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/aristoapp/claude-membaseWrote 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/aristoapp/claude-membase/plugin)<a href="https://agentmods.dev/plugins/aristoapp/claude-membase/plugin"><img src="https://agentmods.dev/badge/plugins/aristoapp/claude-membase/plugin/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/aristoapp/claude-membase/plugin"><img src="https://agentmods.dev/badge/plugins/aristoapp/claude-membase/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
membase 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": "membase",
"version": "0.2.0",
"description": "Persistent memory and wiki workflows for Claude Code.",
"author": {
"name": "Aristo Intelligence",
"email": "[email protected]"
},
"homepage": "https://membase.so",
"repository": "https://github.com/aristoapp/claude-membase",
"license": "MIT",
"keywords": ["membase", "memory", "mcp", "claude-code"],
"skills": "./skills/",
"commands": "./commands/",
"agents": ["./agents/membase-curator.md"],
"mcpServers": "./.mcp.json",
"userConfig": {
"apiUrl": {
"type": "string",
"title": "Membase API URL",
"description": "Membase API endpoint.",
"default": "https://api.membase.so"
},
"autoRecall": {
"type": "boolean",
"title": "Auto Recall",
"description": "Search Membase before user prompts and inject relevant context.",
"default": true
},
"autoWikiRecall": {
"type": "boolean",
"title": "Auto Wiki Recall",
"description": "Include wiki documents in automatic recall.",
"default": false
},
"maxRecallChars": {
"type": "number",
"title": "Max Recall Characters",
"description": "Maximum characters injected by auto-recall.",
"default": 4000,
"min": 500,
"max": 16000
},
"sessionStartContext": {
"type": "string",
"title": "Session Start Context",
"description": "Context injected at Claude Code session start: off, minimal, or profile.",
"default": "minimal"
},
"projectMode": {
"type": "string",
"title": "Project Mode",
"description": "Project scoping mode: auto_git, manual, or off.",
"default": "auto_git"
},
"debug": {
"type": "boolean",
"title": "Debug Logging",
"description": "Write local debug logs under the plugin data directory.",
"default": false
}
}
}
What it installs
The manifest is a name and a version. 5 skills, 8 commands, 1 agent, 4 hooks, 1 MCP server travel with it, and installing the plugin installs all of them — 208 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill membase-wiki A 23 tokens
- Skill membase-recall A 22 tokens
- Skill membase-remember A 17 tokens
- Skill membase-memory-hygiene A 21 tokens
- Skill membase-project-context A 15 tokens
- Command login A 15 tokens
- Command wiki A 13 tokens
- Command index-project A 9 tokens
- Command logout A 7 tokens
- Command recall A 8 tokens
- Command project-config A 13 tokens
- Command remember A 8 tokens
- Command status A 16 tokens
- Agent membase-curator A 21 tokens
- Hook SessionEnd A not measured
- Hook Stop A not measured
- Hook UserPromptSubmit A not measured
- Hook SessionStart A not measured
- MCP server membase A not measured
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 First seen · 64 lines scan A 6134e11a232e
membase is a plugin published in the GitHub repository aristoapp/claude-membase (3 stars, last pushed 3mo 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
cross-code-organizer
Inspect and organize Claude Code memories, skills, MCP servers, hooks, and project context from a local dashboard.
recall
Durable, fully-local project memory for Claude Code. Logs every session to .recall/history.md and condenses it into .recall/context.md with a local Python summarizer (TF-IDF + TextRank) — no API key, no external model, nothing leaves your machine. New sessions resume from the saved context.
claude-mega-brain
OKF-powered knowledge context for Claude Code — injects your project knowledge base at every session.
toonify-mcp
Local context compression for Claude Code workflows, including structured data and debug-heavy output.
captain-memo
Cross-AI local memory layer for Claude Code, Codex, Gemini CLI, Antigravity, goose, Cursor, opencode, Kimi CLI and more: hybrid search, six summarizer providers, hosted or local embedder. Replaces claude-mem.
continuity
Durable project state across AI sessions: decisions, constraints, and rejected paths, versioned in git as plain markdown. Not a memory tool — it answers what is true about the project now, and what must not change.