CRUX-Compress: Skill for Cursor

.cursor/skills/crux-skill-memory-rebalance/SKILL.md

crux-skill-memory-rebalance is a skill for Cursor from zotoio/CRUX-Compress. It costs 54 tokens per session (7,533 once invoked), scanned A, original, MIT.

A procedure for maintaining a file-based memory system called CRUX. It reviews stored memories and their usage records, then suggests or applies changes such as combining, promoting, demoting, or archiving them.

In plain words
What is it for?
Use it during CRUX REM sleep, memory-strength reviews, conflict checks, or cleanup of unused memories and tracking files. The procedure reads settings that control when memories are demoted, archived, or promoted to permanent rules.
Why use it?
It helps keep long-term agent memories consistent and useful as they become outdated, duplicated, unused, or contradictory. It also cleans up tracking files that no longer match stored memories.

Skill for Cursor

Written for Cursor: installed under .cursor/.

This is zotoio/CRUX-Compress's own configuration. It tells 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 →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python .cursor/skills/crux/crux-skill-memory-index/scripts/memory-index.py.

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/skills/crux-skill-memory-rebalance/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/zotoio/CRUX-Compress

Made for: 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-skill-memory-rebalance

README.md
[![agentmods](https://agentmods.dev/badge/skills/zotoio/crux-compress/crux-skill-memory-rebalance/github.svg)](https://agentmods.dev/skills/zotoio/crux-compress/crux-skill-memory-rebalance)
Your own site
<a href="https://agentmods.dev/skills/zotoio/crux-compress/crux-skill-memory-rebalance"><img src="https://agentmods.dev/badge/skills/zotoio/crux-compress/crux-skill-memory-rebalance/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-skill-memory-rebalance

Your own site · 80×15
<a href="https://agentmods.dev/skills/zotoio/crux-compress/crux-skill-memory-rebalance"><img src="https://agentmods.dev/badge/skills/zotoio/crux-compress/crux-skill-memory-rebalance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,533 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Memory Poisoning · line 330
    Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.
    Fix: Do not allow untrusted input to persist in agent memory or context. Validate all content before storing and implement memory isolation between sessions.
  • medium Memory Poisoning · line 340
    Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.
    Fix: Do not allow untrusted input to persist in agent memory or context. Validate all content before storing and implement memory isolation between sessions.
How audits are shown
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 $0.00054 $0.07533
Opus 5 $0.00027 $0.03766
Sonnet 5 $0.00011 $0.01507
Haiku 4.5 $0.00005 $0.00753

Measured 12d ago against content hash 726503534261, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

crux-skill-memory-rebalance 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/skills/crux-skill-memory-rebalance/SKILL.md · 603 lines

How it starts

The opening of the file, as written. The whole thing — 603 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CRUX Skill: Memory Rebalance

The complete REM sleep workflow for the CRUX memory system. Analyses all memories and their reference trackers to verify consistency, detect conflicts, recommend promotions/demotions/archival/consolidation, and apply confirmed changes.

When to Use

Use this skill when:

  • Running REM sleep (/crux-dream --rem or /crux-dream --rem --yolo)
  • Manually rebalancing memory strength scores
  • Investigating potential conflicts between memories
  • Cleaning up orphaned tracker files or stale memories

Prerequisites

Before any operation:

  1. Read config: Load .crux/crux-memories.json and extract:
    • cruxMemories.typeTransitions — promotion thresholds and targets per type
    • cruxMemories.demoteAfterDaysUnreferenced — days before demotion (default 90)
    • cruxMemories.archiveAfterDaysUnreferenced — days before archival (default 180)
    • cruxMemories.referenceTracking.trackingDir — tracker file location (default .crux/reference-tracking)
    • cruxMemories.referenceTracking.promotionToRuleThreshold — reference count triggering rule promotion flag (default 30)
    • cruxMemories.storage.memoriesDir — base memory directory (default memories)
    • cruxMemories.storage.agentMemoriesDir — agent-scoped memory directory (default memories/agents)
    • cruxMemories.storage.archiveDir — archive directory for REM summaries (default .ai-ignored/executed)
    • cruxMemories.typePriority — valid types in priority order
    • flags.enableMemoryCompression — whether compression is enabled (default "false")
    • flags.enableMemoryConsolidation — whether consolidation is enabled (default "false")
    • cruxMemories.compressionTarget — target compressed size as % of original (default 33)
    • cruxMemories.sizeUnit — unit for size thresholds (default "lines")
    • cruxMemories.compressionMinLines — minimum file size in lines before compression is considered (default 500)
    • cruxMemories.maxMemorySize — hard cap on memory file size in lines (default 1000)
    • cruxMemories.maxConsolidatedSize — hard cap on consolidated memory file size in lines (default 2000)
  2. Guard check: If flags.enableMemories is not "true", abort and inform the caller that memories are disabled

Read the full file on GitHub · 603 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 · 603 lines · 54 tokens per session scan A 726503534261

Subscribe to this mod's changes

crux-skill-memory-rebalance is a skill published in the GitHub repository zotoio/CRUX-Compress (8 stars, last pushed 5d ago), licensed MIT. It adds 54 tokens to every session and 7,533 once invoked, about $0.0003 per session on Opus 5. 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.

Related

Other skills, from other repositories

simplemem-skill

Store and retrieve conversation memories across sessions. Use when asked to 'remember this', 'save conversation', 'add to memory', 'what did we discuss about...', 'query memories', or 'import chat history'. Also use proactively to preserve important dialogue context and decisions.

aiming-lab/SimpleMem · 58 tokens

[object Object]

Read, search, and open notes in the user's "{{GRAPHNAME}}" Reflect graph via the reflect CLI. Use when the user asks about their notes, daily notes, journal, or anything they may have written down in Reflect.

team-reflect/reflect-open · 51 tokens

karpathy-llm-wiki

Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.

Astro-Han/karpathy-llm-wiki · 67 tokens

init

Install or update OwnMem in the current repository. Use when the user asks to set up OwnMem, add local project memory for coding agents, or refresh an existing OwnMem installation after a version bump.

grpcer/ownmem · 43 tokens

daily-journal

A passive daily work journal that Claude keeps FOR you so you never have to write it yourself. Append short entries after meaningful work (what was done, what you focused on, artifacts touched) to 01-daily/journal/YYYY-MM-DD.md. Run a guided reflection at night or in the morning. Use when you run /daily-journal, say…

huytieu/COG-second-brain · 107 tokens

alive:session-history

Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…

alivecontext/alive · 76 tokens