CRUX-Compress: Command for Claude Code

.cursor/commands/crux-dream.md

crux-dream is a command for Claude Code, Cursor from zotoio/CRUX-Compress. It costs 0 tokens per session (1,801 once invoked), scanned A, original, MIT.

A command for extracting useful memories after a completed project task and reorganising the stored memory collection. REM sleep here means a memory-maintenance process, not human sleep.

In plain words
What is it for?
It can extract memories from a named specification, run memory rebalancing, automatically apply non-conflicting changes, and ask the user to resolve decisions or conflicts when needed.
Why use it?
It turns completed work into reusable project knowledge and can rebalance the memory collection to keep it useful.

Command for Claude CodeCursor

Written for Claude Code and Cursor: $ARGUMENTS substitution, but also installed under .cursor/. Also seen: mentions subagents.

This is zotoio/CRUX-Compress's own configuration. It tells Claude Code and Cursor how to work on CRUX-Compress itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything CRUX-Compress configures →

Reuse

Borrowing it

Nothing to install: this file belongs to zotoio/CRUX-Compress. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/zotoio/CRUX-Compress/main/.cursor/commands/crux-dream.md
Clone the repo
git clone --depth 1 https://github.com/zotoio/CRUX-Compress

Made for: Claude Code, Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for crux-dream

README.md
[![agentmods](https://agentmods.dev/badge/commands/zotoio/crux-compress/crux-dream/github.svg)](https://agentmods.dev/commands/zotoio/crux-compress/crux-dream)
Your own site
<a href="https://agentmods.dev/commands/zotoio/crux-compress/crux-dream"><img src="https://agentmods.dev/badge/commands/zotoio/crux-compress/crux-dream/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for crux-dream

Your own site · 80×15
<a href="https://agentmods.dev/commands/zotoio/crux-compress/crux-dream"><img src="https://agentmods.dev/badge/commands/zotoio/crux-compress/crux-dream.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,801 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01801
Opus 5 $0.00000 $0.00901
Sonnet 5 $0.00000 $0.00360
Haiku 4.5 $0.00000 $0.00180

Measured 12d ago against content hash dedb35a71a00, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

crux-dream scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/commands/crux-dream.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

crux-dream

Post-execution memory extraction and REM sleep rebalancing.

Repository: github.com/zotoio/CRUX-Compress

Usage

/crux-dream <spec-name>              - Extract memories from a completed spec
/crux-dream --rem                    - Run REM sleep (rebalance all memories)
/crux-dream --rem --yolo             - Run REM sleep, auto-apply non-conflict changes

Instructions

When this command is invoked, spawn a crux-cursor-memory-manager subagent to handle the memory workflow. The manager orchestrates the six memory skills to perform extraction or rebalancing.

User input escalation — CRITICAL: This command uses Pattern B (work first, then escalate) — the subagent must analyse artifacts and rank candidates before the user can make decisions. The subagent NEVER calls AskQuestion directly. ALL user-facing questions (accepting candidates, applying REM changes, resolving conflicts, archiving) are handled by the parent agent (you) using AskQuestion. The subagent returns its analysis and any needs_user_input sections; you collect answers from the user and resume the subagent with them.

Foreground execution — CRITICAL: The subagent MUST run in the foreground (run_in_background: false). Background subagents only return a truncated summary notification to the parent — the full analysis is lost. Foreground execution blocks the parent until the subagent completes and returns its complete response, which the parent then displays verbatim to the user.

Full output relay — CRITICAL: The parent agent MUST relay the subagent's complete response to the user without summarizing, truncating, or paraphrasing. The subagent's response contains the full spec analysis — artifact examination, candidate ranking, conflict reports, resolved bug detection — and all of this must be visible to the user before any decisions are requested. If the response is long, display it in full; do not condense it.

Read the full file on GitHub · 83 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 83 lines · 0 tokens per session scan A dedb35a71a00

Subscribe to this mod's changes

crux-dream is a command published in the GitHub repository zotoio/CRUX-Compress (8 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,801 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.