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/atman-33/workhubWrote 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/atman-33/workhub/memory)<a href="https://agentmods.dev/plugins/atman-33/workhub/memory"><img src="https://agentmods.dev/badge/plugins/atman-33/workhub/memory/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/atman-33/workhub/memory"><img src="https://agentmods.dev/badge/plugins/atman-33/workhub/memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
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 17d 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": "memory",
"version": "0.10.0",
"description": "Long-term memory for agent sessions on a workhub vault. Every session's Q&A pairs are stored in a vault-local SQLite database and new sessions receive a time summary plus the past conversations relevant to the current prompt, found by hybrid keyword + vector search. Fully local: a Japanese-capable embedding model runs on the CPU, nothing is sent anywhere, and no LLM is called. Split out of the workhub plugin so memory can be switched off on its own.",
"author": {
"name": "atman-33",
"url": "https://github.com/atman-33"
}
}
What it installs
The manifest is a name and a version. 5 skills travel with it, and installing the plugin installs all of them — 343 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 17d ago Changed 28f15eec4c2b
- 27d ago Changed 1d2d3ce8ffa5
- 28d ago First seen · 10 lines scan A 270d80749211
memory is a plugin published in the GitHub repository atman-33/workhub (3 stars, last pushed 2d 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 2026-09-19.
Other plugins, from other repositories
memex
Collaborative memory for human-AI work — persistent, searchable, interconnected.
superbrain
Automatic Claude Code -> Obsidian second brain: zero-config session capture, hybrid search, autonomous recall, daily/lessons/preferences.
obsidian-wiki
Maintain an Obsidian LLM-Wiki (structure layer + content curation + orchestrator).
kb
Build and maintain LLM-powered knowledge bases as Obsidian wikis with compile, query, lint, and evolve workflows.
obsidian-vfs
Resolve @obs: mentions, and /obs: Skills from your Obsidian vault into Claude.
obsidian-rag
Obsidian vault integration with local RAG capabilities for Claude Code.