Mysti is a VS Code extension that lets multiple AI coding providers and agents work alone or together on software tasks, including collaborative brainstorming and solution synthesis. It is for developers who want to use providers such as Claude Code, Codex, Gemini, Copilot, or local models within a coding workspace. The catalogue instruction supports using Mysti's agent collaboration workflow.
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/deepmyst/mysti/claude-mdgit clone --depth 1 https://github.com/DeepMyst/MystiWrote 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/deepmyst/mysti/claude-md)<a href="https://agentmods.dev/instructions/deepmyst/mysti/claude-md"><img src="https://agentmods.dev/badge/instructions/deepmyst/mysti/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 5.1 | $0.03393 | $0.03393 |
| Opus 5 | $0.01697 | $0.01697 |
| Sonnet 5 | $0.00679 | $0.00679 |
| Haiku 4.5 | $0.00339 | $0.00339 |
Grade C, and why
Mysti CLAUDE.md scanned grade C with 2 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 6d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- `curl https://cursor.com/install -fsS | bash` (Cursor) Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `curl https://cursor.com/install -fsS | bash` (Cursor) How it starts
The opening of the file, as written. The whole thing — 251 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
Mysti is a VSCode extension providing a unified AI coding assistant interface supporting 12 AI backends (Claude Code, OpenAI Codex, Google Gemini, Cline, GitHub Copilot, Cursor, OpenClaw, OpenCode, