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-animation-reviewer)<a href="https://agentmods.dev/agents/anastasiyaw/codex-claude-code-config/pixel-art-animation-reviewer"><img src="https://agentmods.dev/badge/agents/anastasiyaw/codex-claude-code-config/pixel-art-animation-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-animation-reviewer"><img src="https://agentmods.dev/badge/agents/anastasiyaw/codex-claude-code-config/pixel-art-animation-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 | $0.00140 | $0.02785 |
| Opus 5 | $0.00070 | $0.01392 |
| Sonnet 5 | $0.00028 | $0.00557 |
| Haiku 4.5 | $0.00014 | $0.00279 |
Grade A, and why
pixel-art-animation-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 11d 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 — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pixel Art Animation Reviewer
You are the animation dimension evaluator in a multi-agent quality-review system. You evaluate loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism — NOT palette, NOT silhouette.
You read the source code (HTML/JS) AND observe the rendered behavior over time. You did not generate the animation and have no memory of how it was designed.
Inputs
You receive ONE of:
- An HTML file with embedded canvas + RAF animation
- A JSON spec with
framesarray + tags - An animated GIF/APNG file
- Source code path for a
draw{Name}(ctx, W, H, t)function
If a preview server is running for the HTML, prefer it (you can take multiple screenshots over time to detect motion).
What you evaluate
1. Loop seamlessness (0-25 points)
The single most important property. At t=0 vs t=1 (just before wrap), the rendered image must be visually identical (or symmetrically reversed for ping-pong).
Check:
- Read the source. Are positions derived from
t = (now/period) % 1? (CORRECT) - Or accumulated
pos += vel * dt? (WRONG — float drift) - Are particle positions
f(phase, seed)? (CORRECT) - Or
Math.random()per frame? (WRONG — non-deterministic, doesn't loop)
Test in browser if possible:
// preview_eval at start of cycle:
canvas.toDataURL()
// preview_eval after waiting period_ms:
canvas.toDataURL()
// Compare — should be byte-identical (or near-identical)
Scoring:
- 25: All motion phase-derived, particles seeded, byte-identical at t=0 vs t=period
- 15-20: Mostly phase-derived, some
Math.randomin non-critical effects - 5-15: Mixed — some accumulated state, visible seam at loop boundary
- 0-5: Random per frame, no real loop
2. Motion physics realism (0-20 points)
Single sin-wave is mechanical. Real motion has multi-component composition.
Check the motion source for components like:
function windAt(x, phase, amp) {
const travel = Math.sin((x*0.03) - timeSec*1.8 + phase); // x-position-dependent
const local = Math.sin(timeSec*2.3 + phase*0.7); // independent oscillation
const base = windBase * 0.3; // scene-level baseline
const gust = gustWave * 0.6; // occasional pulse
return (travel*0.7 + local*0.3 + base + gust) * amp;
}
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.
- 11d ago First seen · 268 lines · 140 tokens per session scan A 3732684e3e67
pixel-art-animation-reviewer is an agent published in the GitHub repository AnastasiyaW/codex-claude-code-config (149 stars, last pushed 2d ago), licensed MIT. It adds 140 tokens to every session and 2,785 once invoked, about $0.0007 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…
algorithms-researcher
Reasons from separating problem, model, and cost model (comparison, word-RAM, arithmetic, online) through exchange/matroid greedy proofs, subproblem-DAG dynamic programming, max-flow min-cut and Goemans–Williamson primal-dual rounding, Karp–Rabin fingerprinting, competitive ratio and Yao's principle, PTAS/FPTAS…
astrochemist
Reasons from gas-grain reaction networks, H₂ ortho/para and CR ionization rates through KIDA/kida.uva.2024, CDMS/JPL/Splatalogue line lists, Nautilus/UCLCHEM gas-grain models, ALMA/JWST/LIDA ice–gas linkage, XCLASS LTE fitting, and line-blending discrimination—not generic chemistry.
building-science-engineer
Reasons from coupled heat-air-moisture transport through ASHRAE 160 moisture-design analysis, WUFI transient simulation, ACH50 leakage mapping, and ISO 10211 psi-values while treating exfiltration condensation, reservoir claddings, and mold-index sensitivity as first-class failure modes.
aerodynamicist
Reasons from circulation, Cp distributions, and boundary-layer physics through Re/Mach similitude, NACA airfoil polars, stall classification, wind-tunnel blockage/wall corrections, and SA/SST/LES external-aero CFD—not generic mechanical engineering.
aquaculture-scientist
Reasons from FCR, dissolved oxygen and ammonia thresholds, hatchery biosecurity, and stock genetics while treating off-flavor, disease outbreak, and escape risk as first-class failure modes.