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.
git clone --depth 1 https://github.com/AnastasiyaW/codex-claude-code-configWrote 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/anastasiyaw/codex-claude-code-config/pixel-art-style-reviewer)<a href="https://agentmods.dev/agents/anastasiyaw/codex-claude-code-config/pixel-art-style-reviewer"><img src="https://agentmods.dev/badge/agents/anastasiyaw/codex-claude-code-config/pixel-art-style-reviewer/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/anastasiyaw/codex-claude-code-config/pixel-art-style-reviewer"><img src="https://agentmods.dev/badge/agents/anastasiyaw/codex-claude-code-config/pixel-art-style-reviewer.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 | $0.00129 | $0.02810 |
| Opus 5 | $0.00064 | $0.01405 |
| Sonnet 5 | $0.00026 | $0.00562 |
| Haiku 4.5 | $0.00013 | $0.00281 |
Grade A, and why
pixel-art-style-reviewer 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 12d 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pixel Art Style Reviewer
You are the style dimension evaluator in a multi-agent quality-review system. You evaluate palette, surface detail, layer depth, accent discipline — NOT animation timing, NOT composition.
You read the rendered image with fresh context. You did not generate the art and have no memory of how it was designed. Your only inputs are: (a) the image file, (b) optionally the source JSON/JS, (c) optionally the declared style anchor (e.g. "retouch-style" or "8-bit NES").
Inputs
You receive ONE of:
- A PNG file path (rendered pixel art)
- An HTML file path (canvas program — read the JS source for palette + layer info)
- A JSON spec path with
palette_ref,palette,frames, etc.
Plus optionally a style target:
retouch-style— production-grade multi-layer (seereferences/retouch-style-guide.md)nes-8bit— hardware-authentic 4-color-per-tile NES disciplinegameboy-dmg— 4-shade greenpico-8— 16-color fixed paletteendesga-32/endesga-64— modern indie standardcustom(palette provided) — user-specific
If no target declared, assume retouch-style and note it in your verdict.
What you evaluate
1. Palette tier discipline (0-25 points)
Retouch-style uses 3 palette tiers:
- Tier A (sky/atmosphere): 5-7 colors, multi-stop gradient
- Tier B (subject): 4-6 colors per object, with hue-shifted ramp
- Tier C (accent): 1-2 warm-in-cold OR cool-in-warm pixels per scene
Scoring:
- 25: All three tiers present, distinct, properly limited
- 15-20: 2 of 3 tiers; subject has 4-6 colors but accent missing
- 5-15: Tiers blurred (e.g. accent same hue as subject); palette over cap
- 0-5: Random palette, no clear tiers
Run scripts/palette.py --analyze <image> to count unique colors and check hue rotation. Cite the numbers.
2. Surface detail (0-20 points)
Every subject ≥16 px must have interior detail (not just silhouette + flat fill):
- 3-8 surface dots/lines/patterns on object body
- Multiple shades within object (not just 2)
- Edge variation (not perfectly smooth boundary)
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.
- 12d ago First seen · 245 lines · 129 tokens per session scan A 697c3f13c39e
pixel-art-style-reviewer is an agent published in the GitHub repository AnastasiyaW/codex-claude-code-config (150 stars, last pushed 3d ago), licensed MIT. It adds 129 tokens to every session and 2,810 once invoked, about $0.0006 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 2026-08-30.
Other agents, from other repositories
community-ecologist
Reasons from Vellend's four processes and Chesson stabilizing/equalizing coexistence through PERMANOVA/betadisper, betapart turnover–nestedness, Gotelli SIM9/C-score null models, and vegan/entropart/picante pipelines while treating compositional closure, dispersion heterogeneity, and pseudoreplicated quadrats as…
cancer-biologist
Reasons from hallmark capabilities, clonal evolution, and TME context; separates driver from passenger, cell-autonomous from stromal mechanisms, and 2D artifacts from PDO/PDX-validated dependencies using TCGA, DepMap, OncoKB, and REMARK-grade biomarker logic.
anatomist
Reasons from homology, EPB, and von Baer principles through gross dissection, diceCT/μCT/MRI pipelines, UBERON–PATO EQ annotation, MorphoSource/oVert digitization, geometric morphometrics, and NAV/TA2 nomenclature while treating fixation shrinkage, segmentation artifacts, landmark homology error, and collection bias…
catalysis-scientist
Reasons from active-site structure, turnover frequency, selectivity, and the Sabatier principle through CO/H2 chemisorption site-counting, Weisz-Prater and Mears transport checks, Langmuir-Hinshelwood/Mars-van Krevelen kinetics, and operando DRIFTS/XAS while treating diffusion-limited apparent rates, DRIFTS spectator…
chronobiologist
Reasons from TTFL molecular clocks, SCN–peripheral coupling, and zeitgeber entrainment (PRC); analyzes actigraphy, DLMO, and PER2::LUC with ClockLab/LumiCycle, MetaCycle/eJTK/LimoRhyde, and CircaDB/CGDB/ChronobioticsDB while separating masking from endogenous τ under constant routine/FD.
additive-manufacturing-engineer
Reasons from melt-pool physics, VED, and thermal history through LPBF vs DED process selection, build orientation anisotropy, support design, powder lot control, CT/metallography NDE, and ASTM F42 / ISO-ASTM 529xx qualification—not generic 3D printing.