Skip to main content
skill CX Codex

read-working-memory — Claude Code skill for session context

This skill reads a Working Memory briefing with current priorities and recent knowledge changes. Use it when starting a session or returning to a project.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add nowledge-co/community --skill read-working-memory -a claude-code
Open on GitHub

What read-working-memory does

The skill reads a compact briefing of active topics, priorities, unresolved flags, and recent changes in the knowledge base. It can supply context at the start of a conversation or when resuming work. Connected tools share the same lane’s briefing.

Run nmem --json wm read to read the briefing alone. For a broader startup context, the skill also offers nmem --json context --source-app generic-agent. When a task continues a review, regression, or release, it directs the agent to search-memory after the briefing. Skip the separate read if a Context Bundle already contains Working Memory.

What it helps with

  • load project priorities into a new session
  • check what changed in the knowledge base
  • resume work after a break
  • carry context across connected tools

Example prompts for the agent

  • Read my Working Memory briefing before we start.
  • What priorities and unresolved items are in my current context?
  • I’m returning to this project after a break; load the latest briefing.

How to install read-working-memory

1Skills CLI (Vercel)

npx skills add nowledge-co/community --skill read-working-memory -a claude-code

2Manually: put the files in place

~/.claude/skills/read-working-memory/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/read-working-memory/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about read-working-memory

How do I install read-working-memory in Claude Code?

Run npx skills add nowledge-co/community --skill read-working-memory -a claude-code. The skill file is placed at ~/.claude/skills/read-working-memory/SKILL.md.

What does read-working-memory do?

It reads a briefing of active topics, priorities, unresolved items, and recent knowledge changes so an agent can use context from earlier work.

Which command reads only the Working Memory briefing?

Run nmem --json wm read. For a startup bundle that also includes identity and active rules, the skill provides nmem --json context --source-app generic-agent.

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set7

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor