Claude Code mod
working-memory
把 context window 畫成一顆腦：工具呼叫點亮對應腦區，用量越滿越擁擠，compact 時睡眠整理
Install
/plugin marketplace add Hangghost/learning-hacker-claude-mod
/plugin install working-memory@learning-hacker-claude-modMods install like plugins. Run /reload-plugins or start a new session to load it.
What it can access
- Reach
- L1Reads: reads mod state, draws
- Sees
- every prompt, every tool call, compaction
- Draws in
Pane- Hooks
session.startcommand.runprompt.submittool.callsession.measuresession.compactui.render
From a static scan of the mod's code by awesome-claude-code-mods. It shows what the code asks for, not a security review.
How Claude Code mods work
- A mod is a plugin with a JavaScript or TypeScript module that runs inside Claude Code (version 2.1.287 or later). It can draw panes beside the transcript, a band above the prompt, buttons and toasts, restyle the spinner and tool rows, and watch or rewrite tool calls and prompts.
- It installs like any plugin: add its marketplace with /plugin marketplace add owner/repo, then /plugin install name@marketplace.
- Check what a mod can reach before installing: it runs with your permissions. Reach goes from drawing only, to reading files, to writing files or running processes, to the network. Run claude plugin validate on a clone to list its hooks and calls without running it.
- Turn one off from the Installed tab in /plugin, or start Claude Code with --safe-mode to skip every customization for a session.
Details
- Repository
- Hangghost/learning-hacker-claude-mod
- Folder
plugins/working-memory- Marketplace
learning-hacker-claude-mod- Author
- Hangghost
- License
- MIT
- Last updated
- 17 October 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is working-memory?
把 context window 畫成一顆腦：工具呼叫點亮對應腦區，用量越滿越擁擠，compact 時睡眠整理 It is a mod for Claude Code, from Hangghost/learning-hacker-claude-mod on GitHub.
What can the working-memory mod access?
Its widest reach is "reads" (reads mod state, draws). It sees every prompt, every tool call, compaction. It draws in Pane. Like any mod, it runs with your permissions.
How do I install working-memory?
Inside Claude Code (v2.1.287 or later), run /plugin marketplace add Hangghost/learning-hacker-claude-mod and then /plugin install working-memory@learning-hacker-claude-mod.
Is working-memory popular?
Hangghost/learning-hacker-claude-mod has 14 GitHub stars and 0 forks, and is included in 1 curated Claude Code list. It was last updated on 17 October 2026.
More memory & instructions mods
handoff
14IT-Shelter-Labs/Claude-Mods
A Claude Code mod from IT-Shelter-Labs/Claude-Mods.
view-memory
1Monte9/claude-memory-mods
/view-memory: a pane browsing every auto-memory folder, with search, overdue items, health checks and what each session loads, and a nudge to save once a session runs long
wrap-buttons
lisim/wrap-buttons
After a wrap-up reply, shows buttons to /clear and carry the handoff's next step into a fresh session.
assumption-check
3vumichien/claude-code-mods-kit
After a turn that edited files or ran commands, Haiku lists the choices Claude made that you did not state. Mark each right or wrong, add a note, and send the corrections back as one prompt. Starts off: /assumption-check on turns it on
vitals-strip
davidcoulson/crab-workshop
Unraid and Home Assistant health above the prompt: array and ZFS pools, CPU and memory, the Docker service, the Unraid integration's problem sensors (shelves, HBAs, optics), unread Unraid alerts, parity runs, and HA state, repairs and notifications. Unraid is read through the Unraid Management Agent integration in HA, in one read-only template call. Quiet by default: it shows only what isn't green. /vitals for the full strip.
command-pack
3baselane-sh/mods
The five original slash commands in one mod: /receipt, /standup, /changelog, /pr-description and /handoff. They read git; /handoff also writes .claude/handoff.md. They copy results to the clipboard.
Browse the most popular Claude Code mods, all memory & instructions mods, or the skills and MCP server directories.