tsumugi

A plugin that connects Claude Code to tsumugi, a memory system for coding sessions. It injects relevant past memory and guidance about saving observations.

In plain words
What is it for?
Use it to surface past memory when a session starts, when you submit a prompt, or before the agent reads something.
Why use it?
It helps the coding agent recall earlier context without automatically treating every tool result as a new memory.

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 archfill/tsumugi
agentmods
npx agentmods add plugins/archfill/tsumugi/claude-code
Clone the repo
git clone --depth 1 https://github.com/archfill/tsumugi

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

tsumugi 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.

integrations/claude-code/.claude-plugin/plugin.json · 19 lines

What it actually says

{
  "name": "tsumugi",
  "version": "0.1.0",
  "description": "tsumugi memory integration — 3 inject-only hooks (SessionStart, UserPromptSubmit, PreToolUse(Read)) that surface past memory and guide agent-driven save_observation calls. Does NOT create observations from raw tool output (avoiding the contamination problem documented in ADR-011).",
  "author": {
    "name": "archfill"
  },
  "repository": "https://github.com/archfill/tsumugi",
  "license": "Apache-2.0",
  "keywords": [
    "claude-code",
    "memory",
    "mcp",
    "tsumugi",
    "hooks",
    "inject-only"
  ]
}
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. yesterday First seen · 19 lines scan A 229225a6b10e

Subscribe to this mod's changes

tsumugi is a plugin published in the GitHub repository archfill/tsumugi (0 stars, last pushed 23d 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 2026-08-31.