplies two integers and returns the result."""
    return a * b

Sync vs async

Both def and async def are supported. Synchronous tools run in a thread by default so blocking I/O does not freeze the event loop. For ultra-fast pure-Python tools, opt out:

python
@tool(sync_to_thread=False)
def format_name(first: str, last: str) -> str:
    """Formats a full name."""
    return f"{last.upper()}, {first.capitalize()}"

Native async tools run in the main event loop directly:

python
import aiohttp

@tool
async def fetch(url: str) -> str:
    """Fetches a URL with aiohttp."""
    async with aiohttp.ClientSession() as session:
        async with session.get(url) as r:
            return await r.text()

Validating inputs with Pydantic Field

Use Annotated[T, Field(...)] to give the LLM strict bounds. The framework forwards these into the JSON Schema:

python
from typing import Annotated
from pydantic import Field
from autogen.beta import tool

@tool
def set_temperature(
    temp: Annotated[int, Field(description="Target temperature.", ge=10, le=30)],
    mode: Annotated[str, Field(description="Mode.", pattern="^(heat|cool|auto)$")],
) -> str:
    """Sets the thermostat."""
    return f"Set to {temp}°C in {mode} mode."

You can also override the tool name and description on the decorator:

python
@tool(name="custom_math_tool", description="Performs advanced math.")
def math_op(a: int, b: int) -> int:
    return a + b

Returning typed Input / ToolResult

A plain str return is wrapped in TextInput automatically. For richer payloads, return an Input subtype or compose with ToolResult:

python
from autogen.beta import DataInput, ImageInput, TextInput, ToolResult, tool

@tool
def get_status(task_id: str) -> TextInput:
    return TextInput(f"Task {task_id} is in progress.")

@tool
def get_user_profile(user_id: str) -> DataInput:
    return DataInput({"id": user_id, "name": "Alice", "role": "admin"})

@tool
def fetch_chart(chart_id: str) -> ImageInput:
    return ImageInput(f"https://charts.example.com/{chart_id}.png")

@tool
def analyze_product(product_id: str) -> ToolResult:
    """Returns image + structured metadata in one tool call."""
    return ToolResult(
        ImageInput(f"https://cdn.example.com/products/{product_id}.jpg"),
        {"id": product_id, "name": "Widget Pro", "stock": 42},
    )

For raw bytes of arbitrary format, use BinaryInput(data=..., media_type="application/pdf").

End the turn early with final=True

When the tool already knows the exact final answer, skip the extra LLM round-trip:

python
from autogen.beta import ToolResult, tool

@tool
def handoff_to_human(ticket_id: str) -> ToolResult:
    """Escalates and returns the final user-facing message verbatim."""
    return ToolResult(f"Ticket {ticket_id} was escalated.", final=True)

A final=True ToolResult must contain exactly one part (TextInput or DataInput).

Dependency injection (Context / Inject / Variable / Depends)

Tools can pull execution-time values without exposing them to the LLM. See references/dependency_injection.md for the full table; the basics:

python
from typing import Annotated
from autogen.beta import Context, Inject, Variable, tool

@tool
def query_db(query: str, ctx: Context) -> str:
    """Runs a SQL query."""
    db = ctx.dependencies["db"]
    return db.execute(query)

@tool
def fetch(url: str, http: Annotated[object, Inject("http_session")]) -> str:
    """Fetches with a shared HTTP session."""
    return http.get(url).text

@tool
def send(text: str, api_key: Annotated[str, Variable()]) -> str:
    """Sends a message via the configured channel."""
    ...

Inject annotations are stripped from the LLM-facing schema — they're an internal injection mechanism.

Show full SKILL.md (213 more words)Show less

Going deeper

  • references/dependency_injection.md — Context vs Inject vs Variable vs Depends, defaults, factories, mutability, overrides.
  • website/docs/beta/tools/tools.mdx — full @tool reference, including the synthesized JSON Schema.
  • website/docs/beta/depends.mdx — Depends lifecycle, yield-based teardown, caching, test overrides.
  • website/docs/beta/inputs/inputs.mdx — the Input factory hierarchy and provider support matrix.
  • website/docs/beta/tools/toolkits.mdx — bundle related tools into a reusable Toolkit.
  • website/docs/beta/tools/tool_middleware.mdx — async hooks around a single tool (validation, redaction, approval — see also ag2-hitl).

