What is function-calling?

Patterns for letting a language model call external tools through defined inputs and outputs. Function calling connects the model to actions or data outside the model and can return structured JSON.

Use them to connect models to APIs or other tools, define callable operations, validate inputs with Pydantic, and support structured or parallel tool calls.

They help developers design tool schemas and execution loops that validate model requests and handle tool results predictably.

function-calling — Command by ArieGoldkin

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 commands/ariegoldkin/claude-forge/function-calling

Clone the repo

git clone --depth 1 https://github.com/ArieGoldkin/claude-forge

Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 95 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.

Model	Per session	Once invoked
Fable 5	$0.00060	$0.00095
Opus 5	$0.00030	$0.00048
Sonnet 5	$0.00012	$0.00019
Haiku 4.5	$0.00006	$0.00010

Measured 2d ago against content hash 1526804d0dff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

function-calling 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 2d 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.

plugins/ai-toolkit/commands/function-calling.md · 12 lines

What it actually says