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/21pounder/terminalagent/claude-mdgit clone --depth 1 https://github.com/21pounder/terminalAgentWrote 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.
[](https://agentmods.dev/instructions/21pounder/terminalagent/claude-md)<a href="https://agentmods.dev/instructions/21pounder/terminalagent/claude-md"><img src="https://agentmods.dev/badge/instructions/21pounder/terminalagent/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01616 | $0.01616 |
| Opus 5 | $0.00808 | $0.00808 |
| Sonnet 5 | $0.00323 | $0.00323 |
| Haiku 4.5 | $0.00162 | $0.00162 |
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 5d 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.
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
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.
- 5d ago First seen · 155 lines · 1,616 tokens per session scan A 7c7b3891ca25
terminalAgent CLAUDE.md is an instructions file published in the GitHub repository 21pounder/terminalAgent (120 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 1,616 tokens to every session, about $0.0081 per session on Opus 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.
Other instructions, from other repositories
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.