noosphere

A Claude Code plugin that provides shared, versioned skills and debugging memory, using a GitHub repository as its shared memory backend.

In plain words
What is it for?
Use it to discover shared skills, read fresh public GitHub issues when configured, and maintain shared agent memory through the plugin’s commands, skills, hooks, and MCP server.
Why use it?
It helps agents reuse procedures and preserve debugging knowledge across sessions or agents.

Plugin for Claude Code

Install

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.

Claude Code
/plugin marketplace add JinNing6/Noosphere
agentmods
npx agentmods add plugins/jinning6/noosphere/claude-noosphere
Clone the repo
git clone --depth 1 https://github.com/JinNing6/Noosphere

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

noosphere 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.

plugins/claude-noosphere/.claude-plugin/plugin.json · 43 lines

What it actually says

{
  "name": "noosphere",
  "version": "0.10.0",
  "description": "Live, versioned shared Skills and debug memory for Claude Code agents.",
  "author": {
    "name": "JinNing6",
    "email": "[email protected]",
    "url": "https://github.com/JinNing6"
  },
  "homepage": "https://github.com/JinNing6/Noosphere#install-in-claude-code",
  "repository": "https://github.com/JinNing6/Noosphere",
  "license": "Apache-2.0",
  "keywords": [
    "claude-code",
    "mcp",
    "debugging",
    "agent-memory",
    "shared-skills",
    "noosphere",
    "github"
  ],
  "commands": "./commands/",
  "skills": "./skills/",
  "hooks": "./hooks/hooks.json",
  "mcpServers": "./.mcp.json",
  "userConfig": {
    "github_token": {
      "type": "string",
      "title": "GitHub token",
      "description": "Optional GitHub token for fresh Issue-layer reads and explicit public writes. Anonymous registry discovery works without it.",
      "sensitive": true,
      "required": false
    },
    "noosphere_repo": {
      "type": "string",
      "title": "Noosphere repository",
      "description": "GitHub repository used as the shared memory backend, in owner/repo format.",
      "default": "JinNing6/Noosphere",
      "required": true
    }
  }
}
Changes

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.

  1. 2d ago First seen · 43 lines scan A 8ccf6ed5ebaa

Subscribe to this mod's changes

noosphere is a plugin published in the GitHub repository JinNing6/Noosphere (18 stars, last pushed 9d ago), licensed Apache-2.0. 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.

Related

Other plugins, from other repositories

ainb-hooks

Emit every safely observable Claude Code lifecycle event into Hangar's durable provider log. User-facing events still reach ainb-notifyd over its Unix socket. The same notify.sh powers ATC structured control when installed with AINBMANAGED=atc. stallguard.py additionally blocks turn-end when a session would idle on i.

stevengonsalvez/agents-in-a-box · not measured

illustration

Explanatory & brand illustration skill starring Popa — a pink blob with a green sprout and a notepad — drawn as intricate hand-drawn sketchnotes. Workflow: digest → shot list → per-image generation → QA → deliver, with likeness-locked references. Invoke illustration or illustration:popa.

stevengonsalvez/agents-in-a-box · not measured

tree-ring-memory

Local-first memory lifecycle, project bootstrap, and receipt-backed harness guidance for Claude Code using Tree Ring Memory v0.15+.

TerminallyLazy/Tree-Ring-Memory · not measured

hipocampus

Persistent agent memory that survives across sessions — auto-compacting 3-tier memory with hybrid search. Your agent remembers what it learned, decided, and built.

kevin-hs-sohn/hipocampus · not measured

hotl-plugin marketplace

Human-on-the-Loop (HOTL) operating model for AI-native development.

yimwoo/hotl-plugin · not measured

l123-harness

三级记忆底座:状态放模型外、客观观察、内层不发散、升级需审批。提供 L1 常驻层 / L2 索引 / L3 详情的目录骨架与模板、门禁+审批令牌、零判断事件日志、上下文压缩抢救、以及周审提炼技能。在新项目运行 /l123-harness:init-harness 生成骨架。.

reatcat/l123-harness · not measured