What is FerrisScope CLAUDE.md?

Repository-specific instructions for Claude Code, the coding assistant, when changing FerrisScope. They document naming, architecture, conventions, and build practices.

Use them when adding features, editing Rust or Tauri code, working with Kubernetes data, or preparing FerrisScope changes for release.

They reduce the risk of breaking design rules or changing established names and behavior by mistake.

How dzcorp/FerrisScope configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to dzcorp/FerrisScope. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/dzcorp/FerrisScope/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/dzcorp/FerrisScope

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/dzcorp/ferrisscope/claude-md/github.svg)](https://agentmods.dev/instructions/dzcorp/ferrisscope/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/dzcorp/ferrisscope/claude-md"><img src="https://agentmods.dev/badge/instructions/dzcorp/ferrisscope/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/dzcorp/ferrisscope/claude-md"><img src="https://agentmods.dev/badge/instructions/dzcorp/ferrisscope/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 14,135 This file is loaded in full into every session.

When invoked 14,135 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.14135	$0.14135
Opus 5.5	$0.05654	$0.05654
Sonnet 5.5	$0.02827	$0.02827
Haiku 4.5	$0.01413	$0.01413

Measured 5d ago against content hash ed1d965ef192, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

FerrisScope 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 5d 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.

CLAUDE.md · 365 lines

How it starts

The opening of the file, as written. The whole thing — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Operating notes for Claude Code working in this repo. The user-facing pitch, install, layout, and build instructions live in README.md. This file is the how — rules, conventions, and recipes specific to changing the codebase.

Naming — don't "fix" these

The display name is FerrisScope (mixed case). Everything technical stays lowercase: crates (ferrisscope-core, ferrisscope-kube-ext, ferrisscope-agent, ferrisscope-app), the binary ferrisscope, the Tauri identifier dev.ferrisscope.desktop (Tauri 2 warns against an .app suffix on macOS), disk paths under ~/.config/ferrisscope/, and the SSA field manager constant "ferrisscope" (fetch::FIELD_MANAGER).

The core crate must stay Tauri-free so a future TUI / CLI can reuse the engine. If you're adding tauri to core/Cargo.toml, stop and reconsider.

Hard architectural rules

One reflector per (cluster, resource_kind). Never start a second watch for data already cached.
Reflectors are lazy — started on first subscribe, torn down a few seconds after the last unsubscribe.
Frontend is a mirror, not a source of truth. All canonical state lives in Rust.
A "cluster" owns a task supervisor. Disconnecting aborts the supervisor — no orphaned tasks, no leaked sockets.
Frontend business logic budget is near zero. View state in Zustand; everything else over Tauri commands.

Think it through before shipping

When asked to build, fix, or improve something, actively look for ways it can break before reporting done. Don't stop at "the happy path compiles."

Walk the failure modes. Empty / missing / malformed input. Concurrency and cancellation. Who frees the resource. 403/404/409/410 from the apiserver. Long names, missing namespace, disconnected cluster, stale reflector.
Fix root causes, not symptoms. For bugs, ask why the bad state became reachable before patching where it surfaced. Add a regression test.
Finish the loop. Loading, empty, error, and stale states are part of the feature — a button with no disabled state during in-flight work is unfinished.
Surface what you didn't cover. Wrong assumptions, untested UI paths, related bugs you spotted — name them in the response rather than implying success.

Read the full file on GitHub · 365 lines

Changes

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.

5d ago Changed · +25 lines · +2,430 tokens per session ed1d965ef192
1mo ago Changed · +28 lines · +1,913 tokens per session 436a5b7ea0a8
1mo ago Changed · +8 lines · +615 tokens per session b64c70b3e1b3
1mo ago Changed · +26 lines · +1,105 tokens per session 6e2082cc6bc0
2mo ago First seen · 278 lines · 8,072 tokens per session scan A 22b916235d3d

Subscribe to this mod's changes

FerrisScope CLAUDE.md is an instructions file published in the GitHub repository dzcorp/FerrisScope (22 stars, last pushed 2d ago), licensed Apache-2.0. It adds 14,135 tokens to every session, about $0.0565 per session on Opus 5.5. 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.

FerrisScope CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
FerrisScope CLAUDE.mddzcorp/FerrisScope	Instructions file	22	2d ago	Apache-2.0	A	14,135	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

FerrisScope: Instructions file for Claude Code