# Horos

> Emit and verify an evidence-backed reading boundary over a repository. Classify token sinks (generated files, vendored trees, lockfiles, minified bundles, single-line blobs), write the deterministic boundary agents consult before reading, and print skeleton maps of Python, TypeScript, Go, C++, Solidity and Markdown for oriented reading. Use when a user names Horos or asks to cut the reading cost of a repository without rewriting its code. Never apply a boundary during security review.

## Facts
- Page: https://tashan.sh/capability/skill-wildcat-finance-horos
- tashan id: skill:wildcat-finance/horos
- Source: https://github.com/wildcat-finance/skills
- Type: skill
- Category: other
- tashan score: not scored (catalogued only — too little public evidence)
- Adoption: 9.0
- Upkeep: 100.0
- Freshness: 100.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- License: Apache-2.0
- Official: no

## Install

```sh
cp -r horos ~/.claude/skills/
```

## Security audit
Not scanned. We audit npm-published capabilities; this one has no npm package we can resolve, or has not reached the queue. This is not a clean bill of health.

---
Measured 2026-09-12 by tashan (https://tashan.sh) from public evidence. Scorer s5.