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/RemakeBench/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/plugins/remakebench/skills/skills)<a href="https://agentmods.dev/plugins/remakebench/skills/skills"><img src="https://agentmods.dev/badge/plugins/remakebench/skills/skills/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/plugins/remakebench/skills/skills"><img src="https://agentmods.dev/badge/plugins/remakebench/skills/skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
remakebench-skills 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.
What it actually says
{
"name": "remakebench-skills",
"version": "0.3.0",
"description": "Evidence-driven Claude Code skills for playable 3D production, image-to-3D reconstruction, quality gates, gameplay verification, and cross-model subagents.",
"author": {
"name": "RemakeBench",
"url": "https://github.com/RemakeBench"
},
"homepage": "https://github.com/RemakeBench/skills",
"repository": "https://github.com/RemakeBench/skills",
"license": "MIT",
"keywords": [
"claude-code",
"agent-skills",
"game-development",
"3d",
"blender",
"image-to-3d",
"tripo",
"meshy",
"quality-assurance",
"codex",
"grok",
"multi-model"
],
"skills": [
"./skills/reference-pack-authority",
"./skills/game-production-stages",
"./skills/image-to-3d-modular-kit",
"./skills/3d-asset-quality",
"./skills/asset-judge-loop",
"./skills/verify-by-playing",
"./skills/codex-subagent",
"./skills/grok-subagent"
]
}
What it installs
The manifest is a name and a version. 8 skills travel with it, and installing the plugin installs all of them — 978 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill 3d-asset-quality A 107 tokens
- Skill asset-judge-loop A 178 tokens
- Skill grok-subagent A 87 tokens
- Skill codex-subagent A 119 tokens
- Skill image-to-3d-modular-kit A 89 tokens
- Skill game-production-stages A 85 tokens
- Skill reference-pack-authority A 160 tokens
- Skill verify-by-playing A 153 tokens
What ships with it
1 file beside plugin.json 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 Changed · +4 lines 079e666e10d2
- 1mo ago First seen · 33 lines scan A 2aa8b2252552
remakebench-skills is a plugin published in the GitHub repository RemakeBench/skills (12 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
unreal
Unreal Engine 5.8 skills (Blueprints, C++ gameplay, input, AI, Niagara, packaging).
16.-expert-tools-zbrush
DCC software. A lead and eight specialists that drive Maxon ZBrush 2026 through its agent bridge: sculpting, characters and creatures, stylized work, hard surface, polypaint and renders, posing and 3D print, retopology and export, automation. The bridge was proven live; full live tests of every skill are still pending.
ai-game-behavior
NPC and enemy AI for games: behavior trees, state machines, utility AI, GOAP, navmesh pathfinding, and perception systems.
animation-systems
Game animation systems: blend trees, state machines, IK, root motion, and animation events across Godot AnimationTree, Unity Animator, and Unreal AnimGraph.
incident-response
Production incident management, triage workflows, and automated incident resolution.
error-diagnostics
Error tracing, root cause analysis, and smart debugging for production systems.