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/coding-standards-demo.crux)<a href="https://agentmods.dev/rules/zotoio/crux-compress/coding-standards-demo.crux"><img src="https://agentmods.dev/badge/rules/zotoio/crux-compress/coding-standards-demo.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/coding-standards-demo.crux"><img src="https://agentmods.dev/badge/rules/zotoio/crux-compress/coding-standards-demo.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 | $0.00006 | $0.00937 |
| Opus 5 | $0.00003 | $0.00468 |
| Sonnet 5 | $0.00001 | $0.00187 |
| Haiku 4.5 | $0.00001 | $0.00094 |
Grade A, and why
coding-standards-demo.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 9d 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!
Team Coding Standards and Best Practices
⟦CRUX:coding-standards-demo.md
Ρ{team coding standards+best practices}
Κ{
fn=function; cls=class; var=variable;
JS=JavaScript; TS=TypeScript; Py=Python
}
R.philosophy{
readable≻clever; code→humans first;
∀code→read many×>write 1×
}
R.boyscout{
leave code≥found; touch file→cleanup minor;
¬scope-creep; big refactor→separate ticket
}
R.naming{
vars+fns=descriptive+self-doc; ¬single-letter[except short loops];
JS/TS{var+fn=camelCase; cls=PascalCase; const=SCREAMING_SNAKE};
Py{var+fn=snake_case; cls=PascalCase};
bool→prefix[is|has|can|should];
files{JS/TS=kebab-case; Py=snake_case};
dir=lowercase+hyphens; 1file→1responsibility
}
R.structure{
fn.len≤20..30ln; 1fn→1thing;
nesting≤3levels→use early return|extract fn;
comments→"why"¬"what"
}
R.docs{
∀public[API|cls|fn]→doc comments;
include=[desc,params+types,return,examples?,exceptions?]
}
R.errors{
¬swallow!→log|handle|rethrow;
custom err types→precise handling+debug;
err.msg∋[op failed,expected,actual,IDs,ctx]
}
R.test{
∀new code→tests; cov≥80%⊕meaningful;
name="should [behavior] when [condition]";
pattern=AAA[Arrange→Act→Assert];
mock=[external APIs,DB,filesystem,time]; ¬mock=[unit tested,utils,data structs]
}
R.git{
commit=conventional{type(scope):desc};
types=[feat,fix,docs,style,refactor,test,chore];
branch=[feature/,fix/,refactor/,docs/]+desc; +ticket#?;
PR{title clear,desc what+why,ref issues,small+complete,tests,CI pass}
}
R.security{
¬commit[API keys,secrets,passwords,creds,private keys,PII]!;
use env vars+secret mgmt;
∀input→validate[type,format,range]+sanitize;
DB→parameterized queries; output→encode[XSS];
auth→check before op; use established libs; rate limit; secure sessions
}
R.perf{
DB{¬N+1→eager load; +indexes; paginate; profile slow};
cache{expensive ops+external API; TTL→volatility; invalidation; warming};
frontend{lazy load; optimize images; min bundle; code split}
}
R.deps{
before add→check[maintained?,bundle size?,vulns?,existing alt?];
doc major deps in README;
prod→pin exact ver; libs→ver ranges;
update regularly; monitor vulns
}
R.review{
author{self-review first; PR small+focused; ctx in desc; feedback→constructive};
reviewer{respectful; explain reasoning; required≠suggestions; approve when good enough}
}
R.logging{
log=[startup,shutdown,auth events,biz-critical ops,errors+ctx,perf metrics];
¬log=[sensitive data,high-freq spam,redundant];
levels{ERROR=failed+attention; WARN=unexpected+recoverable;
INFO=normal biz; DEBUG=detailed; TRACE=very detailed}
}
Ω{
standards=living doc→update as team grows;
goal=better code together¬bureaucracy;
?doubt→ask colleague
}
⟧
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.
- 9d ago First seen · 116 lines · 6 tokens per session scan A 247ef70831ca
coding-standards-demo.crux is a cursor rule published in the GitHub repository zotoio/CRUX-Compress (8 stars, last pushed 2d ago), licensed MIT. It adds 6 tokens to every session and 937 once invoked, about $0.0000 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
swift6-migration
Guide for migrating Swift code to Swift 6 with concurrency and strict checking.
swift-argument-parser
Documentation and usage patterns for Swift Argument Parser for command-line tools.
swift-testing-playbook
Comprehensive guide for migrating from XCTest to Swift Testing with best practices from WWDC 2024.
swift-observation
Swift Observation framework documentation and usage patterns for reactive programming.
swift-observable
Migration guide for updating SwiftUI apps from ObservableObject to the @Observable macro.
screenshot-automation
Reusable AppleScript patterns for automated screenshot capture for documentation and testing.