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/lmovse/agent-cli/claude-mdgit clone --depth 1 https://github.com/lmovse/agent-cliWhat 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 | $0.00681 | $0.00681 |
| Opus 5 | $0.00341 | $0.00341 |
| Sonnet 5 | $0.00136 | $0.00136 |
| Haiku 4.5 | $0.00068 | $0.00068 |
Grade A, and why
agent-cli 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 2d 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 — 73 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
This is an Obsidian plugin that embeds AI agent terminals (Claude CLI, Gemini CLI, Codex CLI, OpenCode CLI) directly into the Obsidian sidebar. It uses xterm.js for terminal rendering and a Python PTY bridge to spawn shell processes.
Build Commands
- Development:
npm run dev- Runs esbuild in watch mode for incremental builds - Production build:
npm run build- Runs TypeScript type check (tsc -noEmit -skipLibCheck) then esbuild production bundle
Architecture
The plugin follows a typical Obsidian plugin structure:
Obsidian App
├── src/
│ ├── AgentCLIPlugin (main.ts)
│ │ ├── Registers TerminalView as sidebar item
│ │ ├── Adds ribbon icon and commands
│ │ └── Manages settings persistence
│ ├── TerminalView (TerminalView.ts)
│ │ ├── Creates xterm.js terminal
│ │ ├── Spawns Python PTY process with agent command
│ │ ├── Handles terminal I/O streams
│ │ └── Auto-detects Obsidian dark/light theme
│ ├── SettingTab (SettingTab.ts)
│ │ └── Provides Obsidian settings UI
│ └── settings.ts
│ └── Defines settings interface and defaults
└── scripts/
└── pty_bridge.py
└── Embedded Python PTY bridge script
Key Implementation Details
PTY Bridge
The terminal connects to the AI agent via a Python PTY. The Python script (scripts/pty_bridge.py) is imported as a raw string via esbuild's ?raw loader and executed via python3 -c. It:
- Uses
pty.fork()to create a pseudo-terminal - Spawns
/bin/zshin the PTY - Writes the agent command to the PTY after a brief delay
- Uses
selectorsto multiplex stdin/stdout between xterm.js and the PTY
Settings Storage
Settings are persisted via Obsidian's loadData()/saveData() API. The default settings in settings.ts are merged with stored settings on load.
Terminal Theme Sync
The terminal detects Obsidian's theme by checking document.body.classList.contains('theme-dark') and applies corresponding colors to xterm.js.
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.
- 2d ago First seen · 73 lines · 681 tokens per session scan A 942a1d1801f4
agent-cli CLAUDE.md is an instructions file published in the GitHub repository lmovse/agent-cli (2 stars, last pushed 5mo ago), licensed MIT. It adds 681 tokens to every session, about $0.0034 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 2026-08-31.
Other instructions, from other repositories
claudian AGENTS.md
AGENTS.md instructions for YishenTu/claudian, covering agents.md, project, scope guides, agents.md maintenance and commands.
obsidian-agent-client AGENTS.md
AGENTS.md instructions for RAIT-09/obsidian-agent-client, covering agent client plugin - llm developer guide, architecture, data flow, acp event flow (single path) and permission flow.
obsidian-agent-client copilot-instructions.md
Copilot instructions for RAIT-09/obsidian-agent-client, covering github copilot instructions (obsidian-agent-client), big picture, key directories / “where to change things”, architectural rules (project-specific) and sessionupdate / tool-call update flow (critical).
obsidian-reminder CLAUDE.md
Instructions for uphy/obsidian-reminder, covering obsidian-reminder, language, commands, architecture and local development.
obsidian-claude-sidebar CLAUDE.md
Instructions for derek-larson14/obsidian-claude-sidebar, covering claude sidebar - agent guide, what this plugin does, two things you can help the user do, step 1: diagnose and step 2a: file a bug report.
vault-operator AGENTS.md
Instructions for pssah4/vault-operator, covering vault operator, projekt-regeln, navigation, zuerst lesen, projekt, tech stack and build und deploy.