Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git 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/rules/zotoio/crux-compress/crux-memories-mcp-context)<a href="https://agentmods.dev/rules/zotoio/crux-compress/crux-memories-mcp-context"><img src="https://agentmods.dev/badge/rules/zotoio/crux-compress/crux-memories-mcp-context/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/rules/zotoio/crux-compress/crux-memories-mcp-context"><img src="https://agentmods.dev/badge/rules/zotoio/crux-compress/crux-memories-mcp-context.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 | $0.00347 | $0.00347 |
| Opus 5 | $0.00173 | $0.00173 |
| Sonnet 5 | $0.00069 | $0.00069 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
crux-memories-mcp-context 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.
What it actually says
Use CRUX Memories MCP for Auxiliary Context
When working on non-trivial tasks, proactively query the crux-memories MCP server to find relevant memories that can inform your decisions. Memories contain project-specific learnings, patterns, red flags, and architectural context accumulated over time.
When to Search
- Before making architectural or design decisions
- When encountering unfamiliar parts of the codebase
- When planning implementations, refactors, or debugging
- When the task touches patterns, conventions, or past decisions that may be documented
How to Search
Use the memory-search tool from the crux-memories MCP server:
CallMcpTool: server=user-crux-memories, toolName=memory-search
arguments: { "query": "<natural language description of what you need>", "includeContent": true }
Then read full memory content with memory-read if search results are relevant but need more detail.
Guidelines
- Search early in your workflow, not after you've already committed to an approach
- Use descriptive queries — the search is semantic, so natural language works well
- Filter by
types(core, learning, redflag, idea, goal) when you know the category - Filter by
minStrengthto prioritise well-established memories (strength >= 3) - When a memory influences your response, annotate with
[memory:{title}]per the memories integration rule - Do NOT search if
/crux-amnesiais active (unless the user explicitly invoked a memory command)
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.
- 11d ago First seen · 36 lines · 347 tokens per session scan A c4fc24f55554
crux-memories-mcp-context is a cursor rule published in the GitHub repository zotoio/CRUX-Compress (8 stars, last pushed 4d ago), licensed MIT. It adds 347 tokens to every session, about $0.0017 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.
Other cursor rules, from other repositories
compendium
Prefer the Compendium MCP gateway to shrink noisy/large context before pasting it into the conversation.
context-prime
Prime Claude with comprehensive project understanding.
archcore-context
Archcore knowledge base context — document types, MCP tools, and conventions for working with .archcore/ documents.
context-management
Context window management — prevents AI from losing track during long sessions.
search-routing
Smart Search Routing — always use QMD semantic search when available, never bypass with grep for vault content.
demo-consume-context
Worked example that discovers, loads, and tags a context package per CONSUMING-CONTEXT-PACKAGE.md, then writes a reverse-index addendum — proves the produce/consume/tag loop end-to-end. Do NOT use for real feature work.