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.
/plugin marketplace add susomejias/rembricnpx agentmods add plugins/susomejias/rembric/plugingit clone --depth 1 https://github.com/susomejias/rembricGrade A, and why
rembric 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.
What it actually says
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "rembric",
"version": "0.30.0",
"description": "Memory for Claude Code, backed by your self-hosted Rembric server.",
"author": {
"name": "rembric contributors",
"url": "https://github.com/susomejias/rembric"
},
"repository": "https://github.com/susomejias/rembric",
"license": "MIT",
"keywords": [
"memory",
"mcp",
"rembric",
"agent-memory"
],
"userConfig": {
"server_url": {
"type": "string",
"title": "Rembric server URL",
"description": "Base URL of your Rembric deployment WITHOUT the /mcp suffix. Good: https://memory.example.com or http://192.168.1.10:8787. Bad: https://memory.example.com/mcp (the plugin appends /mcp itself). No trailing slash.",
"required": true
},
"api_token": {
"type": "string",
"title": "Rembric API token",
"description": "Bearer token issued from the Rembric dashboard at /dashboard/tokens (plaintext shown exactly once). Stored in the system keychain.",
"sensitive": true,
"required": true
}
},
"mcpServers": "./.claude-plugin/mcp.json"
}
What ships with it
3 files 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.
- 2d ago First seen · 35 lines scan A bcf43eeed437
rembric is a plugin published in the GitHub repository susomejias/rembric (12 stars, last pushed 7d 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
agentmemory
Upstream-compatible AgentMemory plugin bundled with the independent Windows/Codex downstream. 12 hooks, 56 MCP tools, 8 skills, real-time viewer.
unknowns
Plugin marketplace listing 1 plugin: unknowns.
unknowns
Skills for discovering and closing knowledge gaps across the dev lifecycle, from Thariq's 'Know Your Unknowns'.
tree-ring-memory
Local-first memory lifecycle, project bootstrap, and receipt-backed harness guidance for Claude Code using Tree Ring Memory v0.15+.
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.
wikimoth
Deterministic, token-minimal memory for Claude Code: capture each session as a [[wikilink]] note (edges computed by code, not a model) and recall connected notes at boot.