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 ui-controlgit 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/ui-control)<a href="https://agentmods.dev/skills/dcc-mcp/dcc-mcp-core/ui-control"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-core/ui-control/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/ui-control"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-core/ui-control.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 155 Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
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 | $0.00084 | $0.02396 |
| Opus 5.5 | $0.00034 | $0.00958 |
| Sonnet 5.5 | $0.00017 | $0.00479 |
| Haiku 4.5 | $0.00008 | $0.00240 |
Grade A, and why
ui-control 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 yesterday.
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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DCC UI Control
The Agent Host owns user authorization. Core never enables the standalone Host's legacy native confirmation popup, including when menu invocation is allowed. Missing authorization remains a typed refusal; do not auto-approve or retry it through another input route. For bounded task authorization, use the project-owned DCC-CUA task bridge and its exact target/scope checks.
Use application UI automation only when a typed DCC skill, host API, or adapter
script reports unsupported or capability_missing. Policy denial, user
interruption, authentication, and desktop unavailability are stop conditions.
Backend order
- Use a typed DCC-MCP tool whenever one exists.
- For Chrome, Edge, launchers, and embedded webviews with DevTools access, set
DCC_MCP_UI_CONTROL_BACKEND=chrome(oredge) and use CDP. - For native application UI, set
DCC_MCP_UI_CONTROL_BACKEND=cuaand use the standalonedcc-cuaCLI/Host. mockis an explicit deterministic test backend only; production defaults todcc-cuaand never silently falls back to mock automation.
Core does not package an automation Host in its own release assets. The official
CLI installer reconciles the independently released dcc-cua companion; verify
it with dcc-mcp-cli components status dcc-cua or repair it with
dcc-mcp-cli components ensure dcc-cua --yes. For custom layouts, install
dcc-cua 0.4.0 or newer separately. Core probes the configured
DCC_MCP_INSTALL_DIR, the platform's standard dcc-mcp bin directory,
versioned standalone installs, and then PATH; set DCC_MCP_CUA_BINARY to an
absolute executable path only for a custom location. Core validates
dcc-cua manifest, ensures the shared Host, and keeps one
persistent JSONL bridge per active UI session. It prefers shared-memory image
transport when the native Core extension is present and otherwise uses bounded
binary attachments.
The CUA Host owns native accessibility, capture, banner/border/cursor markers, input scheduling, Escape interruption, browser CDP routing, and platform adapters. Core owns only DCC policy, normalized tool results, audit events, and artifact publication.
What ships with it
26 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.
- references/OWNED_PIXELS_MCP.md 8.9 KB
- scripts/_backend.py 25 KB runs code
- scripts/_cdp_runtime.py 20 KB runs code
- scripts/_chrome_backend.py 29 KB runs code
- scripts/_cua_backend.py 41 KB runs code
- scripts/_cua_cli_host_client.py 13 KB runs code
- scripts/_cua_lifecycle.py 2.3 KB runs code
- scripts/_cua_passive_preparation.py 5.9 KB runs code
- scripts/_cua_pixels.py 5.9 KB runs code
- scripts/_cua_preparation.py 15 KB runs code
- scripts/_cua_snapshot_result.py 3.2 KB runs code
- scripts/_cua_support.py 23 KB runs code
- scripts/_cua_window_frame.py 3.1 KB runs code
- scripts/_entrypoint.py 18 KB runs code
- scripts/_scenario.py 31 KB runs code
- scripts/act.py 390 B runs code
- scripts/capture_preparation.py 500 B runs code
- scripts/find.py 395 B runs code
- scripts/prepare_foreground.py 488 B runs code
- scripts/recording_start.py 441 B runs code
- scripts/recording_state.py 446 B runs code
- scripts/recording_stop.py 435 B runs code
- scripts/snapshot.py 415 B runs code
- scripts/stop_computer_use.py 460 B runs code
- scripts/wait_for.py 415 B runs code
- tools.yaml 29 KB
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.
- yesterday Changed · +11 lines 9c535dcc5e1d
- 15d ago Changed · +28 lines 481c05c17f62
- 27d ago Changed · +5 lines b40068e37b6b
- 1mo ago Changed · +6 lines 6b1e948a43a2
- 1mo ago Changed · +5 lines 2410b9185806
- 1mo ago First seen · 154 lines · 84 tokens per session scan A b9a36724e93b
ui-control is a skill published in the GitHub repository dcc-mcp/dcc-mcp-core (70 stars, last pushed today), licensed MIT. It adds 84 tokens to every session and 2,396 once invoked, about $0.0003 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 2026-08-30.
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.
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-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.
blender-viewport-capture
A Blender viewport capture tool, where the viewport is the window showing a 3D scene while you work. It saves an OpenGL or rendered preview screenshot for visual inspection.
comfyui-img2img
An image-to-image workflow for ComfyUI, a visual tool for running AI image-generation pipelines. It creates a new image from an existing one, including style changes, enhancement, and local redraws.
comfyui-node-installer
A ComfyUI tool for finding custom nodes missing from an image-generation workflow and installing their packages.