What is terminalAgent CLAUDE.md?

Repository instructions for Terminal Coding Agent, a command-line program that coordinates coding assistants and specialized agents. They explain its commands, file references, skills, routing, shared context, and execution modes.

Use them when developing or running the CLI, adding or invoking skills, attaching files, routing work to Reader, Coder, Reviewer, or Coordinator agents, and working with its different execution modes.

They clarify how the multi-agent tool is started and how its parts communicate. This prevents changes that conflict with its requirement to run Claude Code as a separate process.

How 21pounder/terminalAgent configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to 21pounder/terminalAgent. 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/21pounder/terminalAgent/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/21pounder/terminalAgent

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/21pounder/terminalagent/claude-md/github.svg)](https://agentmods.dev/instructions/21pounder/terminalagent/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/21pounder/terminalagent/claude-md"><img src="https://agentmods.dev/badge/instructions/21pounder/terminalagent/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/21pounder/terminalagent/claude-md"><img src="https://agentmods.dev/badge/instructions/21pounder/terminalagent/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,616 This file is loaded in full into every session.

When invoked 1,616 The same file — it is already loaded in full.

Security scan A 0 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.

Model	Per session	Once invoked
Fable 5.1	$0.01616	$0.01616
Opus 5.5	$0.00646	$0.00646
Sonnet 5.5	$0.00323	$0.00323
Haiku 4.5	$0.00162	$0.00162

Measured 2mo ago against content hash 7c7b3891ca25, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

terminalAgent 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 2mo 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 · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 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

Terminal Coding Agent (v5.0) is a CLI-based multi-agent coding assistant powered by the Claude Agent SDK. It wraps the SDK's query() function with a custom terminal UI featuring:

/ command menu for invoking Skills
@ file browser for attaching files to context
Smart routing to specialized agents (Reader, Coder, Reviewer, Coordinator)
Inter-agent communication via message bus and shared context
Multiple execution modes: single, parallel, react, coordinator

Important: The agent spawns Claude Code as a subprocess and cannot run inside Claude Code itself.

Commands

# From repo root
npm run install:all    # Install all dependencies (into deepresearch/)
npm run dev            # Development (tsx src/index.ts)
npm run build          # TypeScript compilation
npm start              # Run compiled output

# From deepresearch/ directory
npm run test:ui        # Test UI components

# Global CLI (after npm link in deepresearch/)
agent                  # Interactive mode
agent "your question"  # Single query
agent /commit          # Invoke a skill directly

Architecture

deepresearch/
├── src/
│   ├── index.ts                  # Main entry, input loop, runQuery/runCoordinator
│   ├── agents/                   # Agent classes
│   │   ├── base.ts               # BaseAgent abstract class (SDK integration)
│   │   ├── types.ts              # SubagentType, AgentConfig, AgentResult
│   │   ├── coordinator.ts        # Multi-agent dispatch, [DISPATCH:agent] parsing
│   │   ├── reader.ts             # Code reading and analysis
│   │   ├── coder.ts              # Code writing and modification
│   │   └── reviewer.ts           # Code review and quality checks
│   ├── core/
│   │   ├── router.ts             # Router class - keyword matching, skill→agent mapping
│   │   ├── session.ts            # Session management
│   │   └── permissions.ts        # Permission mode handling
│   ├── runtime/
│   │   ├── bus.ts                # MessageBus - inter-agent pub/sub communication
│   │   ├── shared.ts             # SharedContext - cross-agent state
│   │   ├── pool.ts               # AgentPool - task queue and parallel execution
│   │   ├── orchestrator.ts       # Orchestrator - execution mode coordination
│   │   └── react.ts              # ReAct executor for multi-step reasoning
│   ├── config/
│   │   ├── agents.ts             # AGENT_CONFIGS, AGENT_KEYWORDS, SKILL_AGENT_MAP
│   │   ├── constants.ts          # VERSION, MAX_SUBAGENT_DEPTH, DEFAULT_MODEL
│   │   └── tools.ts              # MCP_SERVERS configuration
│   ├── ui/
│   │   ├── smart-input.ts        # SmartInput - main input with "/" and "@" triggers
│   │   ├── commands.ts           # CommandPicker - arrow-key navigable "/" menu
│   │   ├── file-browser.ts       # FileBrowser - "@" file selection
│   │   └── theme.ts              # ANSI colors, icons, box drawing
│   ├── tools/
│   │   ├── message.ts            # MessageTool - agent messaging wrapper
│   │   ├── context.ts            # ContextTool - shared context wrapper
│   │   └── dispatch.ts           # Dispatch utilities
│   └── utils/
│       ├── prompt-loader.ts      # Loads agent prompts from .md files
│       ├── transcript.ts         # Session logging (text + JSON)
│       └── message-handler.ts    # SDK message processing
├── prompts/                      # Agent-specific system prompts (.md)
├── .claude/skills/               # Global Skills
├── bin/agent.cjs                 # Global CLI entry (CommonJS wrapper)
└── dist/                         # Build output

Read the full file on GitHub · 155 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.

2mo ago First seen · 155 lines · 1,616 tokens per session scan A 7c7b3891ca25

Subscribe to this mod's changes

terminalAgent CLAUDE.md is an instructions file published in the GitHub repository 21pounder/terminalAgent (116 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 1,616 tokens to every session, about $0.0065 per session on Opus 5.5. 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.

terminalAgent CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
terminalAgent CLAUDE.md21pounder/terminalAgent	Instructions file	116	5mo ago	Apache-2.0	A	1,616	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

terminalAgent: Instructions file for Claude Code