Testing patterns for applications that use large language models, including simulated model responses, asynchronous timeouts, and structured-output checks.

Use it to mock model calls, test asynchronous behavior, replay recorded interactions, and validate structured AI responses.

AI calls can be variable, slow, and difficult to reproduce, so ordinary tests may be unreliable or incomplete.

llm-testing — 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/llm-testing

Clone the repo

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

Or install atk, the plugin that ships this one along with the rest of its 16 skills, 25 commands, 1 agent, 1 hook.

Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 101 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	$0.00059	$0.00101
Opus 5	$0.00030	$0.00051
Sonnet 5	$0.00012	$0.00020
Haiku 4.5	$0.00006	$0.00010

Measured 3d ago against content hash acb37e03da06, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

llm-testing 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 3d 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/llm-testing.md · 12 lines

What it actually says

llm-testing

Invoking skill: atk:llm-patterns

Follow the instructions in the llm-patterns skill (testing patterns) exactly.

$ARGUMENTS

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.

3d ago First seen · 12 lines · 59 tokens per session scan A acb37e03da06

Subscribe to this mod's changes

llm-testing is a command published in the GitHub repository ArieGoldkin/claude-forge (5 stars, last pushed 25d ago), licensed MIT. It adds 59 tokens to every session and 101 once invoked, about $0.0003 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 2026-08-31.

Data and AI Testing agents ai anthropic aws claude claude-code

llm-testing

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

llm-testing

What this file has done since we first saw it

Other commands, from other repositories

prepare-dataset

flow-nexus-neural

git

checklist

clarify

specify