agentmods.dev

claude-tui: Instructions file for Claude Code

CLAUDE.md

claude-tui CLAUDE.md is an instructions file for Claude Code from slima4/claude-tui. It costs 3,334 tokens per session, scanned B, original, MIT.

Project instructions and utilities for Claude Code, including a command-line launcher, status bar, and terminal interface for session information.

In plain words
What is it for?
It helps maintain the repository's tools, run their tests, install or remove them, and show information such as context usage, tokens, cost, duration, and rate limits.
Why use it?
It keeps Claude Code aware of this repository's structure and provides commands for viewing session details and changing status-bar displays.

Instructions file for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is slima4/claude-tui's own configuration. It tells Claude Code how to work on claude-tui itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-tui configures →

not rated 45repo changed 1mo ago B scan 3,334 tokens original MIT
View source ↗ slima4/claude-tui slima4.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to slima4/claude-tui. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/slima4/claude-tui/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/slima4/claude-tui

Made for: Claude Code.

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 claude-tui CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/slima4/claude-tui/claude-md/github.svg)](https://agentmods.dev/instructions/slima4/claude-tui/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/slima4/claude-tui/claude-md"><img src="https://agentmods.dev/badge/instructions/slima4/claude-tui/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for claude-tui CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/slima4/claude-tui/claude-md"><img src="https://agentmods.dev/badge/instructions/slima4/claude-tui/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,334 This file is loaded in full into every session.
When invoked 3,334 The same file — it is already loaded in full.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.03334 $0.03334
Opus 5.5 $0.01334 $0.01334
Sonnet 5.5 $0.00667 $0.00667
Haiku 4.5 $0.00333 $0.00333

Measured 1mo ago against content hash 0b95cc063c47, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

claude-tui CLAUDE.md scanned grade B 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 1mo 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- `install.sh` / `uninstall.sh` — Configures `~/.claude/settings.json` (statusLine, hooks), installs commands to `~/.claude/commands/tui/`, symlinks `claudetui` to PATH.

Makes network callslowCapability

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

Version is auto-detected from git tags at runtime; fallback used for curl/brew installs.
CLAUDE.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 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.

Project Overview

ClaudeTUI is a collection of standalone utilities for Claude Code. Each tool lives in its own subdirectory with its own README.

Top-Level Scripts

  • claudetui.py — CLI dispatcher. Routes all claudetui * subcommands to the correct tool. Detects version from git tags, falls back to _FALLBACK_VERSION. Also implements the sniff launcher (auto-detects sniffer port, sets ANTHROPIC_BASE_URL, execs claude).
  • claude-ui-mode.py — Statusline mode switcher. claudetui mode full|compact|custom. The custom subcommand launches a curses TUI for toggling components.
  • install.sh / uninstall.sh — Configures ~/.claude/settings.json (statusLine, hooks), installs commands to ~/.claude/commands/tui/, symlinks claudetui to PATH.

Tools

claude-code-statusline

Real-time status bar for Claude Code. Single-file script.

  • Entry point: claude-code-statusline/statusline.py
  • Reads session JSON from stdin (provided by Claude Code's statusLine feature)
  • Context size, used tokens, session cost, duration, and rate-limit usage are read directly from the stdin JSON (context_window.*, cost.*, rate_limits.*) — not recomputed
  • Parses the transcript JSONL file only for what stdin does not provide: compaction events, tool calls, errors, turns, cache ratio, thinking blocks, and context history/growth
  • Three modes: full (3-line), compact (1-line), custom (configurable). Switch via claudetui mode
  • Custom config: ~/.claude/claudeui.json under "custom" key, with is_visible(line, component) helper
  • Pluggable widget system (3x7 grid): matrix, hex, bars, progress, none
  • Context window size: read from stdin context_window.context_window_size
  • Context fill ratio: uses stdin context_window.used_percentage (Claude's input-only figure, matches /context); falls back to tokens / limit when it's null (early session, post-compact)
  • Terminal width: read from the COLUMNS env var Claude Code sets (stdout is captured, so ioctl/tput cannot detect it)
  • install.sh sets refreshInterval on the statusLine config so duration, rate-limit reset countdowns, and git state stay fresh while the session is idle
  • Rate-limit usage (5h / 7d): read from stdin rate_limits (Pro/Max only); no OAuth call from the statusline
  • Compaction prediction: fixed 33k buffer model (context_limit - COMPACT_BUFFER), not percentage-based
  • Progress bar: smooth true-color RGB gradient (_lerp_rgb) across 5 color stops (green→teal→yellow→peach→pink); percentage color scales relative to compaction ceiling

Read the full file on GitHub · 202 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. 1mo ago Changed · +6 lines · +241 tokens per session 0b95cc063c47
  2. 1mo ago First seen · 196 lines · 3,093 tokens per session scan B d7961d813a16

Subscribe to this mod's changes

claude-tui CLAUDE.md is an instructions file published in the GitHub repository slima4/claude-tui (45 stars, last pushed 1mo ago), licensed MIT. It adds 3,334 tokens to every session, about $0.0133 per session on Opus 5.5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Codeai-toolsclaudecli-toolsdeveloper-tools
Related

Other instructions, from other repositories

vibetags com-example-config-AsyncTestConfig.instructions.md

Instructions for PIsberg/vibetags, covering copilot instructions for asynctestconfig and immutable type.

PIsberg/vibetags · 82 tokens

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 · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens