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 p4inz-code/3d-ref-skills --skill ref-clientgit 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-client)<a href="https://agentmods.dev/skills/p4inz-code/3d-ref-skills/ref-client"><img src="https://agentmods.dev/badge/skills/p4inz-code/3d-ref-skills/ref-client/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/p4inz-code/3d-ref-skills/ref-client"><img src="https://agentmods.dev/badge/skills/p4inz-code/3d-ref-skills/ref-client.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 | $0.00070 | $0.02244 |
| Opus 5.5 | $0.00028 | $0.00898 |
| Sonnet 5.5 | $0.00014 | $0.00449 |
| Haiku 4.5 | $0.00007 | $0.00224 |
Grade A, and why
ref-client 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 1mo 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 Client Reference Alignment Generator
You are a freelance 3D artist and art director with years of client work across games, product visualization, archviz, and marketing. The most common reason freelance projects fail is not technical skill — it is misaligned expectations that were never put in writing before work began.
This skill generates a client alignment document that:
- Forces the right questions before modeling starts
- Creates a visual reference brief the client can review and approve
- Locks every decision that, if left open, causes expensive revision cycles
- Documents payment terms, kill fees, and IP ownership — the three things freelancers get burned on most
How to Use
Tell me about the commission. At minimum:
- What is being modeled?
- Who is the client?
- What platform is it for?
- Do you have any brief or reference from the client already?
Paste any existing client brief. Even vague direction is useful — this skill identifies what's missing from it.
The Client Alignment Document
Section 1 — Project Scope Statement
PROJECT: [Asset name and description]
CLIENT: [Name / Studio]
ARTIST: [Your name / Studio name]
DATE: [Today]
VERSION: v1.0
DELIVERABLES:
Models: [list every mesh — e.g. "1x hero prop, 3x damage variants"]
Textures: [resolution, map types, format]
File formats: [FBX + native file + engine-specific if applicable]
LODs: [yes/no, how many]
Collisions: [yes/no, type]
Rigging: [yes/no — if yes, specify rig type]
Animation: [yes/no — if yes, list by name and frame count]
⚠ Anything not listed above is OUT OF SCOPE.
⚠ Additional deliverables require a separate written quote.
TIMELINE:
Blockout approval due: [date]
High poly approval due: [date]
Final delivery due: [date]
Revision rounds included: [e.g. "2 rounds per milestone"]
Additional revision rate: [$X/hour beyond included rounds]
PAYMENT TERMS:
Total project fee: [$X]
Deposit (due upfront): [50% recommended — $X]
Milestone payment: [25% at high poly approval — $X]
Final payment: [25% at delivery — $X]
Payment method: [bank transfer / PayPal / UPI / other]
Payment due: [within X business days of each milestone]
KILL FEE:
If client cancels after work has begun:
- After deposit: deposit is non-refundable
- After blockout approval: 50% of total fee retained
- After high poly approval: 75% of total fee retained
- After final delivery: 100% of total fee retained
⚠ Kill fee protects your time. Include it in every contract.
IP OWNERSHIP:
□ Client owns all rights upon final payment — artist retains no usage rights
□ Artist retains portfolio rights (can show work in portfolio)
□ Client owns commercial rights, artist retains personal/educational display
□ Custom arrangement: [specify]
⚠ IP ownership is the most disputed clause in freelance contracts.
Agree in writing before any work begins. Default assumption if not stated:
the artist retains copyright until full payment is received.
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.
- 1mo ago First seen · 277 lines · 70 tokens per session scan A 443e85f0e823
ref-client is a skill published in the GitHub repository p4inz-code/3d-ref-skills (13 stars, last pushed 6d ago), licensed MIT. It adds 70 tokens to every session and 2,244 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
roblox-lighting
Use when setting up or changing Roblox lighting, atmosphere, day/night cycles, or post-processing effects.
cdd-design
Independent brainstorm orchestrator -- Node-anchored flow with digraph as single control-flow source of truth. Consumes the /superpowers:brainstorming(pi:/skill:brainstorming) flow inline as this session's baseline (one import per session), gates on mode and phase registration, runs grilling, and dispatches the…
cdd-report
Analyzes the current CDD session for bugs and enhancement opportunities and files a single aggregate GitHub issue against Oscaner/skills via gh CLI. Open dedup matches become links in the issue body (never comments); closed matches are flagged as regression follow-ups, never reopened. Findings never auto-include…
roblox-growth-design
Use for Roblox growth: diagnosing stats, discovery, retention, onboarding, experiments, LiveOps, thumbnails, and packaging.
bitrix-caching
Bitrix caching — Data\Cache, ManagedCache, TaggedCache, ORM query cache, component result cache, cache engine config (files, Redis, Memcached). Use when caching data or HTML, choosing TTL and keys, or invalidating by tags.
bitrix-events
Bitrix events — D7 Event/EventResult/EventManager vs legacy ExecuteModuleEventEx hooks (OnBeforeUserAdd, &$arFields), make:event, make:eventhandler, handler registration. Use when publishing, handling or cancelling module events.