agentmods.dev

CRUX-Compress: Command for Claude Code

.cursor/commands/crux-remember.md

crux-remember is a command for Claude Code, Cursor from zotoio/CRUX-Compress. It costs 0 tokens per session (738 once invoked), scanned A, original, MIT.

A chat command for saving a new insight or piece of project knowledge in the CRUX memory collection.

In plain words
What is it for?
Creating a memory interactively or from supplied text, with an optional type such as a learning.
Why use it?
It gives you a way to record useful information outside the project’s formal specification process, so it can be included in later memory maintenance.

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 →

not rated 8repo 3d ago A scan 0 tokens original MIT
View source ↗ zotoio/CRUX-Compress compress.md
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-remember.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-remember

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/zotoio/crux-compress/crux-remember"><img src="https://agentmods.dev/badge/commands/zotoio/crux-compress/crux-remember.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 738 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 $0.00738
Opus 5 $0.00000 $0.00369
Sonnet 5 $0.00000 $0.00148
Haiku 4.5 $0.00000 $0.00074

Measured 10d ago against content hash e3ff2579e57c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

crux-remember 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/commands/crux-remember.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

crux-remember

Store ad-hoc memories outside of spec workflows. These memories participate in standard consolidation during REM sleep.

Repository: github.com/zotoio/CRUX-Compress

Usage

/crux-remember                              - Interactively create a new memory
/crux-remember "insight text"               - Create a memory from the provided text
/crux-remember "insight" --type learning    - Create with pre-specified type

Instructions

This command primarily uses Pattern A (pre-collect then spawn) — the user's choices (type, tags, description) are known upfront. The parent agent (you) collects all input via AskQuestion FIRST, then spawns a crux-cursor-memory-manager subagent with the pre-collected answers. The subagent never calls AskQuestion directly. If the subagent encounters an unexpected decision during creation (e.g. conflict, size limit), it falls back to Pattern B and returns needs_user_input.

Argument Handling

  • No arguments: Prompt the user for the memory content/insight they want to save.
  • Quoted text (e.g. "always validate checksums before overwrite"): Use as the memory title/body. Pass $ARGUMENTS to the subagent.
  • --type <type>: If provided, skip the type selection prompt and use the specified type directly.

What Happens

Phase 1 — Parent collects user input (before spawning subagent):

  1. If no text was provided, ask the user what they want to remember
  2. Use the AskQuestion tool to ask the user to select the memory type. Present options from the typeTransitions keys in config: idea, learning, redflag, core, goal. If --type was provided, skip this step.
  3. Use the AskQuestion tool to ask the user for optional tags (comma-separated) and a brief description. Suggest relevant tags based on the memory content and current context.

Phase 2 — Spawn subagent with all answers:

  1. Spawn a crux-cursor-memory-manager subagent in Remember mode, passing ALL collected answers in the task prompt:
    • The memory content/insight text
    • The selected type
    • The user's tags
    • The user's description
    • source: "adhoc"
  2. The subagent creates the memory via crux-skill-memory-crud and rebuilds the index via crux-skill-memory-index
  3. Display the subagent's confirmation to the user — the memory's short hash ID, title, type, and file path

Read the full file on GitHub · 55 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 · 55 lines · 0 tokens per session scan A e3ff2579e57c

Subscribe to this mod's changes

crux-remember is a command published in the GitHub repository zotoio/CRUX-Compress (8 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 738 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.

Memory and contextclaudecompressioncursormarkdownoptimisationrules
Related

Other commands, from other repositories

context-save

An elite context engineering specialist focused on comprehensive, semantic, and dynamically adaptable context preservation across AI workflows. This tool orchestrates advanced context capture, serialization, and retrieval strategies to maintain institutional knowledge and enable seamless multi-session collaboration.

wshobson/agents · 0 tokens

save-session-learnings

Document session learnings to CLAUDE.md and AGENTS.md. Use after completing significant tasks, debugging sessions, or discovering project patterns.

CloudAI-X/claude-workflow-v2 · 28 tokens

wiki-query

Ask questions against the wiki. Synthesizes answers from wiki pages with cross-reference citations.

zosmaai/pi-llm-wiki · 18 tokens

wiki-digest

Generate a daily or weekly digest of wiki changes — new sources, pages, insights, and gaps.

zosmaai/pi-llm-wiki · 20 tokens

memory-why

Show why a memory recall returned what it did -- BM25 vs vector vs hybrid provenance.

FerroxLabs/ijfw · 18 tokens

kiro-steering-custom

Command "kiro-steering-custom" from gotalab/cc-sdd, covering kiro custom steering creation, workflow, available templates, steering principles and tool guidance.

gotalab/cc-sdd · 0 tokens