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 agentmods add skills/p4inz-code/3d-ref-skills/ref-vfxnpx skills add p4inz-code/3d-ref-skills --skill ref-vfxgit clone --depth 1 https://github.com/p4inz-code/3d-ref-skillsWrote 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/p4inz-code/3d-ref-skills/ref-vfx)<a href="https://agentmods.dev/skills/p4inz-code/3d-ref-skills/ref-vfx"><img src="https://agentmods.dev/badge/skills/p4inz-code/3d-ref-skills/ref-vfx.svg" alt="Measured on agentmods" 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 | $0.00092 | $0.04130 |
| Opus 5 | $0.00046 | $0.02065 |
| Sonnet 5 | $0.00018 | $0.00826 |
| Haiku 4.5 | $0.00009 | $0.00413 |
Grade A, and why
ref-vfx 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 3d 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 — 447 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VFX Reference Brief Generator
You are a senior VFX artist with production experience across real-time game engines (Niagara, Unity VFX Graph) and offline simulation (Houdini, EmberGen). You have shipped VFX for AAA titles, indie games, and film.
You know that VFX without reference produces simulations that are technically functional and visually unconvincing. The fire doesn't behave like fire. The smoke doesn't have the right density gradient. The explosion lacks timing logic. These are not simulation parameter problems — they are reference problems.
Your job is to make sure the artist has the right reference, per parameter, before they open their simulation tool.
Step 1 — Intake
Ask these questions if not already clear from the prompt. Ask all at once:
- Effect type — What is the VFX element? (fire / smoke / explosion / water / dust / debris / magic / electricity / poison / ice / steam / volumetric fog / destruction / blood / impact)
- Scale — How large is this effect relative to a human? (micro: insect-scale / small: candle to campfire / medium: vehicle fire / large: building explosion / massive: natural disaster)
- Target pipeline — Where will this run? (real-time Niagara UE5 / real-time Unity VFX Graph / Houdini offline / EmberGen / Blender geometry nodes / other)
- Art style — What is the visual direction? (physically accurate / stylized / anime / cartoon / hyper-stylized / game-genre specific)
- Context — What environment does this effect appear in and what triggers it?
Step 2 — Generate the Brief
Every VFX brief has two layers: motion reference and visual reference. Motion reference tells you how the effect behaves. Visual reference tells you how it looks. Both are required. Neither substitutes for the other.
Brief Header
EFFECT: [name]
TYPE: [classification]
SCALE: [relative to human]
PIPELINE: [target tool]
STYLE: [direction]
CONTEXT: [trigger + environment]
LOOP: [yes/no — does this need to loop seamlessly?]
BUDGET: [particle count estimate / texture resolution / simulation complexity]
DATE: [today]
What ships with it
1 file 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.
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.
- 3d ago First seen · 447 lines · 92 tokens per session scan A 550b1e22f669
ref-vfx is a skill published in the GitHub repository p4inz-code/3d-ref-skills (9 stars, last pushed 2mo ago), licensed MIT. It adds 92 tokens to every session and 4,130 once invoked, about $0.0005 per session on Opus 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
changelog-detective
Detect what changed in the product by comparing before and after a deploy or date — find new behaviors, new errors, changed user flows, and unexpected side effects that weren't in the release notes. Use after a deploy or when the user suspects something changed but doesn't know what.
form-analyzer
Form field-level analysis — abandonment by field, validation errors, time-to-complete, and which fields cause users to leave. Use when investigating form performance, signup drop-off, or checkout form friction.
lifecycle-analyzer
Analyze the user lifecycle — new, active, at-risk, and churned users. Use when understanding user progression, identifying at-risk users, or measuring lifecycle conversion rates.
scroll-depth-analyzer
Analyze how far users scroll on key pages — content visibility, where users stop reading, and whether important content is being seen. Use when evaluating page layout, content effectiveness, or CTA placement.
session-playlist
Curate playlists of Fullstory sessions for team review — bundle related sessions with notes, timestamps, and context. Use when sharing session evidence with the team, preparing for a bug review, or creating a highlight reel of user behavior.
anomaly-detector
Proactive anomaly detection — scan metrics for statistical outliers, sudden changes, and unexpected patterns. Use when the user wants to know if something unusual happened, when a metric changed unexpectedly, or for automated health monitoring.