Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
nowledge-co avatar

Read Working Memory

  • 740 installs
  • 148 repo stars
  • Updated August 3, 2026
  • nowledge-co/community

read-working-memory is a session-start skill that loads a daily Working Memory briefing with active focus areas, priorities, unresolved flags, and recent knowledge changes for developers who need cross-tool project conti

About

read-working-memory is a nowledge-co/community skill that reads a daily Working Memory briefing at the beginning of AI coding sessions. The briefing contains active focus areas, priorities, unresolved flags, and recent knowledge changes so agents resume with current project context instead of cold starts. Claude Code and Grok Build hooks prefer a fuller Context Bundle when available—owner identity, AI Identity, active scope, active rules, and Working Memory—with Working Memory alone as a lighter fallback. Developers invoke read-working-memory when returning after a break or opening a new conversation on an ongoing codebase.

  • Loads daily Working Memory briefing automatically at session start
  • Surfaces active focus areas, priorities, and unresolved flags
  • Provides cross-tool continuity across Claude, Cursor and other agents
  • Supports named spaces with --space parameter for multi-project workflows
  • Falls back gracefully to legacy memory.md for older setups

Read Working Memory by the numbers

  • 740 all-time installs (skills.sh)
  • +17 installs in the week ending Aug 4, 2026 (Skillselion tracking)
  • Ranked #590 of 3,282 Productivity & Planning skills by installs in the Skillselion catalog
  • Security screen: LOW risk (skills.sh audit)
  • Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/nowledge-co/community --skill read-working-memory

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs740
repo stars148
Security audit3 / 3 scanners passed
Last updatedAugust 3, 2026
Repositorynowledge-co/community

How do you restore project context at session start?

Instantly restore project context at the start of every AI coding session.

Who is it for?

Developers using nowledge-co context tooling who start frequent AI sessions and need automatic priority and flag restoration.

Skip if: One-off throwaway scripts or repos without a maintained Working Memory or Context Bundle setup.

When should I use this skill?

A new agent session begins on an ongoing project and recent priorities, flags, or focus areas would improve continuity.

What you get

A loaded Working Memory briefing with active focus, priorities, unresolved flags, and recent knowledge deltas.

Files

SKILL.mdMarkdownGitHub ↗

Read Working Memory

Start every session with context. Claude Code and Grok Build hooks prefer Context Bundle when available: owner identity, AI Identity, active scope, active rules, and Working Memory. Working Memory alone is the lighter fallback.

When to Use

At session start:

  • Beginning of a new conversation
  • Returning to a project after a break
  • When context about recent work would help

During session:

  • User asks "what am I working on?" or "what's my context?"
  • User references recent priorities or decisions
  • Need to understand what's been happening across tools

Skip when:

  • Already loaded this session
  • User explicitly wants a fresh start
  • Working on an isolated, context-independent task

Usage

Prefer Context Bundle for startup context:

nmem --json context --source-app claude-code
# In Grok Build:
nmem --json context --source-app grok

Read Working Memory alone when you only need current priorities:

nmem wm read

If the runtime already knows the current project or agent lane, add --space "<space name>" to either command. Multi-agent orchestrators can set NMEM_AGENT_ID="<agent-slug>" before launching Claude Code or Grok Build so hooks read the right AI Identity automatically. Add NMEM_SPACE only when that whole run should override the identity's default space. Use NMEM_HOST_AGENT_ID only for advanced external aliases.

Fallback for local-only (when nmem is not installed):

cat ~/ai-now/memory.md

This fallback is only for older local-only Default-space setups.

What You'll Find

The Working Memory briefing contains:

  • Active Focus Areas — Topics you're currently engaged with, ranked by recent activity
  • Priorities — Items flagged as important or needing attention
  • Unresolved Flags — Contradictions, stale information, or items needing verification
  • Recent Activity — What changed in your knowledge base since the last briefing
  • Deep Links — References to specific memories for further exploration

How to Use This Context

1. Read once at session start — don't re-read unless asked 2. Reference naturally — mention relevant context when it connects to the current task 3. Avoid duplicate reads — if Context Bundle was already injected and includes Working Memory, do not read Working Memory again 4. Don't overwhelm — share only the parts relevant to what the user is working on 5. Cross-tool continuity — insights saved in other tools (Cursor, Claude Code, Grok Build, Codex) appear here

Troubleshooting

If nmem is not in PATH: pip install nmem-cli, pipx install nmem-cli, or on Arch Linux yay -S nmem-cli / paru -S nmem-cli

If Nowledge Mem is on a remote server, run nmem config client set url https://... and nmem config client set api-key ... once on this machine, or use NMEM_API_URL / NMEM_API_KEY for a temporary override.

Related skills

FAQ

When should read-working-memory run?

read-working-memory runs at session start—new conversations, returns after a break, or any time recent work context would help the agent continue accurately.

How does read-working-memory relate to Context Bundle?

read-working-memory loads the lighter Working Memory briefing; Claude Code and Grok Build hooks prefer the fuller Context Bundle with owner identity, AI Identity, active scope, and rules when available.

Is Read Working Memory safe to install?

skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.

Productivity & Planningagentsautomation

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.