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.
npx agentmods add instructions/ccchow/clawui/claude-mdgit clone --depth 1 https://github.com/ccchow/ClawUIWhat 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 | $0.03682 | $0.03682 |
| Opus 5 | $0.01841 | $0.01841 |
| Sonnet 5 | $0.00736 | $0.00736 |
| Haiku 4.5 | $0.00368 | $0.00368 |
Grade A, and why
ClawUI CLAUDE.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **User Agent calls REST API, not internal functions**: The User Agent runs a Claude CLI session that calls the same HTTP endpoints as the frontend via bash/curl. It does NOT import or call internal functions like `crea How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository. It's also a useful reference for contributors — see CONTRIBUTING.md for the full contributor guide.
Project Overview
ClawUI reads Claude Code session JSONL files from ~/.claude/projects/, visualizes them as vertical timelines, and provides interactive continuation via claude --resume -p. Uses a four-layer data model (see docs/DATA-MODEL.md). Also includes a Plan/Blueprint system for structured task decomposition and execution (see docs/PLAN-SYSTEM.md).
Commands
npm run dev # Start backend + frontend together (concurrently)
npm run dev:backend # Express on port 3001 (tsx watch)
npm run dev:frontend # Next.js on port 3000 (binds 127.0.0.1)
npm run build # Build all
npm run build:backend # TypeScript → dist/
npm run build:frontend # Next.js production build
npm run start:backend # Run compiled backend (node dist/index.js)
npm run lint # ESLint (backend only)
Tests use Vitest in both backend and frontend:
cd backend && npx vitest run # Backend tests
cd frontend && npx vitest run # Frontend tests
cd backend && npx tsc --noEmit # Type-check backend
cd frontend && npx tsc --noEmit # Type-check frontend
Architecture
Monorepo with npm workspaces: backend/ (Express) + frontend/ (Next.js).
Four-Layer Data Model
Layer 1 — Raw: ~/.claude/projects/**/*.jsonl (read-only source of truth)
Layer 2 — Index: .clawui/index.db (SQLite, incremental sync by mtime+size)
+ plans, plan_nodes tables (Plan system extension)
Layer 3 — Enrichment: .clawui/enrichments.json (stars, tags, notes, bookmarks)
Layer 4 — App State: .clawui/app-state.json (UI preferences, recent sessions)
Backend (backend/)
Express server on port 3001. ESM ("type": "module"), uses tsx watch for dev. See docs/BACKEND-ARCHITECTURE.md for detailed file descriptions and security patterns.
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 · 132 lines · 3,682 tokens per session scan A 1a78f5d39ca9
ClawUI CLAUDE.md is an instructions file published in the GitHub repository ccchow/ClawUI (3 stars, last pushed 5mo ago), licensed MIT. It adds 3,682 tokens to every session, about $0.0184 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
data-table-filters CLAUDE.md
Instructions for openstatusHQ/data-table-filters, covering claude.md, project overview, monorepo structure (pnpm + turborepo), key commands and database.
www-sacred AGENTS.md
Instructions for internet-development/www-sacred, covering agents.md, what this repo is, repo map, conventions and the fonts menu previews.
karakeep CLAUDE.md
Claude Code instructions for karakeep-app/karakeep, a project described as: A self-hostable bookmark-everything app (links, notes and images) with AI-based automatic tagging and full text search.
claude-code-tresor CLAUDE.md
Instructions for alirezarezvani/claude-code-tresor, covering claude.md - development guide, 🎯 repository purpose, 🏗️ architecture, 🛠️ common development commands and building & testing.
Codex-Skills AGENTS.md
Instructions for TheGoat395/Codex-Skills, covering repository operating notes, required checks, evidence rules and change hygiene.
sprawling AGENTS.md
Instructions for 2youg1/sprawling, covering agents.md — how work is done in this repository, the loop, read before you write, one change, five steps and the rules a machine holds.