More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Sleep — prune and consolidate your Claude Code memory

    1

    Your Claude Code memory folder only grows. Sleep backs it up, rule-scans for dead paths, stale and orphan notes, lets the AI find duplicates, and changes nothing until you approve.

    Free

    Security scanned
    Sleep — prune and consolidate your Claude Code memory

    Sleep — prune and consolidate your Claude Code memory

    Example session with this skill installed

    /sleep — my memory for this project feels bloated, tidy it up

    • Read your context and instructions
    • Compiled the sleep

    Summary

    Backed up 19 memories, scanned them, and proposed 6 changes. You approved all 6. Boot injection went from

    4,730 → 4,180 tokens (budget 5,000). Nothing was deleted.

    Backup: %LOCALAPPDATA%\Noema\sleep\backup\my-app\2026-11-13T09-12-04 (copy it back to undo).

    Scan (rules only, no AI tokens)

    GroupCountTokens
    ⚠ Hot and suspicious1610
    Dead paths2880
    Past review date1140
    Cold3520
    Orphan (cold + no links)1310
    No rule flags13—

    deploy-notes.md is read in almost every session (22 reads) but points to D:/work/my-app/scripts/deploy.ps1, which no longer exists. That is the most dangerous kind: wrong and trusted.

    Proposal (you approve, then it changes things)

    GroupFileTokActionReason
    ⚠ Hotdeploy-notes.md610fixScript moved to tools/deploy.ps1
    Dead pathapi-keys-setup.md270fixFolder renamed, new path found
    Duplicaterelease-flow.md420mergeSame topic as deploy-notes.md
    Compressproject-status.md980compressDated log → one line of current state
    Reviewpromo-2025.md140archiveCampaign ended
    Cold + orphanlegacy-cron.md310archiveUnread for 96 days, no links

    Compress example for project-status.md:

    • Before: "11-02 started auth refactor; 11-05 hit token bug, tried X, then Y; 11-08 merged; 11-10 deployed"
    • After: "Auth refactor is live (2026-11-10)."

    Wake

    • Handled: 2 fixed, 1 merged, 1 compressed, 2 archived (moved to memory/archive/, listed in ARCHIVE.md).
    • Links pointing to release-flow.md now point to deploy-notes.md.
    • Boot injection: 4,730 → 4,180 tok (budget 5,000). Memory: 19 files / 7,940 tok → 17 files / 6,610 tok.
    • 1 entry in archive/ is older than 30 days and unread. It can be purged if you ask; I won't do it on my own.

    Next steps

    • Run /sleep again in a few weeks, or when the boot-injection number creeps toward your budget.
    • Add review: YYYY-MM-DD to time-sensitive memories so the next scan flags them on time.
    deploy-notes.md

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Claude Code's auto-memory gets loaded at the start of every session. Over weeks it fills up with progress logs, dead paths, duplicates and notes nobody reads, and you pay for all of it in context tokens, every session.

    Sleep does what the brain does overnight: it consolidates experiences into conclusions and prunes weak connections. Say "sleep" or run /sleep:

    1. Backup: the whole memory folder is copied first, so every run can be undone.
    2. Rule scan, with no AI tokens spent:
      • local paths that no longer exist
      • notes past their review: date
      • memories never read in your transcripts (cold)
      • orphans with no links in or out
      • files missing from the MEMORY.md index
      • hot and suspicious: read often and flagged, the most dangerous kind
    3. AI pass, only on what rules can't judge: duplicates, and entries that mix a conclusion with its history and can be rewritten as one line of current state.
    4. Proposal table: grouped by reason and sorted by tokens. Each row gets one of four actions: fix, compress, merge, or archive. Approve it in batches, for example "all dead-path ones, yes".
    5. Wake: you get a before → after report of boot-injection tokens against your budget.

    What it never does

    • It never deletes anything outside archive/. Stale memories are moved there, and the index is updated.
    • It never acts without your approval.
    • Purge permanently deletes files, only from archive/, and only when you explicitly ask for it.

    Works on its own

    If you also run Noema, a free floating window that shows your memory as a 3D neural network, it plays the whole thing live: dimming into sleep, scanned connections lighting up, and the token delta on waking.

    Requirements: Claude Code with auto-memory, Node.js. Tested on Windows.

    Requires local Node.js. Does not validate external URLs. No automatic purging. Users must approve batches of changes manually.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 4 days ago

    • Free with an Agensi account

    Requires

    Claude Code with auto-memory
    Node.js

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Environment Variables

    File Scopes

    ~/.claude/projects/*/memory/**

    Reads the memory folder and your session transcripts (to count which memories were read). Writes only a report and a backup under %LOCALAPPDATA%\Noema\sleep, and edits memory files only after you approve. LOCALAPPDATA is read to locate that folder.

    Listed4 days ago

    What's inside

    Frequently Asked Questions

    Claude Code loads your CLAUDE.md and MEMORY.md index at the start of every session. Sleep archives stale entries, merges duplicates and compresses dated logs into one line of current state, so that boot injection shrinks. The wake report shows the before → after token count against your budget.

    No, the skill prioritizes safety by moving stale files to a dedicated 'archive/' folder and updating 'ARCHIVE.md' rather than deleting data, and it always creates a timestamped backup before starting any cleanup.

    It is built for Claude Code's auto-memory (~/.claude/projects/<project>/memory) and needs Node.js to run the bundled scanner. Tested on Windows. Other agents don't keep memory in that format, so it won't find anything to tidy there.

    Three files: SKILL.md (the instructions Claude follows), noema-sleep.js (a dependency-free Node.js scanner that backs up, scans, and writes the report), and an MIT LICENSE. Put the folder in ~/.claude/skills/sleep.

    No, the skill follows an 'Approval' step where it presents a grouped proposal table (Fix, Compress, Merge, Archive), allowing you to review and confirm all changes before they are applied.

    This skill focuses on internal project memory files; it does not currently check or validate external URLs or third-party documentation links.

    No. Noema is a free floating window that shows your memory as a 3D neural network (github.com/youllook/noema). If it is running, it animates sleep, scan and wake live; without it, Sleep works exactly the same.

    New in Agents & Orchestration