mesh-ops skillA
mesh-ops is agent-read markdown (skill) from dcc-mcp/dcc-mcp-core: Cross-adapter polygon modeling recipe pack for the shared cross-DCC modeling vocabulary. Structured RECIPES.yaml entries for primitive creation, hard-surface edits, topology cleanup, UV generation, radial arraying, and material assignment. Reusable by every DCC adapter's mesh-ops skill (maya, blender, houdini, 3dsmax, and custom hosts) before falling back to raw scripting..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# mesh-ops Cross-adapter polygon modeling recipes for the shared cross-DCC modeling vocabulary. Every recipe is a DCC-agnostic plan: a validated `inputs_schema`, an ordered list of `steps` that dispatch the canonical `mesh_ops__<verb>` tool, a Draft 2020-12 `output_contract`, and a `toolset_profiles: [mesh-ops]` binding. ## How to use 1. `recipes__list` with `skill: mesh-ops` to see the available recipes. 2. `recipes__get` a recipe to read its `inputs_schema`, `steps`, and `output_contract`. 3. `recipes__validate` candidate inputs against the recipe schema before dispatching. 4. `recipes__apply` to obtain the execution plan, then materialize and dispatch the returned `steps` (see "Dispatch contract" below). ## Cross-adapter contract - `dcc: any` — a recipe is not tied to one host; the same plan applies in every DCC adapter that implements the shared modeling verb. - `toolset_profiles: [mesh-ops]` — the recipe belongs to the mesh-ops toolset carried by each adapter's mesh-ops skill. - `steps[].tool` uses the canonical `mesh_ops__<verb>` name, never an adapter-specific slug. - `inputs_schema` is a Draft 2020-12 schema validated by Core without a …
Read the whole file at its exact version.
How to install
mdr add dcc-mcp/dcc-mcp-core/mesh-ops@git:20260918.477d57emdr add dcc-mcp/dcc-mcp-core/mesh-ops@sha256:f8f064e609bf5b6fPin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_ornh5jdr4lwmhuf6)
1 badge views in 30 days
Versions
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5564 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
dcc-mcp/dcc-mcp-core · 47 stars · license MIT · pushed 2026-09-23 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ornh5jdr4lwmhuf6 GET https://markdownregistry.com/api/v1/resolve?ref=dcc-mcp/dcc-mcp-core/mesh-ops GET https://markdownregistry.com/api/v1/blob/f8f064e609bf5b6f7d27feb48a948653326dfb13219257e1dc86665d44eff645
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.