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/cznorth/winkterm/claude-mdgit clone --depth 1 https://github.com/Cznorth/winktermWrote 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/cznorth/winkterm/claude-md)<a href="https://agentmods.dev/instructions/cznorth/winkterm/claude-md"><img src="https://agentmods.dev/badge/instructions/cznorth/winkterm/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 | $0.02439 | $0.02439 |
| Opus 5 | $0.01220 | $0.01220 |
| Sonnet 5 | $0.00488 | $0.00488 |
| Haiku 4.5 | $0.00244 | $0.00244 |
Grade A, and why
winkterm CLAUDE.md scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://localhost:8000/api/agent/handshake This is a copy
89% identical to winkterm AGENTS.md — 38 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 258 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
WinkTerm is an AI + terminal "human-machine fusion" ops tool. The AI and the user share the same pty session, and all interaction happens inside the terminal. The user talks to the AI by typing a # message; the AI can suggest commands and write them into the input line, where the user presses Enter to run or Backspace to edit.
Common Commands
Backend Development
cd backend
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install -r requirements.txt
# Start the development server
python -m uvicorn backend.main:app --reload --port 8000
Frontend Development
cd frontend
npm install
npm run dev # Development mode
npm run build # Build (output to frontend/out/)
npm run lint # Lint check
npm run gen:api # Generate TypeScript types and react-query hooks from OpenAPI
Desktop App Packaging
# Windows
build\build.bat
# Or run manually
pyinstaller build\winkterm.spec --clean --noconfirm
Docker Deployment
docker compose up -d
Architecture
Core Data Flow
User keyboard input
│
▼
Frontend Terminal (xterm.js)
│ WebSocket
▼
ws_handler.py
│
├── Normal input ──► pty_manager.write() ──► shell process
│
└── Lines starting with # ──► intercept ──► Agent (LangGraph)
Key Modules
| Module | Path | Responsibility |
|---|---|---|
| WebSocket handling | backend/terminal/ws_handler.py |
Message dispatch, # detection, Agent invocation |
| PTY management | backend/terminal/pty_manager.py |
Shell process wrapper, read/write, context retrieval |
| Session management | backend/terminal/session_manager.py |
Multi-terminal sessions, active state |
| Agent graph | backend/agent/graph.py |
LangGraph StateGraph definition |
| Agent tools | backend/agent/tools/ |
Terminal interaction tool definitions |
| SSH connections | backend/ssh/ |
SSH connection management, file transfer |
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 · 258 lines · 2,439 tokens per session scan A 853dc02f3e9f
winkterm CLAUDE.md is an instructions file published in the GitHub repository Cznorth/winkterm (20 stars, last pushed 1mo ago), licensed MIT. It adds 2,439 tokens to every session, about $0.0122 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 89% identical to winkterm AGENTS.md, differing in 38 lines, and is treated as a copy.
Other instructions, from other repositories
sshdesk AGENTS.md
Instructions for rylena/sshdesk, covering agent setup, scope, user-facing instruction, development setup and verification.
termcp CLAUDE.md
Claude Code instructions for open-mcp-ai/termcp, covering security & privacy, agent skills, issue tracker, triage labels and domain docs.
zashiki CLAUDE.md
Claude Code instructions for kounetsuman/zashiki, covering zashiki development conventions, comment conventions, testing, documentation (where design, specs, and context live) and issues vs. discussions.
GovOn AGENTS.md
AGENTS.md instructions for GovOn-Org/GovOn, covering govon repository instructions, 우선 문서, 브랜치 전략, 커밋과 pr and 현재 제품 방향.
GovOn copilot-instructions.md
Copilot instructions for GovOn-Org/GovOn, covering github copilot pr review instructions, review tag system, review criteria, report ([must] / [should] tags) and do not report.
codex-session-tui AGENTS.md
Instructions for avikalpa/codex-session-tui, covering agents.md, project purpose, current scope, architecture and safety rules.