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/TheArcForge/HadesWrote 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/thearcforge/hades/claudecodeplugin)<a href="https://agentmods.dev/plugins/thearcforge/hades/claudecodeplugin"><img src="https://agentmods.dev/badge/plugins/thearcforge/hades/claudecodeplugin/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/thearcforge/hades/claudecodeplugin"><img src="https://agentmods.dev/badge/plugins/thearcforge/hades/claudecodeplugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
hades 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
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "hades",
"displayName": "Hades",
"version": "2.1.0",
"description": "Unity-aware AI infrastructure for Claude Code: a queryable knowledge graph of your Unity project, plus observability, project memory, and 22 skills. Connects to the standalone Hades app for macOS and Windows (Windows is beta), which serves 32 MCP tools.",
"author": {
"name": "ArcForge",
"url": "https://github.com/TheArcForge"
},
"license": "MIT",
"homepage": "https://github.com/TheArcForge/Hades",
"repository": "https://github.com/TheArcForge/Hades",
"keywords": ["unity", "game-development", "mcp", "knowledge-graph"]
}
What it installs
The manifest is a name and a version. 22 skills, 6 commands travel with it, and installing the plugin installs all of them — 800 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill unity-addressables A 29 tokens
- Skill unity-ai-behavior A 32 tokens
- Skill unity-performance A 32 tokens
- Skill unity-testing A 35 tokens
- Skill animation-workflow A 25 tokens
- Skill scene-architecture A 31 tokens
- Skill unity-architect A 42 tokens
- Skill unity-audio A 30 tokens
- Skill unity-ecs A 34 tokens
- Skill unity-input A 31 tokens
- Skill unity-networking A 35 tokens
- Skill unity-shaders-hdrp A 30 tokens
- Skill unity-ui A 29 tokens
- Skill unity-vfx A 32 tokens
- Skill component-design A 25 tokens
- Skill data-modeling A 28 tokens
- Skill prefab-architecture A 35 tokens
- Skill prefab-workflow A 33 tokens
- Skill unity-shaders-urp A 31 tokens
- Skill scene-authoring A 32 tokens
- Skill unity-reviewer A 39 tokens
- Skill unity-workflow A 36 tokens
- Command hades-export-traces A 15 tokens
- Command hades-show-proposals A 14 tokens
- Command hades-show-traces A 18 tokens
- Command hades-status A 17 tokens
- Command hades-validate-memory A 16 tokens
- Command hades-rebuild-graph A 14 tokens
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 0f43fe36611b
- 1mo ago First seen · 16 lines scan A 21956ebfaedb
hades is a plugin published in the GitHub repository TheArcForge/Hades (29 stars, last pushed 27d 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 2026-08-30.
Other plugins, from other repositories
claude-brain
Claude Mind - Give Claude photographic memory in ONE portable file. Share, version, and transfer your Claude's brain.
credo
The mentor framework for Claude Code: a self-contained process layer with per-session modes, a work-item lifecycle with a hard Definition of Done, budget-aware autonomy, visual verification, and safety rules that travel into every subagent.
dogma
Intelligent sync of Claude instructions with enforcement hooks for security and consistency.
get-shit-done
Installer for the Get-Shit-Done workflow system (own secured & frozen fork, markdown skills only) - meta-prompting, context engineering and spec-driven development.
hydra
Git Worktree management for parallel agent execution - isolated working directories without Git conflicts.
import
Import external documentation locally - bypass AI-blocking sites via Context7, WebFetch, or Playwright.