flux9s: Instructions file for Claude Code

CLAUDE.md

flux9s CLAUDE.md is an instructions file for Claude Code from dgunzy/flux9s. It costs 5,020 tokens per session, scanned A, a copy of flux9s AGENTS.md, Apache-2.0.

Repository instructions for developing flux9s, covering its design principles, coding standards, error handling, testing, and Git restrictions. CLAUDE.md is a file that tells a coding agent how to work in a project.

In plain words
What is it for?
Use it while modifying flux9s code. It guides asynchronous operations, generated models, error reporting, command and keybinding changes, and the required continuous-integration check.
Why use it?
It gives the agent project-specific rules to follow and prevents unwanted commits, pushes, branches, or broad file restoration.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is dgunzy/flux9s's own configuration. It tells Claude Code how to work on flux9s itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything flux9s configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dgunzy/flux9s. 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/dgunzy/flux9s/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/dgunzy/flux9s

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.

agentmods badge for flux9s CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dgunzy/flux9s/claude-md/github.svg)](https://agentmods.dev/instructions/dgunzy/flux9s/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/dgunzy/flux9s/claude-md"><img src="https://agentmods.dev/badge/instructions/dgunzy/flux9s/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.

agentmods 80×15 button for flux9s CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dgunzy/flux9s/claude-md"><img src="https://agentmods.dev/badge/instructions/dgunzy/flux9s/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,020 This file is loaded in full into every session.
When invoked 5,020 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 100% copy Near-identical to another mod 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.05020 $0.05020
Opus 5.5 $0.02008 $0.02008
Sonnet 5.5 $0.01004 $0.01004
Haiku 4.5 $0.00502 $0.00502

Measured yesterday against content hash 22ff56725584, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

flux9s 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 yesterday.

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.

Origin

This is a copy

100% identical to flux9s AGENTS.md — 50 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 386 lines

How it starts

The opening of the file, as written. The whole thing — 386 lines — stays where its author put it; the contents beside it link to each section on GitHub.

flux9s Development Instructions

Core Philosophy

  • Zero-maintenance model updates: Use code generation over manual types
  • Non-blocking operations: Keep UI responsive with async task spawning
  • Graceful degradation: Log errors, don't crash (only panic for truly unrecoverable errors)
  • K9s alignment: Follow K9s conventions for keybindings and UX

Before You Start

  1. Run just ci after all changes (formats, lints, tests)
  2. Large changes require accompanying tests
  3. Keys and commands are data: add a key to the action table (src/tui/app/actions.rs) and a command to COMMAND_TABLE (src/tui/app/command_mode.rs) — dispatch, footer, and help all come from those entries. Never add a key arm elsewhere
  4. Git operations: User manages their own git workflow. Only use git to restore a single file when explicitly requested (e.g., git restore path/to/file). Never commit, push, create branches, or perform any other git operations

Code Standards

Error Handling

// ✅ Good - Add context to errors
api.patch(name, &params, &patch)
    .await
    .context(format!("Failed to suspend {}/{}", resource_type, name))?;

// ✅ Good - Log errors, return Result
if let Err(e) = operation() {
    tracing::warn!("Operation failed: {}", e);
    return Ok(()); // Continue execution
}

// ❌ Bad - Missing context
api.patch(name, &params, &patch).await?;

// ❌ Bad - Unwrap (use only in tests)
let value = result.unwrap();

State Management

  • Use Arc<RwLock<>> only when truly shared across threads
  • Prefer simple HashMap/Vec for single-threaded state
  • Keep App struct focused - extract complex state into sub-structs

Async Operations

// ✅ Good - Spawn tasks, use channels for results
let (tx, rx) = tokio::sync::oneshot::channel();
self.pending_rx = Some(rx);
tokio::spawn(async move {
    let result = operation().await;
    let _ = tx.send(result);
});

// Later, poll for results
if let Some(result) = app.try_get_result() {
    app.handle_result(result);
}

Read the full file on GitHub · 386 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.

  1. yesterday Changed · +26 lines · +549 tokens per session 22ff56725584
  2. 15d ago Changed · +15 lines · +311 tokens per session 2e4a4ffb557e
  3. 17d ago Changed · +43 lines · +758 tokens per session e082e6c83870
  4. 28d ago Changed · +1 lines · +122 tokens per session 0b99a39db36f
  5. 1mo ago First seen · 301 lines · 3,280 tokens per session scan A a8a43f4a34ee

Subscribe to this mod's changes

flux9s CLAUDE.md is an instructions file published in the GitHub repository dgunzy/flux9s (279 stars, last pushed yesterday), licensed Apache-2.0. It adds 5,020 tokens to every session, about $0.0201 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to flux9s AGENTS.md, differing in 50 lines, and is treated as a copy.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens