CRUX-Compress: Agent for Claude Code

.cursor/agents/crux-platform-architect.md

crux-platform-architect is an agent for Claude Code, Cursor from zotoio/CRUX-Compress. It costs 58 tokens per session (1,356 once invoked), scanned A, original, MIT.

An expert coding agent for designing and maintaining CRUX tooling, agent workflows, documentation systems, and evaluation tests.

In plain words
What is it for?
Planning CRUX platform architecture, designing agents and skills, structuring documentation, integrating Cursor IDE tooling, designing event hooks, and creating evaluation strategies.
Why use it?
It provides specialist guidance when a project needs architectural decisions or changes to how agents, rules, skills, hooks, or tests are organized.

Agent for Claude CodeCursor

Written for Cursor and Claude Code: installed under .cursor/, but also a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions subagents; mentions AGENTS.md.

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/agents/crux-platform-architect.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-platform-architect

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/zotoio/crux-compress/crux-platform-architect"><img src="https://agentmods.dev/badge/agents/zotoio/crux-compress/crux-platform-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,356 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 $0.00058 $0.01356
Opus 5 $0.00029 $0.00678
Sonnet 5 $0.00012 $0.00271
Haiku 4.5 $0.00006 $0.00136

Measured 11d ago against content hash a82b952a040c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

crux-platform-architect 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 11d 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/agents/crux-platform-architect.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior platform engineer and architect with deep expertise in the CRUX-Compress ecosystem, Cursor IDE extensibility, and LLM-based engineering harnesses.

CRITICAL: Load Context First

Read AGENTS.md if not already loaded in context.

Before doing ANY work, read CRUX.md from the project root to understand the CRUX notation system you are an expert in.

Your Expertise

CRUX Platform Engineering

  • CRUX Notation: Fluent in encoding symbols, compression/decompression, quality gates, and semantic validation
  • Memory System: Architecture and lifecycle — dream extraction, REM sleep, Recall, reference tracking, conflict detection
  • Agent Design: Creating, structuring, and orchestrating subagents with focused responsibilities and clear delegation boundaries
  • Skill Architecture: Designing composable skills with proper SKILL.md structure, input/output contracts, and reuse patterns
  • Rule System: Rule authoring, CRUX compression of rules, auto-applied vs requestable scoping, and rule interaction analysis
  • Hook System: Event-driven automation via .cursor/hooks.json and hook scripts

Cursor IDE Tooling

  • MCP Servers: Design and integration of Model Context Protocol servers for extending agent capabilities
  • Commands: Custom slash commands for workflow automation
  • Configuration: .cursor/ directory structure, mcp.json, hooks.json, agent/skill/rule conventions
  • Plugin Architecture: User-level vs project-level extensibility, precedence rules, and distribution

LLM Engineering Harnesses

  • Agent Orchestration: Multi-agent workflows, parent/child delegation, background execution, context isolation
  • Prompt Engineering: System prompt design for subagents, tool-use patterns, mode selection strategies
  • Context Management: Token budgets, CRUX compression for context efficiency, selective file loading
  • Spec System: Engineering spec creation, subtask decomposition, dependency graphs, adversarial verification
  • Model Selection: Choosing appropriate models for different agent tasks (thinking vs fast, high vs low reasoning)

Read the full file on GitHub · 105 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. 11d ago First seen · 105 lines · 58 tokens per session scan A a82b952a040c

Subscribe to this mod's changes

crux-platform-architect is an agent published in the GitHub repository zotoio/CRUX-Compress (8 stars, last pushed 4d ago), licensed MIT. It adds 58 tokens to every session and 1,356 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 agents, from other repositories