What is agent-view CLAUDE.md?

Project instructions for Agent View, a terminal interface for managing and monitoring AI coding-agent sessions. It describes a Bun and Solid.js application with SQLite storage and tmux-based session management.

Use it when developing Agent View, especially its session lifecycle, terminal screens, storage, Git worktrees, notifications, routes, or support for Claude Code and custom commands.

It gives an agent the project’s technology choices, structure, installation context, and main features before making changes. This reduces guesswork when working in the codebase.

agent-view CLAUDE.md — Instructions file by Frayo44

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/frayo44/agent-view/claude-md

Clone the repo

git clone --depth 1 https://github.com/Frayo44/agent-view

Per session 847 This file is loaded in full into every session.

When invoked 847 The same file — it is already loaded in full.

Security scan C 2 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	$0.00847	$0.00847
Opus 5	$0.00424	$0.00424
Sonnet 5	$0.00169	$0.00169
Haiku 4.5	$0.00085	$0.00085

Measured 3d ago against content hash ab2de1f1c3e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

agent-view CLAUDE.md scanned grade C with 2 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 3d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://raw.githubusercontent.com/frayo44/agent-view/main/install.sh | bash

Makes network callslowCapability

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

curl -fsSL https://raw.githubusercontent.com/frayo44/agent-view/main/install.sh | bash

CLAUDE.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent View

OpenTUI-based terminal interface for managing and monitoring AI coding agent sessions.

Tech Stack

Runtime: Bun
Framework: Solid.js
UI: OpenTUI (terminal UI framework)
Storage: SQLite (via bun:sqlite)
Session Management: tmux

Project Structure

src/
├── cli/           # CLI entry point
├── core/          # Core business logic
│   ├── git.ts     # Git/worktree utilities
│   ├── history.ts # History manager for autocomplete
│   ├── session.ts # Session lifecycle management
│   ├── storage.ts # SQLite storage layer
│   ├── tmux.ts    # tmux session control
│   └── types.ts   # TypeScript types
└── tui/           # Terminal UI
    ├── component/ # Reusable components (dialogs)
    ├── context/   # Solid.js contexts (theme, sync, routes)
    ├── routes/    # Page components (home, session)
    └── ui/        # Base UI components (dialog, toast, autocomplete)

Key Features

Session Management: Create, stop, restart, delete AI agent sessions
Tools: Claude Code, plus custom commands for anything else
Notifications: OS notifications via Claude Code hooks (src/core/hooks.ts, src/core/notify.ts) when an agent finishes or needs input
Git Worktrees: Create sessions in isolated git worktrees
Auto-suggestions: Fuzzy search for previously used paths and branch names
Status Monitoring: Real-time session status (running, waiting, idle, error)

Installation

Quick Install (Recommended)

curl -fsSL https://raw.githubusercontent.com/frayo44/agent-view/main/install.sh | bash

This will:

Install Bun if not present
Clone the repository to ~/.agent-view
Build the project
Create agent-view and av commands in ~/.local/bin

Manual Install

git clone https://github.com/frayo44/agent-view.git
cd agent-view
bun install
bun run build

Compile to Standalone Binary

bun run compile        # Compile for current platform
bun run compile:all    # Compile for all platforms (darwin/linux, x64/arm64)

Read the full file on GitHub · 101 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.

3d ago First seen · 101 lines · 847 tokens per session scan C ab2de1f1c3e8

Subscribe to this mod's changes

agent-view CLAUDE.md is an instructions file published in the GitHub repository Frayo44/agent-view (368 stars, last pushed 1mo ago), licensed MIT. It adds 847 tokens to every session, about $0.0042 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

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 · 6,785 tokens

agent-view CLAUDE.md