Common pitfalls

  • Vague docstring — the LLM uses it to decide when to call the tool. "Calculates shipping cost based on destination and weight" is much better than "Shipping calc".
  • No type hints — without them the framework can't generate a useful JSON Schema; the LLM may not call your tool at all.
  • Blocking the event loop — if you write def (sync) tool with heavy CPU or network and pass sync_to_thread=False, the loop blocks. Default behaviour (run in a thread) is safe; only opt out for cheap pure-Python work.
  • Function-level imports inside tools — repo convention disallows them. Hoist import to module top.
  • Nested function definitions inside the tool body — also disallowed (recreates the function on every call).
  • Returning dict directly when you wanted structured data — wrap it in DataInput(...) so the framework treats it as structured rather than coercing to text.
  • Forgetting final=True requires exactly one part — combining multiple Inputs with final=True will raise.

© ag2ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in .agents/skills/ag2-add-custom-tool of ag2ai/build-with-ag2.

  • SKILL.md
  • references/dependency_injection.md

Open the folder on GitHubat commit 29eeac3

Compare with similar skills

Ag2 Add Custom Tool next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Ag2 Add Custom Tool compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ag2 Add Custom Tool this skillag2ai/build-with-ag2252—~1.9kAutomated safety check: PassApache-2.0
Mastering Python SkillSpillwaveSolutions/agent-brain119—~1.4kAutomated safety check: NotesMIT
Framework Migration AssistantArabelaTso/Skills-4-SE253—~1.9kAutomated safety check: PassApache-2.0
Pydantic AIdavila7/claude-code-templates33k3 repos~2.9kAutomated safety check: PassMIT
Fastapi Backendcohen-liel/hivemind110—~710Automated safety check: PassApache-2.0
Python Fastapi Patternsaiskillstore/marketplace4331 repos~1.3kAutomated safety check: NotesNone

Similar skills

  • Mastering Python Skill

    SpillwaveSolutions/agent-brain

    Modern Python coaching covering language foundations through advanced production patterns.

    119 GitHub stars~1.4k tokensUpdated 21 days ago
    DevelopmentAuto-check: notes
  • Framework Migration Assistant

    ArabelaTso/Skills-4-SE

    Automatically migrate Python web applications between frameworks (Flask → FastAPI, Django → FastAPI).

    253 GitHub stars~1.9k tokensUpdated 1 mo ago
    Backend & APIsAuto-check passed
  • Pydantic AI

    davila7/claude-code-templates

    Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.

    33k GitHub starsUsed in 3 repos~2.9k tokens
    AI & LLM EngineeringAuto-check passed
  • Fastapi Backend

    cohen-liel/hivemind

    FastAPI best practices for building production Python backends.

    110 GitHub stars~710 tokensUpdated 5 mo ago
    Backend & APIsAuto-check passed
  • Python Fastapi Patterns

    aiskillstore/marketplace

    FastAPI web framework patterns. An agent skill from aiskillstore/marketplace.

    433 GitHub starsUsed in 1 repo~1.3k tokens
    Backend & APIsAuto-check: notes
  • Fastapi Itechmeat

    Kilo-Org/kilo-marketplace

    FastAPI Python framework. An agent skill from Kilo-Org/kilo-marketplace.

    190 GitHub stars~1.5k tokensUpdated 12 days ago
    Backend & APIsAuto-check passed

More from ag2ai/build-with-ag2

All 16 skills in this repo
  • Ag2 Middleware

    ag2ai/build-with-ag2

    Intercept the AG2 beta agent loop with BaseMiddleware — wrap full turns (onturn), each LLM call (onllmcall), each tool execution (ontoolexecution), or each human-input request (onhumaninput).

