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 (2,046 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 AGENTS.md; 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 2,046 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 $0.02046
Opus 5.5 $0.00026 $0.00818
Sonnet 5.5 $0.00013 $0.00409
Haiku 4.5 $0.00006 $0.00205

Measured 1mo ago against content hash 96e9c2de391a, 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-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 1mo 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 · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 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 keys and defaults: see .cursor/skills/_memory-shared.md#config-reference and .crux/crux-memories.json (authoritative). This skill reads keys under cruxMemories.referenceTracking.* plus cruxMemories.unitOfWork (which 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).

2. Indicate in Output

When: referenceTracking.indicateInOutput is true and an agent's output is influenced by a memory.

Instruction to agents: When your response is influenced by a loaded memory, include the configured indicator in your output. The default format is [memory:{title}], where {title} is replaced with the memory's title frontmatter field.

Example with default format:

Read the full file on GitHub · 188 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. 1mo ago Changed · -32 lines 96e9c2de391a
  2. 2mo 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 14d ago), licensed MIT. It adds 65 tokens to every session and 2,046 once invoked, about $0.0003 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.

Related

crux-skill-memory-reference-tracker compared with skills from other repositories

crux-skill-memory-reference-tracker next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
crux-skill-memory-reference-trackerzotoio/CRUX-CompressSkill814d agoMITA65Cursor
kiro-steering-customgotalab/cc-sddSkill3.8k15d agoMITA14Claude Code, Codex
[object Object]team-reflect/reflect-openSkill1.6kyesterdayMITA51Claude Code, Codex
identity-snapshotdavekilleen/DexSkill5128d agoMITA74Claude Code, Codex
daily-journalhuytieu/COG-second-brainSkill1.3k14d agoMITA107Claude Code
simplemem-skillaiming-lab/SimpleMemSkill3.9k3mo agoMITA58Claude Code, Codex
alive:session-historyalivecontext/aliveSkill1321mo agoMITA76Claude Code