agentmods.dev

claude-tui AGENTS.md

claude-tui AGENTS.md is an instructions file for Codex, OpenCode from slima4/claude-tui. It costs 546 tokens per session, scanned B, original, MIT.

Project guidance for ClaudeTUI, a collection of command-line utilities for Claude Code, including monitoring, status display, and terminal controls.

In plain words
What is it for?
It helps run the monitor and sniffer tests, operate the command dispatcher, change status-bar modes, handle API rate limits, and avoid the uninstall command's repository deletion behavior.
Why use it?
It records the commands, tests, shared data locations, and known risks needed to develop and maintain the utilities safely.

Instructions file for CodexOpenCode

not rated 41 yesterday B scan 546 tokens original MIT
View the source file slima4/claude-tui
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/slima4/claude-tui/agents-md
Clone the repo
git clone --depth 1 https://github.com/slima4/claude-tui

Made for: Codex, OpenCode.

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 AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/slima4/claude-tui/agents-md.svg)](https://agentmods.dev/instructions/slima4/claude-tui/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/slima4/claude-tui/agents-md"><img src="https://agentmods.dev/badge/instructions/slima4/claude-tui/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 546 This file is loaded in full into every session.
When invoked 546 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.00546 $0.00546
Opus 5 $0.00273 $0.00273
Sonnet 5 $0.00109 $0.00109
Haiku 4.5 $0.00055 $0.00055

Measured 4d ago against content hash bad6fb492cc7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

claude-tui AGENTS.md scanned grade B 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 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.

Reads agent configuration directoriesmediumAgent snooping

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

Test tools directly without modifying `~/.claude/settings.json`:
AGENTS.md · 51 lines

What it actually says

AGENTS.md

Quick Commands

python3 claudetui.py monitor         # test monitor
python3 claudetui.py chart           # test efficiency chart
python3 claudetui.py mode custom      # test configurator TUI
python3 claudetui.py --help           # test dispatcher
python3 claude-code-monitor/test_monitor.py -v   # monitor tests
python3 claude-code-sniffer/test_sniffer.py -v   # sniffer tests
PYTHONPATH=. python3 claude_tui_core/test_core.py -v   # core tests

Testing

Only two tools have tests: monitor and sniffer. Run both before/after refactoring.

Gotchas (hard-won knowledge)

  • python3 claudetui.py uninstall removes the repo directory! Use with caution - it deletes the git repo folder

  • Usage API rate limiting: The OAuth usage API frequently returns 429 errors. claude_tui_core/network.py handles exponential backoff (2min → 4min → 8min) and preserves cache.

  • Model Data: Centralized in claude_tui_core/models.py. Keep in sync when updating pricing.

  • Status Page / Usage: Centralized logic in claude_tui_core/network.py.

  • Widget API: widget_fn(frame, ratio) -> list[str] must return exactly 3 rows.

Local Development

Test tools directly without modifying ~/.claude/settings.json:

python3 claudetui.py monitor
python3 claudetui.py chart

To test statusline locally, edit ~/.claude/settings.json to point to your repo path instead of installed path.

Release

  1. Bump _FALLBACK_VERSION in claudetui.py
  2. Commit, tag (git tag v0.X.Y), push with --tags

Key Files

  • Entry point: claudetui.py (routes subcommands to tools)
  • Shared UI Library: claude_tui_components/ (holds build_progress_bar, build_sparkline, ANSI colors, string utils)
  • Shared Logic Core: claude_tui_core/ (models, network, settings/hot-reload)
  • Each tool in its own directory, self-contained with README
  • Config: ~/.claude/claudeui.json (hot-reloads, no restart needed)
  • Tests: claude_tui_core/test_core.py (unit tests for core library)
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 · 51 lines · 546 tokens per session scan B bad6fb492cc7

Subscribe to this mod's changes

claude-tui AGENTS.md is an instructions file published in the GitHub repository slima4/claude-tui (41 stars, last pushed yesterday), licensed MIT. It adds 546 tokens to every session, about $0.0027 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Testingai-toolsclaudeclaude-codecli-toolsdeveloper-tools
Related

Other instructions, from other repositories

plan-critique-skills CLAUDE.md

Instructions for serbanghita/plan-critique-skills, covering project standards, architecture, code style, versioning and releases and documentation.

serbanghita/plan-critique-skills · 1,048 tokens

ohmyzsh-ai-cli-plugins CLAUDE.md

Instructions for gravtice/ohmyzsh-ai-cli-plugins, covering claude.md, project overview, language guidelines, core architecture and plugin structure pattern.

gravtice/ohmyzsh-ai-cli-plugins · 1,579 tokens

AIPlugHub CLAUDE.md

Instructions for ThanhWilliamLe/AIPlugHub, covering 7a-app — application source code, contributing hats, as developer, what belongs here and what does not belong here.

ThanhWilliamLe/AIPlugHub · 319 tokens

claude-code-optimizer CLAUDE.md

Claude Code instructions for carlosduplar/claude-code-optimizer, covering communication, principles, verification protocol, workflow and documentation.

carlosduplar/claude-code-optimizer · 271 tokens

keepup-ai-tools CLAUDE.md

Claude Code instructions for liuqi1024/keepup-ai-tools, covering keepup-ai-tools, 项目结构, 技术要点, 版本规范 and ci.

liuqi1024/keepup-ai-tools · 454 tokens

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

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

PIsberg/vibetags · 82 tokens