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 LogicLabsAI/ultramemory-mcpnpx agentmods add plugins/logiclabsai/ultramemory-mcp/agent-kitgit clone --depth 1 https://github.com/LogicLabsAI/ultramemory-mcpWrote 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/logiclabsai/ultramemory-mcp/agent-kit)<a href="https://agentmods.dev/plugins/logiclabsai/ultramemory-mcp/agent-kit"><img src="https://agentmods.dev/badge/plugins/logiclabsai/ultramemory-mcp/agent-kit.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
ultramemory-kit 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 5d 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": "ultramemory-kit",
"version": "1.9.13",
"description": "UltraMemory Agent Kit \u2014 recall-first memory (Turbo Token Saver), the grounding/checklist harness, and optional MCP + Playwright setup for Claude Code. Bring your own UltraMemory API key.",
"author": {
"name": "LogicLabsAI",
"email": "[email protected]"
},
"homepage": "https://ultramemory.io",
"license": "Apache-2.0",
"keywords": [
"memory",
"recall",
"harness",
"grounding",
"mcp",
"ultramemory",
"token-economics"
]
}
What it installs
The manifest is a name and a version. 7 skills, 2 agents, 2 hooks travel with it, and installing the plugin installs all of them — 672 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill playwright-human-mode A 157 tokens
- Skill atomic-level-checklist-md-confirm-approval-needed A 17 tokens
- Skill swarm A 90 tokens
- Skill setup A 32 tokens
- Skill checklist-bound-execution A 154 tokens
- Skill harness A 68 tokens
- Skill research A 10 tokens
- Agent checklist-verifier A 78 tokens
- Agent checklist-worker A 66 tokens
- Hook UserPromptSubmit A not measured
- Hook Stop 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.
- 5d ago First seen · 21 lines scan A 359268bb4248
ultramemory-kit is a plugin published in the GitHub repository LogicLabsAI/ultramemory-mcp (1 stars, last pushed 1mo 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.
Other plugins, from other repositories
ownmem
Git-native project memory for AI coding agents, with deterministic local recall, evidence gates, and bounded evolution.
krimto
Open-source memory for AI coding agents you own in git — governed by a real user→team→org hierarchy, not a vendor database. Solo to team. Apache-2.0.
thoughtline marketplace
Local-first persistent memory for AI coding agents. Survives across sessions and compactions. Built for game-development workflows.
thoughtline
Local-first persistent memory for AI coding agents. Survives across sessions and compactions. Built for game-development workflows.
deja-vu
deja-vu memory for Claude Code: your own past sessions, from every coding agent on the machine, recalled before you ask.
claude-code-plugin
Prismer Evolution — cross-agent learning network. Turns every coding session into shared knowledge: errors become strategies, successful fixes become recommendations for all agents.