Read Working Memory
Load your daily Working Memory briefing at session start so the agent knows focus areas, priorities, and unresolved flags across tools.
Overview
Read Working Memory is a journey-wide agent skill that loads your daily nmem Working Memory briefing—usable whenever a solo builder needs cross-tool continuity before committing to the next task.
Install
npx skills add https://github.com/nowledge-co/community --skill read-working-memoryWhat is this skill?
- Automatic session-start context via nmem --json wm read
- Surfaces Active Focus Areas, Priorities, and Unresolved Flags from the knowledge base
- Optional --space filter for project or agent lane scoping
- Fallback path documented for legacy ~/ai-now/memory.md Default-space setups
- Explicit skip rules when context already loaded or user wants a fresh start
Adoption & trust: 659 installs on skills.sh; 91 GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You open a new agent chat and lose thread on priorities, flags, and recent knowledge changes that lived in another tool or yesterday’s session.
Who is it for?
Builders running nmem with a synthesized knowledge base who switch between agents and want a standard session opener.
Skip if: Greenfield one-off prompts with no memory system, or users who explicitly want zero prior context every time.
When should I use this skill?
Beginning of a new conversation, returning after a break, or when the user asks what they are working on—unless memory was already loaded or a fresh start is requested.
What do I get? / Deliverables
The agent reads structured focus, priorities, and unresolved flags first, then continues work with shared context or clearly states that no briefing exists yet.
- Parsed Working Memory briefing in session context
- Clear message when exists:false
- Space-scoped context when --space is set
Recommended Skills
Journey fit
Useful at every journey phase - explore requirements and options before committing to a direction.
Where it fits
Resume feature work by loading Active Focus Areas before the agent drafts the next implementation slice.
Reconcile Unresolved Flags about API behavior before approving a PR description.
Pick up post-incident follow-ups listed under Priorities without re-reading slack exports.
See which customer themes were recently flagged before drafting lifecycle emails.
Check whether scope debates from last week are still open before committing to a prototype.
How it compares
Use instead of pasting a long manual status update—this skill is the procedural hook to your existing memory layer, not a replacement knowledge base.
Common Questions / FAQ
Who is read-working-memory for?
Solo builders on the Nowledge community stack who use nmem and want agents to auto-load daily briefings for cross-tool continuity.
When should I use read-working-memory?
At session start in Build, Ship, Operate, or Grow when recent priorities matter; when the user asks for current context; and after breaks before resuming multi-day product work.
Is read-working-memory safe to install?
It reads local or space-scoped memory via nmem—review the Security Audits panel on this page and confirm what data your Working Memory briefing exposes before automating it in shared environments.
SKILL.md
READMESKILL.md - Read Working Memory
# Read Working Memory > Start every session with context. Your Working Memory is a daily briefing synthesized from your knowledge base. ## 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 Read Working Memory with `nmem` first: ```bash nmem --json wm read ``` If it succeeds but reports `exists: false`, say there is no Working Memory briefing yet. If the host already knows a project or agent lane, add `--space "<space name>"`. Only fall back to `~/ai-now/memory.md` 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. **Continuation handoff** — if the task looks like a review, regression, release, resume, or prior-decision question, move straight into `search-memory` after the briefing instead of stopping here 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, Codex) appear here ## Examples ```bash # Read today's briefing nmem --json wm read # Legacy local-only fallback test -f ~/ai-now/memory.md && cat ~/ai-now/memory.md || echo "No Working Memory found. Ensure Nowledge Mem is running with Background Intelligence enabled." ``` ## About Working Memory Working Memory is generated daily by Nowledge Mem's Background Intelligence. It synthesizes your recent knowledge activity into a concise briefing that any connected AI tool can read. **Updated daily** at your configured briefing time (default: 8 AM local time). **Shared across tools** — connected tools read the same lane's briefing. Save an insight in one tool, and that lane's next briefing reflects it for the others. ## Links - [Documentation](https://mem.nowledge.co/docs) - [Nowledge Mem](https://mem.nowledge.co) - [Discord Community](https://nowled.ge/discord) ## Native Plugin These skills work in any agent via CLI. For auto-recall, auto-capture, and graph tools, check if your agent has a native Nowledge Mem plugin — run the `check-integration` skill or see https://mem.nowledge.co/docs/integrations