A file-based record database for coding agents and people. It stores project decisions with their status, links them to files, detects when those files change, and supports full-text search.

Use it to record and search architecture choices, trade-offs, conventions, and other project decisions. It can serve as a shared source of context for future work.

It keeps important decisions and project context from being lost in conversations or scattered documents. File-change checks help reveal when a decision may need review.

kauri — Plugin by mhashim6

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 mhashim6/kauri

agentmods

npx agentmods add plugins/mhashim6/kauri/claude-code

Clone the repo

git clone --depth 1 https://github.com/mhashim6/kauri

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

kauri 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 yesterday.

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-code/.claude-plugin/plugin.json · 14 lines

What it actually says

{
  "name": "kauri",
  "version": "0.1.2",
  "description": "Kauri — a deterministic record database for LLM agents and humans. Tracks project decisions with structured lifecycle semantics, file-based staleness detection, and full-text search.",
  "author": {
    "name": "Kauri contributors"
  },
  "repository": "https://github.com/mhashim6/kauri",
  "license": "MIT",
  "keywords": ["decisions", "adr", "records", "context", "memory"],
  "skills": "./skills/",
  "mcpServers": "./.mcp.json"
}

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.

yesterday First seen · 14 lines scan A 801fd1323e2b

Subscribe to this mod's changes

kauri is a plugin published in the GitHub repository mhashim6/kauri (5 stars, last pushed 4mo 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.

Data and AI Databases Memory and context adr agent agent-memory ai-agents calude decision

kauri

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

beevibe

memX

tsubasa

tsubasa

agmem

claude-plugins-official