shogun-scene

shogun-scene is a skill for Claude Code, Codex from dcc-mcp/dcc-mcp-shogun. It costs 70 tokens per session (541 once invoked), scanned A, original, MIT.

A set of controlled inspection tools for Vicon Shogun Post motion-capture scenes. It can read scene metadata, subjects, markers, skeletons, trajectories, object relationships, setup information, rigid bodies, channels, and camera presentation state.

In plain words
What is it for?
It is for examining a motion-capture scene, finding subjects and objects, reading bounded values at specific frames, checking setups and gaps, and changing limited display or selection state.
Why use it?
It gives an agent structured scene information through Shogun Post's local control interface without allowing arbitrary Python or HSL scripts.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for examining a motion-capture scene, finding subjects and objects, reading bounded values at specific frames, checking setups and gaps, and changing limited display or selection state.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dcc-mcp/dcc-mcp-shogun/shogun-scene
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.

Any agent
npx skills add dcc-mcp/dcc-mcp-shogun --skill shogun-scene
Clone the repo
git clone --depth 1 https://github.com/dcc-mcp/dcc-mcp-shogun

Made for: Claude Code, Codex.

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.

agentmods badge for shogun-scene

README.md
[![agentmods](https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-shogun/shogun-scene/github.svg)](https://agentmods.dev/skills/dcc-mcp/dcc-mcp-shogun/shogun-scene)
Your own site
<a href="https://agentmods.dev/skills/dcc-mcp/dcc-mcp-shogun/shogun-scene"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-shogun/shogun-scene/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.

agentmods 80×15 button for shogun-scene

Your own site · 80×15
<a href="https://agentmods.dev/skills/dcc-mcp/dcc-mcp-shogun/shogun-scene"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-shogun/shogun-scene.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 541 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 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00070 $0.00541
Opus 5 $0.00035 $0.00270
Sonnet 5 $0.00014 $0.00108
Haiku 4.5 $0.00007 $0.00054

Measured 10d ago against content hash 289cbd46b5e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

shogun-scene 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 10d ago.

The scan reads SKILL.md. This mod also ships 28 executable files (scripts/_result.py, scripts/clear_object_selection.py, scripts/get_bone_details.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

src/dcc_mcp_shogun/skills/shogun-scene/SKILL.md · 51 lines

What it actually says

Vicon Shogun Post Scene

Use these typed operations before considering UI Control. They connect only to the local Shogun Post control stream and never expose arbitrary Python or HSL execution.

Start with inspect_scene, then use the returned subject names for marker, skeleton, constraint, subject-parameter, or trajectory queries. The official Scene object model is capability-gated: use list_scene_objects before an object-detail, setup-parameter, channel, selection, or display-property call. Attribute inspection returns names only because values may contain production notes. Setup inspection accepts only LabelingSetup and SolvingSetup, and reports whether an expression exists without returning its source text. Rigid bodies are exact-type filtered; their details require one frame and return a bounded attached-marker inventory. Channel reads require one explicit frame, and gap lists are bounded. Camera inspection excludes device identifiers, firmware, and capture/video file paths. The three display/selection controls are non-destructive but can change the user's current view/selection. The Skill does not expose object creation, removal, renaming, reparenting, setup-parameter creation/expression edits, raw attribute/channel writes, or arbitrary HSL/Python. Use the separate shogun-files Skill for the three explicitly bounded file mutations implemented through the official SDK.

Paths returned by tools are reduced to file names. Adapter diagnostics must not publish SDK install directories, machine names, credentials, or full production scene paths.

Files

What ships with it

29 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 10d ago First seen · 51 lines · 70 tokens per session scan A 289cbd46b5e5

Subscribe to this mod's changes

shogun-scene is a skill published in the GitHub repository dcc-mcp/dcc-mcp-shogun (0 stars, last pushed 12d ago), licensed MIT. It adds 70 tokens to every session and 541 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.

Related

Other skills, from other repositories

maya-mgear

mGear Shifter deep integration - inspect environments, list components, create guides, build rigs, export templates, and import sample templates.

dcc-mcp/dcc-mcp-maya-mgear · 31 tokens

mgear-import-to-scene

Import asset files into Maya scene with mGear rigging context awareness, following the dccmcpcore.assetimport contract.

dcc-mcp/dcc-mcp-maya-mgear · 32 tokens

marmoset-lookdev

Domain skill - inspect Toolbag PBR materials and frame either the whole scene or an exact object for lookdev and render preparation. Use before material validation or camera rendering. Not for arbitrary Python execution.

dcc-mcp/dcc-mcp-marmoset · 46 tokens

marmoset-scene

Domain skill - inspect, import models, create explicit PBR materials, control visibility, save, and render the active Marmoset Toolbag scene through typed host operations. Use for Toolbag scene and camera-output workflows. Not for arbitrary Python execution.

dcc-mcp/dcc-mcp-marmoset · 56 tokens

shotgrid-crud

ShotGrid CRUD skill — create, read, update, and delete ShotGrid entities. Use when an AI agent needs to manage ShotGrid data: find entities, create new records, update fields, or delete/retire entities. Not for batch operations or schema queries.

dcc-mcp/dcc-mcp-fpt · 59 tokens

shotgrid-batch

ShotGrid batch operations skill — create, update, or delete multiple entities in a single API call. Use when an AI agent needs to perform the same operation on many entities efficiently. Not for single-entity CRUD — use shotgrid-crud.

dcc-mcp/dcc-mcp-fpt · 54 tokens