What is 1code CLAUDE.md?

Project instructions for 1Code, a desktop app that provides AI help with local software projects.

Use them when planning or implementing substantial changes in the 1Code repository, including new features, architecture changes, or security work.

They tell an AI coding assistant when to read the project's proposal rules and which development commands and conventions to follow.

1code CLAUDE.md — Instructions file by 21st-dev

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/21st-dev/1code/claude-md

Clone the repo

git clone --depth 1 https://github.com/21st-dev/1code

Per session 2,703 This file is loaded in full into every session.

When invoked 2,703 The same file — it is already loaded in full.

Security scan D 3 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	$0.02703	$0.02703
Opus 5	$0.01352	$0.01352
Sonnet 5	$0.00541	$0.00541
Haiku 4.5	$0.00270	$0.00270

Measured 2d ago against content hash 42b8690b2757, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

1code CLAUDE.md scanned grade D with 3 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

fetch('http://localhost:7799/log',{method:'POST',headers:{'Content-Type':'application/json'},body:JSON.stringify({tag:'TAG',msg:'MESSAGE',data:{},ts:Date.now()})}).catch(()=>{});

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf ~/Library/Application\ Support/Agents\ Dev/

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**Clear logs:** `curl -X DELETE http://localhost:7799/logs`

CLAUDE.md · 275 lines

How it starts

The opening of the file, as written. The whole thing — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenSpec Instructions

These instructions are for AI assistants working in this project.

Always open @/openspec/AGENTS.md when the request:

Mentions planning or proposals (words like proposal, spec, change, plan)
Introduces new capabilities, breaking changes, architecture shifts, or big performance/security work
Sounds ambiguous and you need the authoritative spec before coding

Use @/openspec/AGENTS.md to learn:

How to create and apply change proposals
Spec format and conventions
Project structure and guidelines

Keep this managed block so 'openspec update' can refresh the instructions.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What is this?

21st Agents - A local-first Electron desktop app for AI-powered code assistance. Users create chat sessions linked to local project folders, interact with Claude in Plan or Agent mode, and see real-time tool execution (bash, file edits, web search, etc.).

Commands

# Development
bun run dev              # Start Electron with hot reload

# Build
bun run build            # Compile app
bun run package          # Package for current platform (dir)
bun run package:mac      # Build macOS (DMG + ZIP)
bun run package:win      # Build Windows (NSIS + portable)
bun run package:linux    # Build Linux (AppImage + DEB)

# Database (Drizzle + SQLite)
bun run db:generate      # Generate migrations from schema
bun run db:push          # Push schema directly (dev only)

Architecture

src/
├── main/                    # Electron main process
│   ├── index.ts             # App entry, window lifecycle
│   ├── auth-manager.ts      # OAuth flow, token refresh
│   ├── auth-store.ts        # Encrypted credential storage (safeStorage)
│   ├── windows/main.ts      # Window creation, IPC handlers
│   └── lib/
│       ├── db/              # Drizzle + SQLite
│       │   ├── index.ts     # DB init, auto-migrate on startup
│       │   ├── schema/      # Drizzle table definitions
│       │   └── utils.ts     # ID generation
│       └── trpc/routers/    # tRPC routers (projects, chats, claude)
│
├── preload/                 # IPC bridge (context isolation)
│   └── index.ts             # Exposes desktopApi + tRPC bridge
│
└── renderer/                # React 19 UI
    ├── App.tsx              # Root with providers
    ├── features/
    │   ├── agents/          # Main chat interface
    │   │   ├── main/        # active-chat.tsx, new-chat-form.tsx
    │   │   ├── ui/          # Tool renderers, preview, diff view
    │   │   ├── commands/    # Slash commands (/plan, /agent, /clear)
    │   │   ├── atoms/       # Jotai atoms for agent state
    │   │   └── stores/      # Zustand store for sub-chats
    │   ├── sidebar/         # Chat list, archive, navigation
    │   ├── sub-chats/       # Tab/sidebar sub-chat management
    │   └── layout/          # Main layout with resizable panels
    ├── components/ui/       # Radix UI wrappers (button, dialog, etc.)
    └── lib/
        ├── atoms/           # Global Jotai atoms
        ├── stores/          # Global Zustand stores
        ├── trpc.ts          # Real tRPC client
        └── mock-api.ts      # DEPRECATED - being replaced with real tRPC

Read the full file on GitHub · 275 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 · 275 lines · 2,703 tokens per session scan D 42b8690b2757

Subscribe to this mod's changes

1code CLAUDE.md is an instructions file published in the GitHub repository 21st-dev/1code (5,600 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 2,703 tokens to every session, about $0.0135 per session on Opus 5. A static security scan graded it D with 3 findings (sends data to an external url, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Planning Security

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

1code CLAUDE.md