What is kate-code CLAUDE.md?

Build and architecture instructions for Kate Code, a Kate text-editor plugin that connects the editor to Claude Code through a local protocol service. Kate is a desktop code editor, and the plugin adds an agent chat panel and editor tools.

Use them when building or modifying the Kate plugin, its Claude Code connection, chat interface, permission dialog, or editor-tool server.

They show how to compile, install, enable, and navigate the plugin's editor integration, communication layer, user interface, and built-in MCP server.

kate-code CLAUDE.md — Instructions file by undefinedopcode

Install

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.

agentmods

npx agentmods add instructions/undefinedopcode/kate-code/claude-md

Clone the repo

git clone --depth 1 https://github.com/undefinedopcode/kate-code

Per session 1,063 This file is loaded in full into every session.

When invoked 1,063 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.01063	$0.01063
Opus 5	$0.00531	$0.00531
Sonnet 5	$0.00213	$0.00213
Haiku 4.5	$0.00106	$0.00106

Measured 2d ago against content hash 661cf5e9d6b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kate-code 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 2d 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 · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kate-Code Plugin

A Kate text editor plugin that wraps Claude Code using claude-code-acp.

Build Instructions

cmake -B build -DCMAKE_BUILD_TYPE=Debug
cmake --build build

Installation

cmake --install build --prefix ~/.local

Then restart Kate and enable the plugin via: Settings > Configure Kate > Plugins > Enable "Kate Code"

Architecture

Layer Structure

Plugin: KateCodePlugin, KateCodeView - Kate integration
ACP: ACPService, ACPSession - JSON-RPC 2.0 over stdin/stdout to claude-code-acp
MCP: MCPServer - Built-in MCP server executable for Kate editor tools
UI: ChatWidget, ChatWebView, ChatInputWidget, PermissionDialog
Util: KDEColorScheme - reads ~/.config/kdeglobals

Key Files

src/plugin/KateCodePlugin.{h,cpp} - Plugin registration via K_PLUGIN_CLASS_WITH_JSON
src/plugin/KateCodeView.{h,cpp} - Creates side panel tool view, provides Kate context
src/acp/ACPService.{h,cpp} - QProcess-based claude-code-acp subprocess management
src/acp/ACPSession.{h,cpp} - Protocol flow and session state management
src/acp/ACPModels.h - Data structures (Message, ToolCall, TodoItem, etc.)
src/mcp/MCPServer.{h,cpp} - MCP protocol handler (initialize, tools/list, tools/call)
src/mcp/main.cpp - MCP server entry point (stdio JSON-RPC loop)
src/ui/ChatWidget.{h,cpp} - Main chat interface with ACP integration
src/ui/ChatWebView.{h,cpp} - QWebEngineView for HTML/CSS/JS rendering
src/ui/ChatInputWidget.{h,cpp} - Multiline text input with send button
src/ui/PermissionDialog.{h,cpp} - Modal dialog for tool approval requests
src/config/SettingsStore.{h,cpp} - QSettings + KWallet storage, ACPProvider management
src/config/KateCodeConfigPage.{h,cpp} - Kate config page with provider table, diff colors, summaries
src/util/KDEColorScheme.{h,cpp} - KDE color extraction from kdeglobals
src/web/chat.{html,css,js} - Web assets for chat interface
src/katecode.qrc - Qt resource file for web assets
src/katecode.json - KPlugin metadata

Read the full file on GitHub · 86 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.

2d ago First seen · 86 lines · 1,063 tokens per session scan A 661cf5e9d6b6

Subscribe to this mod's changes

kate-code CLAUDE.md is an instructions file published in the GitHub repository undefinedopcode/kate-code (20 stars, last pushed 5mo ago), licensed MIT. It adds 1,063 tokens to every session, about $0.0053 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.

Planning

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

buildNext

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 · 6,785 tokens

kate-code CLAUDE.md