What is crux-skill-memory-index?

A skill that builds a sorted list of memory files, using their priority and reference-tracking data. It writes the list to `.crux/memory-index.yml`.

Use it after creating, editing, or deleting memories, after bulk memory changes, or after a dream cycle that extracts new memories.

It gives the agent one discovery list instead of requiring it to inspect every memory file whenever memories change.

How zotoio/CRUX-Compress configures Cursor

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-index/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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/zotoio/crux-compress/crux-skill-memory-index/github.svg)](https://agentmods.dev/skills/zotoio/crux-compress/crux-skill-memory-index)

Your own site

<a href="https://agentmods.dev/skills/zotoio/crux-compress/crux-skill-memory-index"><img src="https://agentmods.dev/badge/skills/zotoio/crux-compress/crux-skill-memory-index/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/zotoio/crux-compress/crux-skill-memory-index"><img src="https://agentmods.dev/badge/skills/zotoio/crux-compress/crux-skill-memory-index.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 993 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 pass 7 Sept 2026

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.

Model	Per session	Once invoked
Fable 5.1	$0.00042	$0.00993
Opus 5.5	$0.00017	$0.00397
Sonnet 5.5	$0.00008	$0.00199
Haiku 4.5	$0.00004	$0.00099

Measured 1mo ago against content hash 74d51c1768f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

crux-skill-memory-index 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 1mo ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/memory-index.py, scripts/post-dream.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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-index/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CRUX Skill: Memory Index

Builds a prioritised index of all memory files by scanning the configured memory directories, joining with reference tracker data, and writing a sorted index to .crux/memory-index.yml.

When to Use

After creating, updating, or deleting memories (post-CRUD housekeeping)
During REM sleep / dream cycles to refresh the index
When an agent needs to discover available memories sorted by priority
After bulk operations that may have changed multiple memory files

Quick Start

# Rebuild the index (uses default config path)
python .cursor/skills/crux/crux-skill-memory-index/scripts/memory-index.py

# Rebuild with a custom config path
python .cursor/skills/crux/crux-skill-memory-index/scripts/memory-index.py --config path/to/config.json

# Post-dream rebuild (checks enableMemories flag, then rebuilds)
python .cursor/skills/crux/crux-skill-memory-index/scripts/post-dream.py

Post-Dream Rebuild

The post-dream.py script is a convenience wrapper invoked programmatically by the /crux-dream workflow after memory extraction or REM sleep completes. It:

Checks .crux/crux-memories.json — exits early if enableMemories is not "true"
Calls memory-index.py to rebuild the index
The MCP server's file watcher detects the index timestamp change automatically

This script is not a Cursor event hook and is not registered in .cursor/hooks.json.

Configuration

Reads .crux/crux-memories.json — uses cruxMemories.storage.memoriesDir / agentMemoriesDir / indexFile, cruxMemories.referenceTracking.trackingDir, and cruxMemories.typePriority.

Config keys and defaults: see .cursor/skills/_memory-shared.md#config-reference and .crux/crux-memories.json (authoritative).

Index File Format

The generated .crux/memory-index.yml contains a flat list under the memories key, sorted by:

Type priority — types earlier in typePriority rank higher
Strength descending — within a type, stronger memories first
References descending — ties broken by reference count

Read the full file on GitHub · 100 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

1mo ago Changed · -27 lines 74d51c1768f6
2mo ago First seen · 127 lines · 42 tokens per session scan A 43006e2d9f8a

Subscribe to this mod's changes

crux-skill-memory-index is a skill published in the GitHub repository zotoio/CRUX-Compress (8 stars, last pushed 14d ago), licensed MIT. It adds 42 tokens to every session and 993 once invoked, about $0.0002 per session on Opus 5.5. 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.

Memory and context claude compression cursor markdown optimisation rules

crux-skill-memory-index next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
crux-skill-memory-indexzotoio/CRUX-Compress	Skill	8	14d ago	MIT	A	42	Cursor
kiro-steering-customgotalab/cc-sdd	Skill	3.8k	15d ago	MIT	A	14	Claude Code, Codex
[object Object]team-reflect/reflect-open	Skill	1.6k	yesterday	MIT	A	51	Claude Code, Codex
identity-snapshotdavekilleen/Dex	Skill	512	8d ago	MIT	A	74	Claude Code, Codex
daily-journalhuytieu/COG-second-brain	Skill	1.3k	14d ago	MIT	A	107	Claude Code
simplemem-skillaiming-lab/SimpleMem	Skill	3.9k	3mo ago	MIT	A	58	Claude Code, Codex
alive:session-historyalivecontext/alive	Skill	132	1mo ago	MIT	A	76	Claude Code

CRUX-Compress: Skill for Cursor