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/fpindej/netrock/claude-mdgit clone --depth 1 https://github.com/fpindej/netrockWrote 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/fpindej/netrock/claude-md)<a href="https://agentmods.dev/instructions/fpindej/netrock/claude-md"><img src="https://agentmods.dev/badge/instructions/fpindej/netrock/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 | $0.02492 | $0.02492 |
| Opus 5 | $0.01246 | $0.01246 |
| Sonnet 5 | $0.00498 | $0.00498 |
| Haiku 4.5 | $0.00249 | $0.00249 |
Grade A, and why
netrock 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 4d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
NETrock - .NET 10 API (Clean Architecture) + SvelteKit frontend (Svelte 5), fully dockerized.
The backend API is the core of the project. It is a public-facing API designed to serve any client - multiple frontends, mobile apps, other backends, third-party integrations. The SvelteKit frontend is a fully functional reference client, not a throwaway. Treat every API change as if unknown consumers depend on it.
Frontend (SvelteKit :5173) → /api/* proxy → Backend API (.NET :8080) → PostgreSQL / MinIO
Backend layers: WebApi → Application ← Infrastructure → Domain + Shared
Hard Rules
Backend
Result/Result<T>for all fallible operations - never throw for business logicTimeProvider(injected) - neverDateTime.UtcNoworDateTimeOffset.UtcNow- C# 13
extension(T)syntax for new extension methods - Never
null!- fix the design instead ProblemDetails(RFC 9457) for all error responses - never anonymous objects or raw stringsinternalon all Infrastructure service implementations/// <summary>XML docs on all public and internal API surfaceSystem.Text.Jsononly - neverNewtonsoft.Json- NuGet versions in
Directory.Packages.propsonly - never in.csproj
Frontend
- Never hand-edit
v1.d.ts- runpnpm run api:generate - Svelte 5 Runes only - never
export let interface Props+$props()- never$props<{...}>()- Logical CSS only:
ms-*/me-*/ps-*/pe-*- neverml-*/mr-*/pl-*/pr-* - No
any- define proper interfaces - Feature folders in
$lib/components/{feature}/with barrelindex.ts - Use shadcn-svelte components (
pnpm dlx shadcn-svelte@latest add <name>) - never build what shadcn already provides - Pixel-perfect responsiveness - mobile, tablet, desktop, ultrawide, landscape and portrait
- Touch targets minimum 44px on all interactive elements
- Unified UX - reuse existing components and patterns so the app feels like one product, not five
- No overflow - dialogs, modals, and pages must never show scrollbars. Fit content to viewport.
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.
- 4d ago First seen · 158 lines · 2,492 tokens per session scan A 3e14ea568753
netrock CLAUDE.md is an instructions file published in the GitHub repository fpindej/netrock (231 stars, last pushed 5d ago), licensed MIT. It adds 2,492 tokens to every session, about $0.0125 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
fullstack-clean-architecture AGENTS.md
Instructions for aps08/fullstack-clean-architecture, covering agent & project guidelines, agent behavior rules, 🚀 quick commands, frontend (web/) and backend (server/).
fullstack-clean-architecture CLAUDE.md
Instructions for aps08/fullstack-clean-architecture: See @AGENTS.md for full technology guidelines, architecture, and coding standards.
openresto CLAUDE.md
Claude Code instructions for karanshukla/openresto, covering claude.md, commands, run everything (recommended for local dev), backend only and frontend only.
tutor-management-app CLAUDE.md
Instructions for t1112000/tutor-management-app, covering claude.md, commands, architecture, auth and page pattern.
dockside CLAUDE.md
Instructions for newsnowlabs/dockside, covering repo notes, the dockside cli, session setup, ad-hoc http checks and integration suite invocation (local mode).
tutor-management-app AGENTS.md
Instructions for t1112000/tutor-management-app, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.