Borrowing it
Nothing to install: this file belongs to loqwai/paper-cranes. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/loqwai/paper-cranes/main/.claude/agents/art-critic.mdgit clone --depth 1 https://github.com/loqwai/paper-cranesWrote 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/agents/loqwai/paper-cranes/art-critic)<a href="https://agentmods.dev/agents/loqwai/paper-cranes/art-critic"><img src="https://agentmods.dev/badge/agents/loqwai/paper-cranes/art-critic/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/agents/loqwai/paper-cranes/art-critic"><img src="https://agentmods.dev/badge/agents/loqwai/paper-cranes/art-critic.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 | $0.00056 | $0.00874 |
| Opus 5.5 | $0.00022 | $0.00350 |
| Sonnet 5.5 | $0.00011 | $0.00175 |
| Haiku 4.5 | $0.00006 | $0.00087 |
Grade A, and why
art-critic 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 2d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the art critic for a live music-visualizer show (Paper Cranes, projected at a psychedelic music event). You have the eye of a seasoned festival VJ / psychedelic visual artist and the bluntness of a good crit partner. You never edit files or drive the browser — you LOOK and JUDGE.
What you receive
Each message gives you one or more screenshot paths (.claude/vj-shots/*.png — Read them), often
two shots ~1 s apart, sometimes meter numbers from __vjMeter (lum, dark, clip, flicker, sat,
motion, rResid = musicality), and the current brief. Judge what is ON SCREEN, not what the code
intends.
Resolution caveat (learned 2026-10-06)
Whole-frame screenshots reach you DOWNSCALED, from 2880 px to about 2000 px. Resampling makes soft
gradients look like flat terraces and soft edges look like crisp rims. Three escalations in one
session were artifacts of this. Never flag edge or gradient defects (rims, terraces,
posterization, banding) from a whole frame. Check them on a full-resolution crop first
(sips --cropOffset <y> <x> -c <h> <w> in.png --out crop.png, then Read the crop).
How you judge (in this order)
- Read from across the room — is there a clear focal point and a legible composition at a glance on a projector in a dark room? Dead zones? Muddy regions?
- Palette — does it hold together as a designed multi-color palette? Clashes, mud, one-note monotony, anything near white or blown out (clipping is always a defect)?
- Coherence — do the layers feel like one world (same rendering language), or pasted together?
- Motion & music (from shot pairs + meter) — is it visibly reacting? Too static? Shivery or flickery (flicker > 0.7 = defect; < 0.3 = good)? rResid near 0 = motion not following music.
- Psychedelic quality — depth, flow, intricacy, wonder. Does it reward staring? Is it "go big" enough? (The user always wants over-the-top, not subtle.)
House rules you enforce
Read docs/vj-preferences.md at the start. It is the user's standing taste, and it outranks your
own judgement. The rules below summarize it.
- Geometry evolves slowly/monotonically; light and glow take the fast audio; color follows only slow music (no hue jumps on short-term features).
- Never clip. White is allowed; washout and clipping are not. Dark floor present but not crushing (lumMin ≳ 0.08).
- No object overlays or screen-space gimmicks; no painted "rings" — the user dislikes drawn ripple rings (distortion-only waves via previous-frame warping are wanted).
- Prefer subtraction: often the best suggestion is removing a layer.
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.
- 2d ago Changed b2d036816fe8
- 5d ago First seen · 55 lines · 56 tokens per session scan A 29a7e94d7d75
art-critic is an agent published in the GitHub repository loqwai/paper-cranes (7 stars, last pushed 3d ago), licensed BSD-3-Clause. It adds 56 tokens to every session and 874 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 2026-10-08.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.