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 marketplace-publish-extensiongit 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/marketplace-publish-extension)<a href="https://agentmods.dev/skills/dcc-mcp/dcc-mcp-core/marketplace-publish-extension"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-core/marketplace-publish-extension/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/marketplace-publish-extension"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-core/marketplace-publish-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Agent Snooping · line 26 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00088 | $0.01175 |
| Opus 5 | $0.00044 | $0.00588 |
| Sonnet 5 | $0.00018 | $0.00235 |
| Haiku 4.5 | $0.00009 | $0.00118 |
Grade A, and why
marketplace-publish-extension 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 12d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Marketplace Publish Extension
CLI-First Control Path
For marketplace and live-DCC operations, use the dcc-mcp skill and
dcc-mcp-cli whenever shell access is available. Its consent-gated install and
update check → update apply contract is the single source of truth; do not
invent a package-local CLI bootstrap path.
Publish (register or update) a DCC-MCP Skill, bundle, or Agent Plugin package
to a marketplace catalog (marketplace.json).
Prefer the CLI for local and CI publishing:
dcc-mcp-cli marketplace pack ./my-extension --out dist/
dcc-mcp-cli marketplace publish ./my-extension \
--catalog ./marketplace.json \
--install-url https://github.com/<owner>/<repo>/releases/download/v0.1.0/my-extension.zip \
--sha256 sha256:<digest> \
--min-core-version 0.19.0 \
--skill-root skill/my-extension
Tools
marketplace_publish_extension__publish
Scan an extension directory, build a CatalogEntry, and upsert it into the
target marketplace.json (local file or remote URL-backed file). When the
catalog source is a local git repository the tool can optionally commit and
push the change.
Prerequisites
- dcc-mcp-core installed
- Write access to the target marketplace catalog path
- Git (if using commit+push mode)
Release Gate — Python 3.7
- Verify py37 wheels exist and py37 CI is green before publishing.
py37-litefallback wheels do NOT satisfy the release gate. Native py37 builds are an LTS requirement with no automatic calendar expiry.- Confirm
requires-python = ">=3.7"inpyproject.tomlis unchanged. - Removing native py37 requires an accepted superseding ADR, a major release, and at least 180 days of notice.
Workflow
- Point the tool at a local Skill directory containing
SKILL.md, or an Agent Plugin directory containing rootplugin.jsonandskills/*/SKILL.md. - The CLI reads Skill frontmatter or Agent Plugin manifest metadata.
- Additional CLI-supplied fields (install url, ref, skill roots, tags,
maintainer, icon, and
showcase) are merged in. Use a repository-relative 16:9 PNG, JPEG, WebP, AVIF, or animated GIF path; the marketplace resolves it at the pinned 40-character Git revision. - A
CatalogEntryis built and upserted into the targetmarketplace.json. New catalogs use the v1skillslayout and preserve v1-only fields when an existing entry is updated. - If the catalog source is a git repo and
--commitis passed, the updatedmarketplace.jsonis committed and pushed.
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.
- 12d ago First seen · 113 lines · 88 tokens per session scan A 21ece640c987
marketplace-publish-extension is a skill published in the GitHub repository dcc-mcp/dcc-mcp-core (44 stars, last pushed yesterday), licensed MIT. It adds 88 tokens to every session and 1,175 once invoked, about $0.0004 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.
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-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.
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.