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-integration.crux)<a href="https://agentmods.dev/rules/zotoio/crux-compress/crux-memories-integration.crux"><img src="https://agentmods.dev/badge/rules/zotoio/crux-compress/crux-memories-integration.crux/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-integration.crux"><img src="https://agentmods.dev/badge/rules/zotoio/crux-compress/crux-memories-integration.crux.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 | $0.00513 | $0.00513 |
| Opus 5 | $0.00257 | $0.00257 |
| Sonnet 5 | $0.00103 | $0.00103 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
crux-memories-integration.crux 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.
What it actually says
[!IMPORTANT] Generated file - do not edit!
CRUX Memories Integration Rule
⟦CRUX:crux-memories-integration.md
Ρ{CRUX Memories agent integration}
Κ{cfg=.crux/crux-memories.json; idx=.crux/memory-index.yml}
Φ.amnesia{/crux-amnesia=session override ≻ enableMemories;
suppress[discover,load,annotate,refs,dream-nudge]; ¬Δ cfg|files|trackers|idx;
subagents→inherit; explicit /crux-dream|recall|remember|meditate|forget→user intent OK}
Φ.enabled{enableMemories="true"→
discover: read idx→load likely matches(title|desc|tags);
MCP→semantic search ≻ idx scan;
⊛annotate: [memory:{title}] inline near influenced stmt!;
⊛annotate=load-bearing: ¬annotate→0refs ∧ ¬strength ∧ ¬REM signal ∧ stale-nudge;
⊛passthrough: subagent [memory:T]→parent MUST preserve verbatim in user-facing reply;
¬strip; recursive(any depth); paraphrase→copy [memory:…] alongside;
subagent omits literal syntax but mem identifiable via idx→parent adds annotation;
⊛self-check: pre-respond→mem influenced ∧ ¬annotated→add;
afterAgentResponse hook→auto .refs.yml tracking; ¬manual ref-tracker skill;
post-spec→suggest /crux-dream}
Φ.disabled{enableMemories="false"→skip all silently}
R.general{¬direct read|write→use skills; scope=base+own agent; repo-local;
dir=memories/ (cfg: cruxMemories.storage.memoriesDir)}
R.mcp{~/.cursor/mcp.json→{mcpServers:{crux-memories:{command:"crux-mcp-server",
args:["-t","stdio","--config",".crux/crux-memories.json"]}}}
MCP avail→semantic search ≻ linear idx scan}
⟧
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.
- 12d ago First seen · 48 lines · 513 tokens per session scan A 630c34fc94ed
crux-memories-integration.crux is a cursor rule published in the GitHub repository zotoio/CRUX-Compress (8 stars, last pushed 5d ago), licensed MIT. It adds 513 tokens to every session, about $0.0026 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.