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-core --skill dcc-cuagit clone --depth 1 https://github.com/dcc-mcp/dcc-mcp-coreWrote 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-core/dcc-cua)<a href="https://agentmods.dev/skills/dcc-mcp/dcc-mcp-core/dcc-cua"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-core/dcc-cua/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-core/dcc-cua"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-core/dcc-cua.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00131 | $0.01556 |
| Opus 5 | $0.00066 | $0.00778 |
| Sonnet 5 | $0.00026 | $0.00311 |
| Haiku 4.5 | $0.00013 | $0.00156 |
Grade A, and why
dcc-cua 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DCC-CUA — Project UI Control Router
Use this Skill as the canonical route whenever the user explicitly names
dcc-cua, DCC CUA, our dcc-cua, or 我们的 dcc-cua.
Non-substitution contract
An explicit DCC-CUA request is a hard routing boundary, regardless of whether the target is Maya, Chrome, a browser, or another desktop application.
- Use the project-owned
dcc-cuaruntime and DCC-MCPui-controlsurface. - Never load or call generic Codex/OpenAI Computer Use, the
computer-useSkill,@oai/sky, or Browser/Chrome automation plugins for that request. - Never treat a DCC-CUA runtime, binding, readiness, or permission failure as permission to change providers.
- Repair the project route when safely possible. Otherwise report the exact blocker and stop.
- Use a generic provider only after the user explicitly retracts the DCC-CUA requirement or explicitly requests that provider by name.
This boundary is provider selection, not an authorization bypass. DCC-CUA task grants, target binding, interruption, and confirmation policy still apply.
Runtime preflight
Use the official component contract; do not download an arbitrary executable:
dcc-mcp-cli components status dcc-cua
dcc-mcp-cli components ensure dcc-cua --yes
dcc-cua manifest
dcc-cua ping
Run components ensure only when installation or repair is authorized. It
consumes the official versionless manifest, verifies the declared SHA-256, and
reconciles the independently released companion executable.
For semantic application profiles:
dcc-cua profiles
dcc-cua profile --id <profile-id>
Do not invent a profile ID. Runtime-advertised capabilities are authoritative.
Execution order
- Prefer a typed DCC-MCP host tool when it directly expresses the operation.
- Use DCC-CUA only for the UI behavior that typed host tools cannot expose.
- Bind one exact target with process ID and native window handle whenever the surface supports them.
- Open one scoped session with the minimum task grant required for the work.
- Take a fresh observation before each action that depends on UI state.
- Act using stable semantic control or DOM references when available.
- Wait for a typed state transition and verify the real final state.
- Stop the session on success, failure, interruption, or abandonment.
What ships with it
1 file 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.
- 9d ago First seen · 148 lines · 131 tokens per session scan A 8a9958a270c5
dcc-cua is a skill published in the GitHub repository dcc-mcp/dcc-mcp-core (42 stars, last pushed today), licensed MIT. It adds 131 tokens to every session and 1,556 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
artclaw-tool-creator
A guided tool for creating custom tools in the ArtClaw system, which connects an AI assistant with digital-content applications. It can package an existing skill, generate a script, or combine tools, then preview and save the result.
houdini-simulation
A Houdini guide for building smoke, fire, rigid-body, fluid, and cloth simulations. It covers the usual node steps for setting up, solving, processing, and caching these effects.
sd-node-ops
A Substance Designer guide for creating, connecting, and configuring nodes in material graphs, which are step-by-step networks that produce textures.
houdini-node-ops
A Houdini guide for creating and connecting nodes and setting their parameters. Houdini is a 3D application that builds many models and effects as connected processing steps called nodes.
ue5-blueprint-workflow
UE5.6/UE5.7 Blueprint graph workflow for feature implementation, input events, node wiring, and graph validation. Use when requests involve adding Blueprint logic, keyboard input behavior, function chains, event graph edits, or pin-level connection guidance.
blender-context
A read-only Blender context inspector, where Blender is software for creating and rendering 3D scenes. It reports the current selection, scene contents, file, viewport camera, and collection hierarchy.