memory-setup SKILL.md skillA

memory-setup from atman-33/workhub is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add atman-33/workhub/memory-setup@git:20260919.2bfb375

Pins git:20260919.2bfb375 in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: atman-33/workhub
Path: plugins/memory/skills/memory-setup/SKILL.md
Versions recorded: 2
Latest version: git:20260919.2bfb375, committed Sep 19, 2026
First version recorded: Sep 17, 2026
Size: 3,313 bytes
Repository stars: 3
License: MIT

Set up the workhub long-term memory engine on this machine - install its dependencies, download the local embedding model, initialize the vault memory database, and verify the result. Use when the workhub app prompts for memory setup, when memory hooks report they are skipped, or when the user asks to enable/repair long-term memory.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# memory-setup — Enable long-term memory on this machine

The workhub plugin ships memory hooks that save each session's Q&A pairs
into a vault-local SQLite database and inject relevant past conversations
into new sessions (hybrid FTS5 + vector search, fully local, no LLM).
The hooks stay silently disabled until this one-time machine setup has run.

## Steps

1. **Run the idempotent setup script** (safe to re-run; fast no-op when
   already set up):

   ```bash
   node "${CLAUDE_PLUGIN_ROOT}/engine/cli.mjs" setup
   ```

   This installs npm dependencies (node-sqlite3-wasm,
   @huggingface/transformers) into `~/.workhub/memory-engine/`, downloads
   the embedding model (~320 MB, one time) into
   `~/.workhub/memory-engine/models/`, copies the engine to
   `~/.workhub/memory-engine/engine/` (the stable path the vault's OpenCode
   memory plugin calls), creates `<vault>/_ai/state/memory.db`, makes sure
   the vault `.gitignore` excludes the database, and writes the
   `.setup-version` marker the hooks and the workhub app check.

   The first run takes several minutes, almost all of it the model download.
   Warn the user before starting if they seem to be in a hurry. No dependency
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add atman-33/workhub/memory-setup@sha256:f22b1b2c82bb4f6e

The line at the top of this page pins the label git:20260919.2bfb375, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_enm6vquaxweqiq5n.svg)](https://markdownregistry.com/a/art_enm6vquaxweqiq5n)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Sep 17, 2026 and Sep 19, 2026, about one every 2 days.

version	committed	commit	size	audit
git:20260919.2bfb375 latest	2026-09-19	2bfb375	3,313 B	A	view · diff
git:20260917.0f594d4	2026-09-17	0f594d4	3,314 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (3313 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

atman-33/workhub · 3 stars · license MIT · pushed 2026-10-15 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_enm6vquaxweqiq5n
GET https://markdownregistry.com/api/v1/resolve?ref=atman-33/workhub/memory-setup
GET https://markdownregistry.com/api/v1/blob/f22b1b2c82bb4f6e9ea24a563f2f1184ff6b119d14acbf66e84881a37b094d59

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from atman-33/workhub

CLAUDE.md CLAUDE.md file

atman-33/workhub · CLAUDE.md

git:20260929.5a11e52 · audit A · 3 stars

AGENTS.md@demo-vault AGENTS.md file

atman-33/workhub · demo-vault/AGENTS.md

git:20260830.27fbb5d · audit A · 3 stars

CLAUDE.md@demo-vault CLAUDE.md file

atman-33/workhub · demo-vault/CLAUDE.md

git:20260930.4c9347d · audit A · 3 stars

handoff-go SKILL.md skill

atman-33/workhub · plugins/agent-ops/skills/handoff-go/SKILL.md · Write a handoff document and launch the next agent in a split multiplexer pane (herdr or zellij), with new-window and…