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 agent-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/agent-creation-update)<a href="https://agentmods.dev/skills/sideshowroberto/vfx-agent-toolkit/agent-creation-update"><img src="https://agentmods.dev/badge/skills/sideshowroberto/vfx-agent-toolkit/agent-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/agent-creation-update"><img src="https://agentmods.dev/badge/skills/sideshowroberto/vfx-agent-toolkit/agent-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 | $0.00031 | $0.02759 |
| Opus 5.5 | $0.00012 | $0.01104 |
| Sonnet 5.5 | $0.00006 | $0.00552 |
| Haiku 4.5 | $0.00003 | $0.00276 |
Grade A, and why
agent-creation-update 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 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.
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 — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Creation & Update
Version: 1.0.0 Last Updated: 2025-10-25 Dependencies: Python 3.8+, VFX_SKILL_CONSTITUTION.md
Automate agent lifecycle management with constitutional compliance enforcement. Handles creation, updates, validation, and archiving of Claude Code agents following Article IX requirements.
Quick Start
Create New Agent
cd <workspace>\.claude\skills\agent-creation-update\scripts
python create_agent.py my-agent-name \
--description "Agent purpose. Use when scenarios. Triggers: keywords" \
--tools "Read,Write,Edit" \
--type general-helper
Update Existing Agent
python update_agent.py my-agent-name minor \
--changelog "Added feature X. Fixed bug Y."
Validate Agent
python validate_agent.py my-agent-name
Archive Agent
python archive_agent.py my-agent-name
Standard Workflows
Workflow 1: Create New Agent
Use When: Starting a new agent from scratch
Command:
cd <workspace>\.claude\skills\agent-creation-update\scripts
python create_agent.py <agent-name> \
--description "What it does. Use when scenarios. Triggers: keywords" \
--tools "Read,Write,Edit,Grep,Bash" \
--type <agent-type>
Agent Types:
tool-specialist- Expert in single tool (Blender, Unreal, Houdini)cross-tool- Coordinates workflows across multiple applicationsgeneral-helper- Utility agent (documentation, testing, validation)
What It Does:
- Validates agent name format (lowercase-with-hyphens, 3-50 chars)
- Loads agent template from
reference/agent_template.md - Replaces placeholders: {{NAME}}, {{DESCRIPTION}}, {{TOOLS}}, {{DATE}}
- Saves to
.claude/agents/<agent-name>.md - Validates created agent automatically
- Reports success or validation errors
Expected Output:
Agent created: .claude\agents\my-agent-name.md
Validation: PASSED (6/6 checks)
Success Criteria: Agent file created, validation passes (6/6), version 1.0.0
What ships with it
34 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.
- docs/CREATE_AGENT_USAGE.md 11 KB
- IMPLEMENTATION_SUMMARY_ARCHIVE.md 15 KB
- INTEGRATION_TEST_IMPLEMENTATION_SUMMARY.md 15 KB
- reference/agent_template.md 7.1 KB
- reference/examples/cross_tool_pipeline.md 14 KB
- reference/examples/general_helper.md 15 KB
- reference/examples/tool_specialist.md 8.9 KB
- reference/validation_rules.md 33 KB
- scripts/archive_agent.py 7.0 KB runs code
- scripts/ARCHIVE_QUICKSTART.txt 2.1 KB
- scripts/ARCHIVE_WORKFLOW.txt 14 KB
- scripts/create_agent.py 18 KB runs code
- scripts/README_ARCHIVE.md 9.7 KB
- scripts/README.md 9.8 KB
- scripts/test_create_agent.py 9.1 KB runs code
- scripts/test_update_agent.py 15 KB runs code
- scripts/test_validation.py 6.9 KB runs code
- scripts/update_agent.py 19 KB runs code
- scripts/validate_agent.py 17 KB runs code
- scripts/VALIDATION_IMPLEMENTATION_SUMMARY.md 12 KB
- scripts/VALIDATION_QUICK_START.txt 6.0 KB
- SKILL_COMPLETION_REPORT.md 18 KB
- tests/fixtures/sample_agents/.gitkeep 145 B
- tests/INTEGRATION_TEST_VISUAL_SUMMARY.txt 10.0 KB
- tests/manual_test_archive.py 7.7 KB runs code
- tests/QUICK_START.txt 3.1 KB
- tests/README.md 13 KB
- tests/run_all_tests.py 10 KB runs code
- tests/test_archive.py 15 KB runs code
- tests/test_create.py 166 B runs code
- tests/test_integration.py 22 KB runs code
- tests/test_update.py 162 B runs code
- tests/test_validate.py 163 B runs code
- UPDATE_AGENT_IMPLEMENTATION_SUMMARY.md 14 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.
- today First seen · 345 lines · 31 tokens per session scan A 3500cd071c85
agent-creation-update is a skill published in the GitHub repository sideshowroberto/vfx-agent-toolkit (16 stars, last pushed 22d ago), licensed MIT. It adds 31 tokens to every session and 2,759 once invoked, about $0.0001 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 2026-11-02.
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…