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 sideshowroberto/vfx-agent-toolkit --skill skill-creation-updategit clone --depth 1 https://github.com/sideshowroberto/vfx-agent-toolkitWrote 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/sideshowroberto/vfx-agent-toolkit/skill-creation-update)<a href="https://agentmods.dev/skills/sideshowroberto/vfx-agent-toolkit/skill-creation-update"><img src="https://agentmods.dev/badge/skills/sideshowroberto/vfx-agent-toolkit/skill-creation-update/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/sideshowroberto/vfx-agent-toolkit/skill-creation-update"><img src="https://agentmods.dev/badge/skills/sideshowroberto/vfx-agent-toolkit/skill-creation-update.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 | $0.00049 | $0.03933 |
| Opus 5.5 | $0.00020 | $0.01573 |
| Sonnet 5.5 | $0.00010 | $0.00787 |
| Haiku 4.5 | $0.00005 | $0.00393 |
Grade D, and why
skill-creation-update scanned grade D with 2 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 today.
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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls .claude/skills/SKILL_NAME/ Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf .claude/skills/skill-name How it starts
The opening of the file, as written. The whole thing — 422 lines — stays where its author put it; the contents beside it link to each section on GitHub.
skill-creation-update
Skill Version: 1.3.1 Last Updated: 2026-10-09 Dependencies: Python 3.12+, VFX_SKILL_CONSTITUTION.md (v2.0.0+) Status: Production-ready
Quick Start
Create New Skill
python .claude\skills\skill-creation-update\scripts\create_skill.py houdini-hda-export \
--description "Export Houdini Digital Assets for Unreal Engine" \
--triggers "hda export,houdini to unreal" \
--dependencies "Houdini 20+,UE 5.5+" \
--model sonnet
Validate Skill Compliance
# Validate Claude Code skill
python .claude\skills\skill-creation-update\scripts\validate_skill.py unreal-vfx-automation
# Output: Article I: [OK] PASS, Article III: [OK] PASS (470 lines), Overall: [OK] PASS
# Validate Agent OS standard
python .claude\skills\skill-creation-update\scripts\validate_skill.py unreal-engine-standards --agent-os
# Output: Agent OS Headers: [OK] PASS, Article III: [OK] PASS (414 lines), Overall: [OK] PASS
Test with Multiple Targets (Article I)
python .claude\skills\skill-creation-update\scripts\test_skill.py unreal-vfx-automation \
--targets Shot001,Shot002,Shot003
# Output: 3/3 passed [OK], Article I: [OK] VALIDATED
Update Skill Version
python .claude\skills\skill-creation-update\scripts\update_skill.py unreal-vfx-automation \
--version 1.1.0 \
--changes "Added Sequencer integration"
# Output: [OK] Updated to 1.1.0, [OK] Compliance maintained
Standard Workflows
Workflow 1: Create New Skill from Template
Steps:
- Plan scope: Identify repeatable workflow, verify 3+ projects can use it
- Run create_skill.py:
python .claude\skills\skill-creation-update\scripts\create_skill.py SKILL_NAME \ --description "What + When + Triggers (Article VIII)" \ --triggers "trigger1,trigger2,trigger3" \ --dependencies "Required software" \ --model sonnet - Verify structure:
ls .claude/skills/SKILL_NAME/ # Expected: SKILL.md, reference/, scripts/ - Fill SKILL.md sections: Quick Start, Workflows (3-5), Troubleshooting (4-5 issues)
- Create reference docs: Move detailed content to
reference/*.md - Validate line count:
wc -l .claude/skills/SKILL_NAME/SKILL.md # Must be <500 lines
What ships with it
11 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.
- reference/constitutional_validation.md 36 KB
- reference/skill_template_guide.md 30 KB
- scripts/auto_refactor.py 1.9 KB runs code
- scripts/batch_fix_skills.py 6.8 KB runs code
- scripts/batch_validate.py 2.4 KB runs code
- scripts/create_skill.py 12 KB runs code
- scripts/detailed_validate.py 2.1 KB runs code
- scripts/remove_model_field.py 2.6 KB runs code
- scripts/test_skill.py 14 KB runs code
- scripts/update_skill.py 15 KB runs code
- scripts/validate_skill.py 32 KB runs code
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.
- today First seen · 422 lines · 49 tokens per session scan D 5d768668c745
skill-creation-update is a skill published in the GitHub repository sideshowroberto/vfx-agent-toolkit (16 stars, last pushed 22d ago), licensed MIT. It adds 49 tokens to every session and 3,933 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it D with 2 findings (enumerates other installed skills, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-02.
Other skills, from other repositories
dcc-cua
A routing guide for controlling application interfaces through the project’s DCC-CUA system. DCC applications are digital-content tools such as Maya, Blender, and Houdini.
mesh-ops
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…
marketplace-publish-extension
Infrastructure skill — publish (register/update) an extension package to a marketplace catalog. Reads the extension's SKILL.md frontmatter, constructs a CatalogEntry, and upserts it into the target marketplace.json. Optionally commits and pushes when the catalog source is a git repository. Use after scaffolding an…
marketplace-create-extension
Infrastructure skill — scaffold a new marketplace extension package (SKILL.md + tools.yaml + scripts/) with MIT-0 licensing. Use when creating a publishable marketplace entry for any DCC host. Not for editing existing extensions or driving live DCC scenes — use domain skills for that.
clawhub-compat
Example skill — demonstrates full compatibility with the ClawHub/OpenClaw skill format. Use as a reference when creating skills for both the dcc-mcp-core ecosystem and ClawHub marketplace. Not intended for production use — this is an authoring reference only.
example-layered-skill
Example skill — reference implementation of the internal layered architecture pattern (Tools / Services / Utils) for complex skills with shared business logic. Use as a template when a skill outgrows a single scripts/execute.py file. Not intended for production use — see docs/guide/skills.md for the architectural…