What is dcc-mcp-maya-mgear AGENTS.md?

A repository instruction guide for a Maya mGear integration in the DCC-MCP ecosystem. It explains the repository layout and the commands used to check and test the skill files.

Use it when editing the Maya mGear skills, understanding their purpose, or running formatting, lint, and test checks.

It prevents agents from treating this skill-only repository like a normal Python package and gives them the project's actual validation steps.

How dcc-mcp/dcc-mcp-maya-mgear configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to dcc-mcp/dcc-mcp-maya-mgear. 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/dcc-mcp/dcc-mcp-maya-mgear/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/dcc-mcp/dcc-mcp-maya-mgear

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/dcc-mcp/dcc-mcp-maya-mgear/agents-md/github.svg)](https://agentmods.dev/instructions/dcc-mcp/dcc-mcp-maya-mgear/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/dcc-mcp/dcc-mcp-maya-mgear/agents-md"><img src="https://agentmods.dev/badge/instructions/dcc-mcp/dcc-mcp-maya-mgear/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/dcc-mcp/dcc-mcp-maya-mgear/agents-md"><img src="https://agentmods.dev/badge/instructions/dcc-mcp/dcc-mcp-maya-mgear/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,340 This file is loaded in full into every session.

When invoked 1,340 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	$0.01340	$0.01340
Opus 5.5	$0.00536	$0.00536
Sonnet 5.5	$0.00268	$0.00268
Haiku 4.5	$0.00134	$0.00134

Measured 1mo ago against content hash 17653b32b2b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dcc-mcp-maya-mgear 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 1mo 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 · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — dcc-mcp-maya-mgear

mGear Shifter rigging integration for the DCC-MCP ecosystem — inspect mGear environments, list Shifter components, create guides, build rigs, export rigs to FBX/Alembic, and export templates through typed MCP tools. Navigation map for AI agents, not a reference manual. Detailed tool tables and API live in README.md.

Repo shape — read this first

This is a skill-only repository. There is no pyproject.toml, no Python package, no justfile, and no PyPI publish step. The deliverable is the two skill directories under skill/, installed from Git through the marketplace:

dcc-mcp marketplace install dcc-mcp-maya-mgear --dcc maya
# -> ~/.dcc-mcp/marketplace/maya/dcc-mcp-maya-mgear/

If you were looking for an adapter package with a src/ layout, you are in the wrong repo — that is dcc-mcp-maya.

Build & test

CI runs everything on Python 3.12 with plain commands. No justfile — do not invent vx just recipes here.

pip install ruff
ruff check skill/ tests/
ruff format --check skill/ tests/

pip install pytest pyyaml dcc-mcp-core
pytest tests/ -q

Additional gates, all defined inline in .github/workflows/ci.yml:

skill-lint / skill-package — SKILL.md frontmatter must declare name: maya-mgear with metadata.dcc-mcp.depends; skill/maya-mgear/tools.yaml must list exactly 7 tools; metadata/depends.md must exist; scripts/ must contain .py files.
marketplace-lint — validates marketplace.json against a copy of the marketplace-v1 schema plus a relative-icon-exists check. Needs pip install jsonschema.
layout guard — root-level SKILL.md, tools.yaml, metadata/, and scripts/ are forbidden; the canonical paths are the two skill/*/ directories.

Lint config lives in ruff.toml: line-length 88, target-version = "py37", and a deliberately narrow rule set (E4, E7, E9, F) pinned so a ruff upgrade cannot silently widen it. Widen the rule set on purpose, never by accident.

Read the full file on GitHub · 76 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.

1mo ago First seen · 76 lines · 1,340 tokens per session scan A 17653b32b2b4

Subscribe to this mod's changes

dcc-mcp-maya-mgear AGENTS.md is an instructions file published in the GitHub repository dcc-mcp/dcc-mcp-maya-mgear (5 stars, last pushed 21d ago), licensed MIT. It adds 1,340 tokens to every session, about $0.0054 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 2026-09-29.

Building agents Creative and media agent-skills dcc-mcp maya mcp mgear model-context-protocol

dcc-mcp-maya-mgear AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
dcc-mcp-maya-mgear AGENTS.mddcc-mcp/dcc-mcp-maya-mgear	Instructions file	5	21d ago	MIT	A	1,340	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	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	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	2d ago	MIT	A	4,313	Codex, OpenCode

dcc-mcp-maya-mgear: Instructions file for Codex