    252 GitHub stars~1.9k tokensUpdated 1 mo ago
    Auto-check passed
  • Ag2 Use Builtin Tools

    ag2ai/build-with-ag2

    Wire AG2 beta's shipped tools into an Agent — both provider-native server-side tools (web search, web fetch, code execution, MCP, image generation, memory) and locally-executed common toolkits…

    252 GitHub stars~1.3k tokensUpdated 1 mo ago
    Auto-check passed
  • Ag2 Knowledge And Memory

    ag2ai/build-with-ag2

    Persist agent state across runs, shape what the LLM sees per turn, and cap history to fit a context window.

    252 GitHub stars~2.9k tokensUpdated 1 mo ago
    Auto-check passed
  • Ag2 Observers And Alerts

    ag2ai/build-with-ag2

    Monitor an AG2 beta agent's stream — log events, detect repeated tool calls, track token spend, build trigger-driven observers, route observer alerts to the model, and halt on FATAL conditions.

    252 GitHub stars~2.5k tokensUpdated 1 mo ago
    Auto-check passed
  • Ag2 Quickstart

    ag2ai/build-with-ag2

    Build a minimal AG2 beta Agent end to end — pick a model provider, set a prompt, call agent.ask(), then continue the conversation with reply.ask() (multi-turn).

    252 GitHub stars~1.7k tokensUpdated 1 mo ago
    Auto-check: notes
  • Ag2 Structured Output

    ag2ai/build-with-ag2

    Get a typed Python value back from an AG2 beta Agent instead of free text.

    252 GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed

Works with

Categories

Questions about Ag2 Add Custom Tool

What does Ag2 Add Custom Tool do?

Add a custom Python tool to an AG2 beta Agent using the @tool decorator. Ag2 Add Custom Tool is an agent skill from ag2ai/build-with-ag2. Add a custom Python tool to an AG2 beta Agent using the @tool decorator.

When should I use Ag2 Add Custom Tool?

Ag2 Add Custom Tool fits situations like: the user wants to give an Agent a new capability backed by Python code (API calls; tasks that involve Design patterns.

How do I install Ag2 Add Custom Tool in Claude Code?

Run `npx skills add ag2ai/build-with-ag2 --skill ag2-add-custom-tool -a claude-code`. Or copy the skill folder (.agents/skills/ag2-add-custom-tool in ag2ai/build-with-ag2) into .claude/skills/ag2-add-custom-tool in your project. Claude Code loads it when a task matches its description.

How do I install Ag2 Add Custom Tool in Codex?

Run `npx skills add ag2ai/build-with-ag2 --skill ag2-add-custom-tool -a codex`. Or copy the skill folder (.agents/skills/ag2-add-custom-tool in ag2ai/build-with-ag2) into .agents/skills/ag2-add-custom-tool in your project. Codex loads it when a task matches its description.

Can I use Ag2 Add Custom Tool in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ag2ai/build-with-ag2 --skill ag2-add-custom-tool -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ag2-add-custom-tool, .gemini/skills/ag2-add-custom-tool, .github/skills/ag2-add-custom-tool and .opencode/skills/ag2-add-custom-tool in your project.

What does Ag2 Add Custom Tool need to run?

SKILL.md names no scripts, command-line tools or credentials: Ag2 Add Custom Tool is instructions for the agent only. Our summary lists: Python 3.

Does Ag2 Add Custom Tool access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Ag2 Add Custom Tool safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Ag2 Add Custom Tool use?

Ag2 Add Custom Tool is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ag2 Add Custom Tool use?

About 1.9k tokens (SKILL.md is roughly 7.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.3k tokens, read only when the agent opens those files.

What are the alternatives to Ag2 Add Custom Tool?

Skills that share tags, products or a category with Ag2 Add Custom Tool: Mastering Python Skill (SpillwaveSolutions/agent-brain, 119 stars), Framework Migration Assistant (ArabelaTso/Skills-4-SE, 253 stars), Pydantic AI (davila7/claude-code-templates, 33k stars) and Fastapi Backend (cohen-liel/hivemind, 110 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ag2 Add Custom Tool?

ag2ai (a GitHub organization) maintains it in ag2ai/build-with-ag2, which has 252 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on September 6, 2026.

Source: ag2ai/build-with-ag2 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.