CRUX-Compress: Skill for Cursor

.cursor/skills/crux-skill-memory-reference-tracker/SKILL.md

crux-skill-memory-reference-tracker is a skill for Cursor from zotoio/CRUX-Compress. It costs 65 tokens per session (2,450 once invoked), scanned A, original, MIT.

A procedure for tracking when CRUX memories are used in agent responses. It stores reference counts and recent uses in separate .refs.yml files instead of putting usage data inside the memory itself.

In plain words
What is it for?
Use it when recording a memory reference, checking promotion candidates, or cleaning up unused tracking files during REM sleep. It follows settings for tracking location, output annotations, promotion thresholds, and stored history.
Why use it?
It keeps memory content separate from changing usage statistics and helps detect memories that should become permanent rules. It also keeps recent-reference lists within the configured size.

Skill for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions 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 →

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-reference-tracker/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-reference-tracker

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/zotoio/crux-compress/crux-skill-memory-reference-tracker"><img src="https://agentmods.dev/badge/skills/zotoio/crux-compress/crux-skill-memory-reference-tracker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,450 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: 3 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 3
    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 20
    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 155
    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 $0.00065 $0.02450
Opus 5 $0.00032 $0.01225
Sonnet 5 $0.00013 $0.00490
Haiku 4.5 $0.00006 $0.00245

Measured 10d ago against content hash 92d1beb527f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

crux-skill-memory-reference-tracker 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 10d 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-reference-tracker/SKILL.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CRUX Skill: Memory Reference Tracker

Manages per-memory reference tracking files (.refs.yml) in the configured trackingDir. Tracker files are the single source of truth for how often, how recently, and by whom a memory was referenced. Memory frontmatter stays clean — it stores what a memory is, not how often it is used.

Config

All settings live in .crux/crux-memories.json under cruxMemories.referenceTracking:

Key Type Default Description
enabled boolean true Master switch for reference tracking
trackingDir string .crux/reference-tracking Directory for .refs.yml files
indicateInOutput boolean true Whether agents annotate output when influenced by a memory
indicatorFormat string [memory:{title}] Format string for output annotations ({title} is replaced with the memory title)
promotionToRuleThreshold integer 30 Total reference count that flags a memory for promotion to a permanent rule
maxReferencesStored integer 10 Maximum entries in recent_references (oldest evicted when cap exceeded)

Additionally, cruxMemories.unitOfWork (e.g. spec) determines the key name used in recent_references source entries.

Operations

1. Record Reference

When: An agent's output is influenced by a memory.

Steps:

  1. Read config from .crux/crux-memories.json. If referenceTracking.enabled is false, skip all tracking.
  2. Determine the memory slug from the memory filename (strip .memory.md or .memory.crux.md suffix and any path prefix).
  3. Look for {trackingDir}/{slug}.refs.yml.
    • If it does not exist — create it (see Lazy Creation).
    • If it exists — read and update it.
  4. Increment the references counter by 1.
  5. Set last_referenced to today's date (YYYY-MM-DD).
  6. Update recent_references (see Manage Recent References).
  7. Sync strength from the memory file's frontmatter into the tracker (see Sync Strength).
  8. Write the updated tracker file.
  9. Check whether references now exceeds promotionToRuleThreshold (see Promotion Flag).

Read the full file on GitHub · 220 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. 10d ago First seen · 220 lines · 65 tokens per session scan A 92d1beb527f1

Subscribe to this mod's changes

crux-skill-memory-reference-tracker is a skill published in the GitHub repository zotoio/CRUX-Compress (8 stars, last pushed 3d ago), licensed MIT. It adds 65 tokens to every session and 2,450 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

ijfw-handoff

Session handoff generation and loading. Trigger: session end, context full, /handoff.

FerroxLabs/ijfw · 23 tokens