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 vfx-plangit 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/vfx-plan)<a href="https://agentmods.dev/skills/sideshowroberto/vfx-agent-toolkit/vfx-plan"><img src="https://agentmods.dev/badge/skills/sideshowroberto/vfx-agent-toolkit/vfx-plan/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/vfx-plan"><img src="https://agentmods.dev/badge/skills/sideshowroberto/vfx-agent-toolkit/vfx-plan.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 | $0.00058 | $0.01724 |
| Opus 5.5 | $0.00023 | $0.00690 |
| Sonnet 5.5 | $0.00012 | $0.00345 |
| Haiku 4.5 | $0.00006 | $0.00172 |
Grade A, and why
vfx-plan 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VFX Plan Skill
Purpose
Guides you to the right planning mode for a VFX task, helps clarify requirements before work begins, and optionally runs an adversarial review pass. Prevents the two most common planning failures: over-planning simple tasks and under-planning complex ones.
Usage
Invoke this skill when:
- Starting a new tool, script, or pipeline component
- Requirements feel ambiguous ("make it better", "set this up")
- The task touches multiple apps or files
- Getting it wrong means significant rework
- You don't fully understand the solution space yet
Simple questions with clear answers don't need planning. "What's the Python call to get selected objects in Blender?" - just ask.
Step 1 - Choose Your Mode
Answer: how well do I understand what I'm building?
Mode 1: Iterative
"I know what I want, not exactly how"
Use when requirements will evolve as you build. Discovery is part of the process.
VFX signals:
- Building a Houdini terrain generator - node network constraints emerge as you build
- Prototyping a ComfyUI workflow - which parameters matter reveals itself through iteration
- Writing a new Blender addon - UX changes based on what you see working
- Any first-time exploration of an API or tool
Process:
- State the broad goal clearly
- Build the first working version
- Observe what's actually needed
- Iterate toward stability
- Formalize as a skill when the pattern is proven
Keep planning docs short - guides, not contracts. The plan will change.
Mode 2: Spec-Driven
"I know exactly what I need to build"
Use when requirements are locked and you want zero gaps before writing code.
VFX signals:
- "Build a Nuke comp: Read -> ACES -> Grade -> DeepMerge -> Write, with these exact specs"
- "Export these 12 shots to these exact paths via Sequencer"
- "Batch render a folder of .blend files to EXR with these settings"
- Delivering a tool to a client or another team member
Process:
- Write the spec first - inputs, outputs, constraints, edge cases
- Claude drafts against the spec
- Validate output matches spec - the spec is the test
- Done
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 · 234 lines · 58 tokens per session scan A cd95f84f425e
vfx-plan is a skill published in the GitHub repository sideshowroberto/vfx-agent-toolkit (16 stars, last pushed 22d ago), licensed MIT. It adds 58 tokens to every session and 1,724 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 2026-11-02.
Other skills, from other repositories
skills-pr-handle
Use when explicitly asked to handle a pull request in the Scenario skills repository, including review comments and skill validation.
pr-handle-comments
Handle review comments received on GitHub for the current branch's PR or a given PR number or URL, by triaging each unresolved thread, fixing what is warranted, pushing, and replying in each thread, when asked to address, fix or answer PR comments. Works in any Scenario repository.
pr-summary
Refresh the current pull request description from its net changes, following the repository's PR template, when asked to update or write the PR summary. Works in any Scenario repository, whatever its default branch.
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…