agentmods.dev

youclaw CLAUDE.md

youclaw CLAUDE.md is an instructions file for coding agents from OtterMind/youclaw. It costs 1,627 tokens per session, scanned A, original, MIT.

Repository instructions for YouClaw, a desktop AI assistant built with a Tauri desktop shell, a Bun backend, and a React web interface.

In plain words
What is it for?
Use them to start development, run type checks and tests, build the desktop sidecar, or understand where the backend, frontend, database, scheduler, and agent code live.
Why use it?
They show how the desktop and web parts fit together and provide the commands used to develop, test, and build them.

Instructions file

not rated 724 4mo ago A scan 1,627 tokens original MIT
View the source file OtterMind/youclaw
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/ottermind/youclaw/claude-md
Clone the repo
git clone --depth 1 https://github.com/OtterMind/youclaw

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 youclaw CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ottermind/youclaw/claude-md.svg)](https://agentmods.dev/instructions/ottermind/youclaw/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ottermind/youclaw/claude-md"><img src="https://agentmods.dev/badge/instructions/ottermind/youclaw/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,627 This file is loaded in full into every session.
When invoked 1,627 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.

ModelPer sessionOnce invoked
Fable 5 $0.01627 $0.01627
Opus 5 $0.00813 $0.00813
Sonnet 5 $0.00325 $0.00325
Haiku 4.5 $0.00163 $0.00163

Measured 4d ago against content hash d67c7dbdd060, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

youclaw 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.

CLAUDE.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

YouClaw

Desktop AI assistant app, inspired by CLaude code.

Commands

bun dev              # Start backend dev mode (Bun)
bun dev:web          # Start frontend dev mode (Vite)
bun dev:tauri        # Start Tauri dev mode (Vite frontend + Bun backend + WebView, auto-opens DevTools)
bun start            # Production backend
bun typecheck        # TypeScript type check
bun test             # Run tests (bun test)
bun build:sidecar    # Compile Bun sidecar binary
bun build:tauri      # Build Tauri desktop app

Tech Stack

  • Runtime: Bun (backend sidecar + package manager)
  • Desktop Shell: Tauri 2 (Rust, window/tray/updater)
  • Backend: Hono (HTTP) + bun:sqlite (database) + Pino (logging)
  • Agent: @mariozechner/pi-coding-agent + @mariozechner/pi-ai
  • Frontend: Vite + React + shadcn/ui + Tailwind CSS
  • Validation: Zod (v4, import from zod/v4)
  • Scheduling: croner (cron expression parser)
  • Telegram: grammY
  • Config Format: YAML (yaml library)

Architecture

  • Desktop mode: Tauri (Rust shell) -> WebView loads frontend + Sidecar runs Bun backend
  • Web mode: Vite frontend + Bun backend deployed independently, frontend proxies API via Vite proxy
  • Dev mode: bun dev:tauri launches Vite frontend + Bun backend + Tauri WebView simultaneously (debug skips sidecar)
  • Build pipeline: bun build --compile compiles backend into single-file sidecar -> Vite compiles frontend embedded in Rust binary -> Tauri bundles DMG/MSI/AppImage
  • Frontend communicates with Bun backend uniformly via HTTP/SSE (same for desktop and web mode)
  • Port config: Rust reads port from Tauri Store -> injects PORT env var to sidecar; frontend reads port from the same Store to build baseUrl
  • Three-layer architecture: Entry layer (Telegram/Web/API) -> Core layer (AgentManager/Scheduler/Memory/Skills) -> Storage layer (SQLite/filesystem)
  • EventBus decouples Agent execution from multi-channel output
  • IPC Watcher uses filesystem polling for Agent <-> main process communication (scheduled task CRUD)

Read the full file on GitHub · 133 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. 4d ago First seen · 133 lines · 1,627 tokens per session scan A d67c7dbdd060

Subscribe to this mod's changes

youclaw CLAUDE.md is an instructions file published in the GitHub repository OtterMind/youclaw (724 stars, last pushed 4mo ago), licensed MIT. It adds 1,627 tokens to every session, about $0.0081 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.

aiai-agentclaudeclaude-codeopenclaw
Related

Other instructions, from other repositories

librefang AGENTS.md

AGENTS.md instructions for librefang/librefang, covering stack, layout, build, architecture and kernelhandle trait.

librefang/librefang · 2,087 tokens

autonomous-os AGENTS.md

AGENTS.md instructions for autonomous-ai/autonomous-os, covering agents.md, multi-ide rules, working style, parallel work / subagents and device access rules.

autonomous-ai/autonomous-os · 3,197 tokens

OneManCompany CLAUDE.md

Instructions for 1mancompany/OneManCompany, covering gstack and skill routing.

1mancompany/OneManCompany · 365 tokens

souls-directory CLAUDE.md

Instructions for thedaviddias/souls-directory, covering claude.md — project context for ai assistants, project overview, tech stack, critical rules and database is convex.

thedaviddias/souls-directory · 1,675 tokens

jentic-one GEMINI.md

Instructions for jentic/jentic-one: Otherwise, read AGENTS.md — this repo's canonical agent guidance.

jentic/jentic-one · 51 tokens

clawock AGENTS.md

AGENTS.md instructions for KCNyu/clawock, covering agents.md - your workspace, every session, kcn 偏好, git hook (one-time setup per clone) and git auto-commit rules.

KCNyu/clawock · 2,140 tokens