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.
npx agentmods add instructions/hyprmcp/jetski/claude-mdgit clone --depth 1 https://github.com/hyprmcp/jetskiWrote 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/instructions/hyprmcp/jetski/claude-md)<a href="https://agentmods.dev/instructions/hyprmcp/jetski/claude-md"><img src="https://agentmods.dev/badge/instructions/hyprmcp/jetski/claude-md.svg" alt="Measured on agentmods" 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 | $0.01374 | $0.01374 |
| Opus 5 | $0.00687 | $0.00687 |
| Sonnet 5 | $0.00275 | $0.00275 |
| Haiku 4.5 | $0.00137 | $0.00137 |
Grade A, and why
jetski CLAUDE.md 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 6d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Development Commands
Basic Development
npm startorng serve- Start development server on http://localhost:4200npm run buildorng build- Build for production (outputs todist/)npm run watchorng build --watch --configuration development- Build in watch mode for developmentnpm testorng test- Run unit tests with Karma
Angular CLI Commands
ng generate component <name>- Generate new componentng generate service <name>- Generate new serviceng generate --help- List all available schematics
Architecture Overview
Framework & Stack
- Angular 20 with zoneless change detection (
provideZonelessChangeDetection()) - Standalone components architecture (no NgModules except for UI library)
- Spartan UI (@spartan-ng/brain) with Tailwind CSS for styling
- Lucide Angular for icons
- TypeScript with strict configuration
Project Structure
projects/ui/- UI application projectsrc/app/- Main application codeapp.ts- Root component with navigation and layoutapp.config.ts- Application configuration with providersapp.routes.ts- Route definitions with lazy-loaded pagescomponents/- Reusable UI componentspages/- Route-specific page components (dashboard, servers, monitoring, settings)services/- Application services (theme service)libs/ui/- Custom UI component library (Spartan UI components)
public/- Static assets
Key Architecture Patterns
- Bundle Loading: Two-bundle strategy with initial bundle and lazy-loaded authenticated bundle
- Authentication Guard: Routes are protected by an OAuth-based auth guard
- Signals: Uses Angular signals for reactive state management (see ThemeService)
- Standalone Components: All components are standalone, no NgModules needed
- Path Mapping: Custom UI components are mapped via tsconfig paths (
@spartan-ng/helm/button)
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.
- 6d ago First seen · 153 lines · 1,374 tokens per session scan A 1746d7e7d6c1
jetski CLAUDE.md is an instructions file published in the GitHub repository hyprmcp/jetski (211 stars, last pushed 4mo ago), licensed MIT. It adds 1,374 tokens to every session, about $0.0069 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 2026-08-30.
Other instructions, from other repositories
kubara AGENTS.md
AGENTS.md instructions for kubara-io/kubara, covering ai agent context, scope, product intent (stable), truth hierarchy and reference map.
rocketship AGENTS.md
Instructions for rocketship-ai/rocketship, covering agents.md, rocketship cloud v1 snapshot, architecture overview, development commands and build and install.
k8s4claw CLAUDE.md
Instructions for Prismer-AI/k8s4claw, covering claude.md, what this is, build & test commands, running a single test and pre-commit checklist.
rocketship CLAUDE.md
Instructions for rocketship-ai/rocketship, covering claude.md, rocketship cloud v1 snapshot (for agents), architecture overview, development commands and build and install.
kubara CLAUDE.md
Claude Code instructions for kubara-io/kubara, a project described as: kubara is a single binary CLI tool written in Go providing a lightweight framework for bootstrapping Kubernetes platforms with production-proven best practices.
ollama CLAUDE.md
Claude Code instructions for ollama/ollama: See AGENTS.md for the shared agent instructions for this repository.