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.
curl -O https://raw.githubusercontent.com/zotoio/CRUX-Compress/main/.cursor/agents/crux-platform-architect.mdgit clone --depth 1 https://github.com/zotoio/CRUX-CompressWrote 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.
[](https://agentmods.dev/agents/zotoio/crux-compress/crux-platform-architect)<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.
<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>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00058 | $0.01520 |
| Opus 5.5 | $0.00023 | $0.00608 |
| Sonnet 5.5 | $0.00012 | $0.00304 |
| Haiku 4.5 | $0.00006 | $0.00152 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 107 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.
Load Context
Read AGENTS.md if not already loaded in context. If your task involves compressing, decompressing, authoring, or validating CRUX notation, read CRUX.md. Otherwise rely on _CRUX-RULE.mdc and the CRUX block in AGENTS.md for symbol-aware behavior.
Honor context_manifest
Before reading AGENTS.md, CRUX.md, or .crux/crux-memories.json, check your task prompt for a context_manifest stanza. If a file is marked loaded, do not re-read it. If a probe field is present, acknowledge it in your first internal reasoning step. If the stanza is missing entirely, fall back to the unconditional loads documented above.
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.jsonand 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)
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.
- 1mo ago Changed · +2 lines 2939b5112995
- 2mo ago First seen · 105 lines · 58 tokens per session scan A a82b952a040c
crux-platform-architect is an agent published in the GitHub repository zotoio/CRUX-Compress (8 stars, last pushed 14d ago), licensed MIT. It adds 58 tokens to every session and 1,520 once invoked, about $0.0002 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.
crux-platform-architect compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| crux-platform-architectzotoio/CRUX-Compress | Agent | 8 | 14d ago | MIT | A | 58 | Claude Code, Cursor |
| codebase-maintainer-agentyu-iskw/meta-agent-skills | Agent | 2 | 2d ago | none | A | 22 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | yesterday | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | 4d ago | MIT | A | 33 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 2d ago | MIT | A | 52 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 61 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 11 | Claude Code |