CRUX-Compress: Command for Claude Code

.cursor/commands/crux-meditate.md

crux-meditate is a command for Claude Code, Cursor from zotoio/CRUX-Compress. It costs 0 tokens per session (23,508 once invoked), scanned A, original, MIT.

A command for exploring a topic, question, or code area through several layers of agent analysis while using stored project memories.

In plain words
What is it for?
It can explore the current conversation, a supplied topic, or referenced files and folders, with options for quick, random-model, per-branch, or ensemble exploration.
Why use it?
It helps break an unfamiliar subject into related themes and examine those themes from multiple perspectives.

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 →

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-meditate.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-meditate

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/zotoio/crux-compress/crux-meditate"><img src="https://agentmods.dev/badge/commands/zotoio/crux-compress/crux-meditate.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 23,508 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 $0.23508
Opus 5 $0.00000 $0.11754
Sonnet 5 $0.00000 $0.04702
Haiku 4.5 $0.00000 $0.02351

Measured 12d ago against content hash 9cffc81664ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

crux-meditate 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/commands/crux-meditate.md · 1,101 lines

How it starts

The opening of the file, as written. The whole thing — 1,101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

crux-meditate

Recursive memory-informed exploration of themes, topics, and intent through 3-level deep agent inception.

Repository: github.com/zotoio/CRUX-Compress

Usage

/crux-meditate                          - Explore facets derived from current chat context
/crux-meditate "topic or question"      - Explore a specific theme
/crux-meditate @file.ts @folder/        - Explore facets around referenced code
/crux-meditate --quick "topic"          - Fast parallel-fanout exploration (legacy behaviour)
/crux-meditate --random-model "topic"   - One tree, model randomly picked from `cruxMemories.meditate.modelPool` (same agent count as default)
/crux-meditate --model-per-branch "topic" - One tree, each top-level facet branch assigned a model from the pool; descendants inherit (same agent count as default)
/crux-meditate --ensemble "topic"       - Ensemble max: run on every model in the pool in parallel, then aggregate
/crux-meditate --ensemble --quick "topic" - Ensemble max of Quick-mode trees

The --quick, --random-model, --model-per-branch, and --ensemble flags may appear anywhere in $ARGUMENTS. --quick may be combined with any of the model-strategy flags. --random-model, --model-per-branch, and --ensemble are mutually exclusive — passing more than one aborts with an error.

Modes

Two orthogonal axes control a meditation: the recursion mode (Research vs Quick) and the model strategy (how cruxMemories.meditate.modelPool is used, if at all).

Recursion mode

Mode Flag Default? Behaviour
Research (none — default) yes Depth-first serial recursion. Each depth's findings drive the next depth's facet derivation. Globally unique facet allocation across all branches. Bottom-up incorporation. Branch peer review at the top. Mandatory citations at every step.
Quick --quick no Fast parallel fan-out (legacy behaviour). All 3 facets per node derived upfront and explored in parallel. Citations are still mandatory (same ## Citations requirement as Research mode), but the parent validates them best-effort and warns rather than re-spawning offending children. Use when you want speed over rigor.

Read the full file on GitHub · 1,101 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 · 1,101 lines · 0 tokens per session scan A 9cffc81664ac

Subscribe to this mod's changes

crux-meditate is a command published in the GitHub repository zotoio/CRUX-Compress (8 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 23,508 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.