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-houdini --skill houdini-kinefxgit clone --depth 1 https://github.com/dcc-mcp/dcc-mcp-houdiniWrote 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-houdini/houdini-kinefx)<a href="https://agentmods.dev/skills/dcc-mcp/dcc-mcp-houdini/houdini-kinefx"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-houdini/houdini-kinefx/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-houdini/houdini-kinefx"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-houdini/houdini-kinefx.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 | $0.00086 | $0.01356 |
| Opus 5.5 | $0.00034 | $0.00542 |
| Sonnet 5.5 | $0.00017 | $0.00271 |
| Haiku 4.5 | $0.00009 | $0.00136 |
Grade A, and why
houdini-kinefx 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 7d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
houdini-kinefx
Typed KineFX character animation tools for agents. Scene tools are
affinity: main; the pure planning tools (plan_character_workflow,
design_character, biped_joint_map) are affinity: any — they need no Houdini
and are fully unit-testable headless.
KineFX operates at the SOP level — skeletons are geometry with joint point attributes, rigs are SOP networks, and mocap data is applied via SOP nodes.
The eight-stage character-animation workflow (codex design → hyper3d generation
→ Biped template → biped retarget → rig inversion → Motion Mixer full body IK →
ragdoll → KineFx APEX FBX biped template) is designed in
docs/guide/houdini-character-animation-workflow.md and returned as data by
plan_character_workflow. External codex/hyper3d steps degrade to offline
equivalents (design_character, import_generated_character).
Tool groups
workflow(pure/headless):plan_character_workflowreturns the full eight-stage design, gaps/enhancements, external-capability status and acceptance criteria;design_characteremits/validates a structured design spec (the codex equivalent);biped_joint_mapreturns cross-convention joint maps;import_generated_characteringests a generated mesh or builds a proxy (the hyper3d equivalent).rig:create_insect_rig(anatomy-aware honeybee),create_rig(generic joint chain),create_biped_template(standard 22-joint humanoid biped in 5 naming conventions),invert_rig(world→local rig inversion).pose:set_rig_posesets joint transforms;validate_ground_contactsverifies named support joints against one ground surface.capture:capture_jointscaptures skinning weights;deform_gsplat_with_rigdeforms GSplat centers and quaternion orientation.mocap:apply_mocapapplies FBX/BVH/clip mocap onto a rig skeleton.retarget/mixer:build_retarget_motion_mixerbuilds the Houdini 22 Rig Match Pose → Map Points → Full Body IK → MotionClip → APEX → Motion Mixer chain (now with optional explicit cross-conventionjoint_map);configure_biped_retargetbuilds a single-source retarget with an explicit naming map.simulation:build_ragdollbuilds proxy colliders, a constraint network and an RBD solver for a physics ragdoll.apex:build_apex_fbx_bipedpacks an APEX biped character and reports the engine-ready FBX export contract.
What ships with it
20 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/_character_common.py 10 KB runs code
- scripts/_kinefx_common.py 7.2 KB runs code
- scripts/apply_mocap.py 3.8 KB runs code
- scripts/biped_joint_map.py 2.1 KB runs code
- scripts/build_apex_fbx_biped.py 6.2 KB runs code
- scripts/build_ragdoll.py 9.3 KB runs code
- scripts/build_retarget_motion_mixer.py 13 KB runs code
- scripts/capture_joints.py 3.2 KB runs code
- scripts/configure_biped_retarget.py 9.2 KB runs code
- scripts/create_biped_template.py 3.0 KB runs code
- scripts/create_insect_rig.py 11 KB runs code
- scripts/create_rig.py 4.1 KB runs code
- scripts/deform_gsplat_with_rig.py 3.8 KB runs code
- scripts/design_character.py 5.9 KB runs code
- scripts/import_generated_character.py 8.0 KB runs code
- scripts/invert_rig.py 12 KB runs code
- scripts/plan_character_workflow.py 11 KB runs code
- scripts/set_rig_pose.py 5.2 KB runs code
- scripts/validate_ground_contacts.py 5.2 KB runs code
- tools.yaml 26 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.
- 7d ago Changed · +31 lines · +39 tokens per session 1d6e6956965e
- 2mo ago First seen · 58 lines · 47 tokens per session scan A ce0849c4f9d6
houdini-kinefx is a skill published in the GitHub repository dcc-mcp/dcc-mcp-houdini (19 stars, last pushed 4d ago), licensed MIT. It adds 86 tokens to every session and 1,356 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.
houdini-kinefx compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| houdini-kinefxdcc-mcp/dcc-mcp-houdini | Skill | 19 | 4d ago | MIT | A | 86 | Claude Code |
| maya-import-to-scenedcc-mcp/dcc-mcp-maya | Skill | 67 | 5d ago | MIT | A | 78 | Claude Code |
| usd-toolsdcc-mcp/dcc-mcp-core | Skill | 73 | yesterday | MIT | A | 83 | Claude Code |
| blender-physicsdcc-mcp/dcc-mcp-blender | Skill | 60 | yesterday | MIT | A | 29 | Claude Code |
| spatial-interchangedcc-mcp/dcc-mcp-core | Skill | 73 | yesterday | MIT | A | 35 | Claude Code, Codex |
| maya-riggingdcc-mcp/dcc-mcp-maya | Skill | 67 | 5d ago | MIT | A | 78 | Claude Code |
| blender-interchangedcc-mcp/dcc-mcp-blender | Skill | 60 | yesterday | MIT | A | 52 | Claude Code |