What is model-optimizer?

An automated agent that tests changes to a machine-learning model's inference code, keeping changes that reduce latency on a chosen device while preserving a required quality level.

It is for optimizing model inference speed on a fixed device, using an automatic keep-or-revert loop. It can be used with different models; the example targets the Wan 2.2 VAE decoder.

It removes the need to try performance changes manually and helps prevent faster code from lowering model quality. The target, limits, and stopping rules are read from goals.json.

How heygen-com/auto-model-optim configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to heygen-com/auto-model-optim. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/heygen-com/auto-model-optim/main/.claude/agents/model-optimizer.md

Clone the repo

git clone --depth 1 https://github.com/heygen-com/auto-model-optim

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/heygen-com/auto-model-optim/model-optimizer/github.svg)](https://agentmods.dev/agents/heygen-com/auto-model-optim/model-optimizer)

Your own site

<a href="https://agentmods.dev/agents/heygen-com/auto-model-optim/model-optimizer"><img src="https://agentmods.dev/badge/agents/heygen-com/auto-model-optim/model-optimizer/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/heygen-com/auto-model-optim/model-optimizer"><img src="https://agentmods.dev/badge/agents/heygen-com/auto-model-optim/model-optimizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 79 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 760 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 unknown 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 5.1	$0.00079	$0.00760
Opus 5.5	$0.00032	$0.00304
Sonnet 5.5	$0.00016	$0.00152
Haiku 4.5	$0.00008	$0.00076

Measured 2mo ago against content hash 37c55ea91625, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

model-optimizer 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 2mo 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.

.claude/agents/model-optimizer.md · 51 lines

The source is not reproduced here

No licence file

Read it on GitHub

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.

2mo ago First seen · 51 lines · 79 tokens per session scan A 37c55ea91625

Subscribe to this mod's changes

model-optimizer is an agent published in the GitHub repository heygen-com/auto-model-optim (7 stars, last pushed 4mo ago), with no licence file. It adds 79 tokens to every session and 760 once invoked, about $0.0003 per session on Opus 5.5. 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 Debugging

model-optimizer next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
model-optimizerheygen-com/auto-model-optim	Agent	7	4mo ago	none	A	79	Claude Code
dgx-spark-ops-engineerwshobson/agents	Agent	42k	yesterday	MIT	A	63	Claude Code
workflow-prompt-writergrowthxai/output	Agent	444	4d ago	Apache-2.0	B	42	Claude Code
pytorch-build-resolverloulanyue/awesome-claude-notes	Agent	271	1mo ago	MIT	A	52	Claude Code
alchemistpjt222/agent-almanac	Agent	43	yesterday	MIT	A	32	Claude Code
integration-checkerbrycewang-stanford/Auto-Empirical-Research-Skills	Agent	4.9k	4d ago	none	A	53	Claude Code
pixeltable-debuggerpixeltable/pixeltable-skill	Agent	6	2d ago	Apache-2.0	A	56	Claude Code

auto-model-optim: Agent for Claude Code