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.
npx skills add dcc-mcp/dcc-mcp-shogun --skill shogun-pipelinegit clone --depth 1 https://github.com/dcc-mcp/dcc-mcp-shogunWrote 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.
[](https://agentmods.dev/skills/dcc-mcp/dcc-mcp-shogun/shogun-pipeline)<a href="https://agentmods.dev/skills/dcc-mcp/dcc-mcp-shogun/shogun-pipeline"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-shogun/shogun-pipeline/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.
<a href="https://agentmods.dev/skills/dcc-mcp/dcc-mcp-shogun/shogun-pipeline"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-shogun/shogun-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00063 | $0.00807 |
| Opus 5 | $0.00032 | $0.00404 |
| Sonnet 5 | $0.00013 | $0.00161 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
shogun-pipeline 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 11d 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.
What it actually says
Vicon Shogun Post Pipeline
Use shogun-pipeline__run_pipeline_command only after inspecting the scene,
saving a recovery copy, and confirming the intended production parameters.
The host operator must set DCC_MCP_SHOGUN_PIPELINE_ALLOWLIST to a
comma-separated list of exact installed command identifiers before starting
the adapter. They must also set DCC_MCP_SHOGUN_PIPELINE_ABI=fixed9-v1 to
attest that every enabled command implements the exact positional contract
below. No commands are enabled by default, and an absent or unsupported ABI
attestation fails before the adapter connects to the host.
The command contract is fixed and positional:
command(load_type, processing_mode, export_c3d, export_fbx, fill_gap_mode, fill_gap_width, filter_cutoff, filter_threshold, label_threshold)
A no-argument host script is not directly compatible with fixed9-v1. It may
only be invoked through a separately audited host wrapper that implements this
exact signature. The adapter does not discover, install, or rewrite wrappers.
Modes and Boolean values are converted to bounded numeric literals. The public tool never accepts HSL source, script paths, free-form strings, extra arguments, or command-line fragments. A command absent from the operator allowlist fails before connecting to the host. Invalid configuration, missing HSL capability, and host or scene rejection return bounded typed errors; there is no Python, UI automation, or arbitrary HSL fallback.
The official HSL bridge returns a command result string but provides no generic scene-state read-back for custom scripts. The tool therefore reports only whether the host call returned and whether a result was present; it does not expose the result text or claim that custom scene effects were verified. Follow with the narrowest applicable typed scene inspection tool.
This tool is asynchronous and monolithic. Its first response is a Core-owned
pending job receipt. Keep the exact Shogun host process and its adapter sidecar
running, retain the Core job ID, and poll jobs_get_status with
include_result: true until the job is terminal. A completed Core job means the
worker stopped; it does not by itself mean the nested Shogun operation succeeded.
Inspect the nested Skill result for success or a bounded error, then perform the
typed scene or artifact verification required by the command.
The 1800-second timeout hint is scheduling metadata, not a cancellable HSL
deadline or a sidecar lifetime guarantee. The CLI wait default is 600 seconds;
for an expected 30-minute call, use --wait-timeout-secs 1800 or poll the saved
job ID separately. If the sidecar stops, the job becomes interrupted and the
scene may have an unknown effect. This destructive, non-idempotent operation
must not be replayed automatically after a timeout, disconnect, or restart.
What ships with it
2 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.
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.
- 11d ago First seen · 68 lines · 63 tokens per session scan A 16157d945082
shogun-pipeline is a skill published in the GitHub repository dcc-mcp/dcc-mcp-shogun (0 stars, last pushed 13d ago), licensed MIT. It adds 63 tokens to every session and 807 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.
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.
mgear-import-to-scene
Import asset files into Maya scene with mGear rigging context awareness, following the dccmcpcore.assetimport contract.
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.
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.
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.
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.