What is vrm-expression-agent-harness AGENTS.md?

A workflow guide for extending VRM avatar files with model-specific facial expressions. VRM is a file format for 3D humanoid avatars, and the guide explains how to inspect and safely transform those files.

Use it when creating expression extensions for VRM, VRMA, or GLB avatar models and when preparing the resulting files for WebUI preview.

It prevents agents from overwriting source files, inventing unsupported expressions, exposing private model files, or skipping required checks and reports.

How shinshin86/vrm-expression-agent-harness configures Codex and OpenC

Reuse

Borrowing it

Nothing to install: this file belongs to shinshin86/vrm-expression-agent-harness. 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/shinshin86/vrm-expression-agent-harness/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/shinshin86/vrm-expression-agent-harness

Made for: Codex, OpenCode.

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/instructions/shinshin86/vrm-expression-agent-harness/agents-md/github.svg)](https://agentmods.dev/instructions/shinshin86/vrm-expression-agent-harness/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/shinshin86/vrm-expression-agent-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/shinshin86/vrm-expression-agent-harness/agents-md/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/instructions/shinshin86/vrm-expression-agent-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/shinshin86/vrm-expression-agent-harness/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 447 This file is loaded in full into every session.

When invoked 447 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00447	$0.00447
Opus 5.5	$0.00179	$0.00179
Sonnet 5.5	$0.00089	$0.00089
Haiku 4.5	$0.00045	$0.00045

Measured 2mo ago against content hash fe7eea435f69, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

vrm-expression-agent-harness AGENTS.md 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.

AGENTS.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

You are an AI coding agent working in the VRM Expression Agent Harness.

Mission

Given a user-owned VRM file, produce the best model-specific AITuber expression extension that the file can honestly support. Follow the model-specific workflow: inspect, reason, derive from existing morph deltas, verify, self-review, and prepare for WebUI preview.

Non-Negotiable Rules

Read this file, docs/agent-operating-manual.md, and docs/success-contract.md before touching the target VRM.
Never overwrite the input VRM.
Never assume a universal conversion algorithm is sufficient.
Do not invent geometry or expressions without source morph material.
Keep source VRM/VRMA/GLB files and generated model files in the local workspace unless the user confirms they may be shared.
Keep reports focused on project-relative paths and model facts.
Every model-specific transformation script must live under that model's workspace output/scripts directory.
Run the self-review loop in harness/self-review-loop.md at least three times.

Required Outputs

For each target model, create an output folder containing:

extended VRM file with a new name,
INSPECTION.md,
PLAN.md,
EXPRESSIONS.md,
VERIFY.md,
SELF_REVIEW.md,
model-specific scripts used for inspection, derivation, and verification.

Required Expression Classification

For each requested expression, classify it as one of:

already_available
aliasable
derivable
unsupported

Unsupported is acceptable when the model lacks source morphs. Do not hide this.

Required Review Gates

Inspection review before writing derivation code.
Plan review before modifying any output VRM.
Structural verification after derivation.
Visual WebUI review after generation.
Asset and license review before final response.

Final Response Requirements

Report:

input and output filenames,
VRM version and license metadata summary,
expressions added, aliased, already available, and unsupported,
verification result,
WebUI preview instructions,
any residual risks.

Read the full file on GitHub · 61 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.

2mo ago First seen · 61 lines · 447 tokens per session scan A fe7eea435f69

Subscribe to this mod's changes

vrm-expression-agent-harness AGENTS.md is an instructions file published in the GitHub repository shinshin86/vrm-expression-agent-harness (21 stars, last pushed 4mo ago), licensed MIT. It adds 447 tokens to every session, about $0.0018 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.

Building agents Game development

vrm-expression-agent-harness AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
vrm-expression-agent-harness AGENTS.mdshinshin86/vrm-expression-agent-harness	Instructions file	21	4mo ago	MIT	A	447	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

vrm-expression-agent-harness: Instructions file for Codex