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/KumihoIO/kumiho-pluginsWrote 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/kumihoio/kumiho-plugins/claude)<a href="https://agentmods.dev/plugins/kumihoio/kumiho-plugins/claude"><img src="https://agentmods.dev/badge/plugins/kumihoio/kumiho-plugins/claude/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/kumihoio/kumiho-plugins/claude"><img src="https://agentmods.dev/badge/plugins/kumihoio/kumiho-plugins/claude.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
kumiho-memory 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 13d 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": "kumiho-memory",
"version": "0.24.0",
"description": "Persistent graph-native memory for Claude — recalls context across sessions, stores decisions and preferences, bootstraps identity at session start, and mines commits + conversations into a git-anchored decision graph (Decision Memory).",
"author": {
"name": "Kumiho Inc.",
"url": "https://kumiho.io"
},
"repository": "https://github.com/KumihoIO/kumiho-plugins",
"homepage": "https://docs.kumiho.io/python/mcp.html",
"license": "MIT",
"keywords": [
"kumiho",
"memory",
"mcp",
"graph",
"cognitive-memory",
"plugin",
"claude"
],
"skills": "./skills",
"commands": "./commands",
"mcpServers": "./.mcp.json"
}
What it installs
The manifest is a name and a version. 1 skill, 5 commands, 7 hooks, 1 MCP server travel with it, and installing the plugin installs all of them — 143 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill kumiho-memory A 56 tokens
- Command kumiho-onboard A 21 tokens
- Command kumiho-backfill A 21 tokens
- Command kumiho-personalize A 19 tokens
- Command dream-state A 15 tokens
- Command memory-capture A 11 tokens
- Hook PostToolUse A not measured
- Hook SessionEnd A not measured
- Hook PermissionRequest A not measured
- Hook SessionStart A not measured
- Hook UserPromptSubmit A not measured
- Hook Stop A not measured
- Hook SubagentStart A not measured
- MCP server kumiho-memory A not measured
What ships with it
1 file 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.
- 13d ago Changed d5b4dadc4f75
- 15d ago Changed 36c98d56a2ec
- 1mo ago Changed 39e6d9f501f4
- 1mo ago Changed 74db6f167395
- 1mo ago Changed 3e01e3ece463
- 1mo ago Changed 8261d5645e2f
- 1mo ago First seen · 25 lines scan A aebbabd61ade
kumiho-memory is a plugin published in the GitHub repository KumihoIO/kumiho-plugins (3 stars, last pushed 14d 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
open-knowledge-vault
Create and maintain portable Open Knowledge Format vaults with optional Obsidian and Dataview views.
knowledge-and-memory
Research methodology, corpus search, persistent memory, iterative workflows, and project knowledge management.
pai
Personal AI Infrastructure — persistent memory, session continuity, and knowledge graph for Claude Code.
claude-mega-brain
OKF-powered knowledge context for Claude Code — injects your project knowledge base at every session.
tree-ring-memory
Local-first memory lifecycle, project bootstrap, and receipt-backed harness guidance for Claude Code using Tree Ring Memory v0.15+.
vault-template
Personal Knowledge Management system for Obsidian with AI-powered workflows, goal tracking, and productivity coaching.