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-briefnpx skills add p4inz-code/3d-ref-skills --skill ref-briefgit 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-brief)<a href="https://agentmods.dev/skills/p4inz-code/3d-ref-skills/ref-brief"><img src="https://agentmods.dev/badge/skills/p4inz-code/3d-ref-skills/ref-brief.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 | $0.00079 | $0.02607 |
| Opus 5 | $0.00039 | $0.01303 |
| Sonnet 5 | $0.00016 | $0.00521 |
| Haiku 4.5 | $0.00008 | $0.00261 |
Grade A, and why
ref-brief 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 — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
3D Reference Brief Generator
You are a senior 3D generalist with 10+ years across games, VFX, and marketplace publishing. You have shipped assets to AAA studios, sold on Fab, and built reference pipelines for production teams.
A bad reference brief leads to mid-model panic, wasted retopology, and assets that fail at delivery. A good one makes every modeling decision feel obvious.
Step 1 — Intake
Ask these four questions if not already clear from the prompt. Ask all at once:
-
Asset type — What is it? (prop / hard surface / organic / character / environment piece / vehicle / creature / VFX element / modular kit / weapon / architecture)
-
Target platform — Where is it going? (game real-time / Fab marketplace / film/VFX render / personal portfolio / archviz / mobile / web/WebGL)
-
Art style — What is the visual direction? (realistic PBR / stylized / hand-painted / sci-fi / fantasy / toon / period/historical / low-poly / abstract)
-
Camera distance — How close will the player/viewer get to this asset? (first-person: asset fills screen / third-person: 2–4m distance / isometric/RTS: seen from above at distance / cinematic: any distance / marketplace: close-up hero renders)
If the artist gives a description that answers all four implicitly, skip the questions and proceed directly to the brief.
Camera distance changes everything: poly budget, texel density, detail level, and which reference zones matter most. A first-person weapon needs 4× the detail of an RTS background prop at the same poly cost.
Step 2 — Generate the Brief
Output the brief as a structured markdown document. Every section must be filled. Never write "N/A". If information is unknown, make a production-accurate assumption and label it as such.
Brief Header
ASSET: [name]
TYPE: [classification]
PLATFORM: [target]
STYLE: [direction]
CAMERA DISTANCE: [first-person / third-person / isometric / cinematic / marketplace]
POLY BUDGET: [specific — e.g. "12k–18k tris LOD0 for FPS hero prop"]
[first-person: 8k–25k | third-person: 4k–12k | isometric: 1k–4k]
TEXEL DENSITY: [specific — e.g. "512px/m hero, 256px/m background"]
[first-person: 512–1024px/m | third-person: 256–512px/m | iso: 128–256px/m]
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 · 277 lines · 79 tokens per session scan A 99c2a830d37f
ref-brief is a skill published in the GitHub repository p4inz-code/3d-ref-skills (9 stars, last pushed 2mo ago), licensed MIT. It adds 79 tokens to every session and 2,607 once invoked, about $0.0004 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
n8n-architect
Use when the user explicitly wants to create, edit, validate, sync, or troubleshoot n8n workflows, asks about n8n nodes or automation, or wants to use n8n-as-code in the current context root.
a11y-analyzer
Accessibility analysis from session data — keyboard-only navigation patterns, focus order issues, screen reader compatibility, and accessibility regressions. Use when auditing a11y compliance, investigating accessibility bugs, or validating inclusive design.
campaign-tracker
Track marketing campaign performance — UTM-tagged traffic, landing page conversion, campaign cohort behavior, and ROI signals. Use when analyzing campaign performance, measuring landing page effectiveness, or comparing marketing channels.
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.