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-substance3d-painter --skill painter-projectgit clone --depth 1 https://github.com/dcc-mcp/dcc-mcp-substance3d-painterWrote 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-substance3d-painter/painter-project)<a href="https://agentmods.dev/skills/dcc-mcp/dcc-mcp-substance3d-painter/painter-project"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-substance3d-painter/painter-project/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-substance3d-painter/painter-project"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-substance3d-painter/painter-project.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 | $0.00056 | $0.01578 |
| Opus 5.5 | $0.00022 | $0.00631 |
| Sonnet 5.5 | $0.00011 | $0.00316 |
| Haiku 4.5 | $0.00006 | $0.00158 |
Grade A, and why
painter-project 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 1mo 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Painter Project
Every tool in this skill runs through Painter's main-thread bridge and returns
a core job envelope. Use --wait when calling through dcc-mcp-cli, or poll
jobs_get_status with the returned job_id until the job is terminal.
execute_materialized_script is the bounded companion to Core's
materialize_script. It accepts only the unchanged Python file_ref returned
by Core: no inline source, direct path, arguments, execution mode, or UI route.
A FileRef proves source identity and freshness; it is not a trust decision or a
same-process Python security sandbox. Materialize only source trusted to run
with the current Painter process privileges. Reflective code or background work
intended to outlive the fixed request lifecycle is outside this tool contract.
Before Painter runs the fixed main() entry point, the adapter verifies the
materialization sidecar, scoped path, regular-file identity, single-link
ownership, size, UTF-8 encoding, digest, expiry, and a stable file snapshot.
The full security and expiry check is repeated immediately before main-thread
dispatch. Execution remains bound to the validated function definition, its
prefix helpers/imports, and its prefix globals. The adapter invokes that
entrypoint through a host callable captured before source entry. Direct json
and executor-module imports resolve to request-private JSON state. The executor
import is a minimal facade with no executor callables or canonical module state,
so a retained facade cannot regain host globals after return. The adapter
snapshots the strict JSON result when valid and executes suffix source exactly
once after every source-entered main() attempt in a quarantined side-effect
phase. Rebinding, object/module attributes, and mutable aliases in suffix source
cannot change the captured behavior or result, and
suffix failures do not clobber the main outcome (including a stable rejection
for invalid results). The suffix is side-effect-only; if main() needs a helper,
import, or mutable initialization introduced only by that suffix, execution
fails closed with script_suffix_dependency. Define all main() dependencies
before the entrypoint.
Cancellation is propagated only from the exact host token and job captured
before source entry; source-installed ambient tokens are rejected as execution
failures. The captured host ContextVar state, cancellation module bindings,
validator alias, and canonical JSON serializer are restored after both source
phases. These fixed-contract guarantees do not isolate arbitrary untrusted
Python running in Painter's process. Results
must be strict portable JSON with plain string-keyed objects and plain lists;
tuples, custom mappings, non-string keys, nested NaN, and Infinity are rejected.
Host-owned validation enforces maximum container depth 64, 10,000 value nodes,
and 256 KiB of compact UTF-8 JSON. The byte limit covers the complete public
response, including host-owned context and postcondition fields. Rejected
contracts return stable error codes without exposing host paths.
| Contract state | Result | Painter source entered |
|---|---|---|
| Exact, live Core FileRef and unchanged snapshot | Pre-suffix validated main() result plus digest/size postcondition; suffix still runs once |
Yes |
| Missing/extra fields, inline/path/mode input, wrong scope, or expired | file_ref_invalid, file_ref_scope_denied, or file_ref_expired |
No |
| Link, hardlink, replacement, identity, size, or digest drift | Stable file_ref_* integrity error |
No |
| Non-UTF-8 source, invalid syntax, or invalid fixed entry contract | Stable script_* error with rematerialization prompt |
No |
main() depends on helper/import/state introduced only by the suffix |
script_suffix_dependency without retry/rematerialization prompt |
Yes |
| Exception, forged adapter/cancellation error, or invalid/over-budget result after source entry | Stable script_* error without retry/rematerialization prompt; suffix still runs once |
Yes |
What ships with it
25 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.
- scripts/add_generator_effect.py 3.1 KB runs code
- scripts/add_mask.py 4.7 KB runs code
- scripts/apply_smart_material.py 1.5 KB runs code
- scripts/bake_mesh_maps.py 7.6 KB runs code
- scripts/close_project.py 1.0 KB runs code
- scripts/create_export_preset.py 821 B runs code
- scripts/create_pbr_fill_layer.py 2.9 KB runs code
- scripts/create_project.py 3.3 KB runs code
- scripts/create_textured_pbr_layer.py 3.3 KB runs code
- scripts/execute_materialized_script.py 1.3 KB runs code
- scripts/export_textures.py 6.6 KB runs code
- scripts/import_resource.py 4.3 KB runs code
- scripts/insert_paint_layer.py 2.0 KB runs code
- scripts/inspect_camera.py 841 B runs code
- scripts/inspect_project.py 4.4 KB runs code
- scripts/list_export_presets.py 1.4 KB runs code
- scripts/list_layer_stack.py 1.2 KB runs code
- scripts/list_texture_sets.py 862 B runs code
- scripts/open_project.py 1.5 KB runs code
- scripts/reload_mesh.py 2.8 KB runs code
- scripts/save_project_as.py 1.6 KB runs code
- scripts/save_project.py 1.6 KB runs code
- scripts/search_resources.py 2.1 KB runs code
- scripts/start_camera_orbit.py 3.7 KB runs code
- tools.yaml 31 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.
- 1mo ago First seen · 116 lines · 56 tokens per session scan A a433a72911f5
painter-project is a skill published in the GitHub repository dcc-mcp/dcc-mcp-substance3d-painter (0 stars, last pushed yesterday), licensed MIT. It adds 56 tokens to every session and 1,578 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
designer-session
Host skill - inspect, author, save, and export a Substance 3D Designer graph. Use when an Agent needs bounded node, connection, parameter, gradient, output, package, resource, map, or SBSAR operations instead of arbitrary Python execution.
designer-offline
Offline artifact skill - cook hash-pinned SBS sources and render compiled SBSAR maps and bake pinned UV0 mesh positions and FBX colour IDs with installed official Substance tools without a Designer GUI.
designer-effects
Host skill - apply discoverable procedural effect recipes (blur, warp, levels, sharpen, edge detect, blend, mask) to a Substance 3D Designer graph. Use when an Agent needs bounded effect-chain authoring instead of arbitrary node surgery.
designer-animation
Host animation skill - discover time-like Designer inputs and bake ordered frames by sweeping one of them across a bounded range.
designer-dynamics
Host dynamics skill - sweep an integer iteration-count parameter in a Substance 3D Designer graph and bake each pass as a separate verified texture.
designer-lighting
Host skill - bake lighting-response maps (normal, ambient occlusion, curvature, thickness, emissive) from a height or mask source in Substance 3D Designer.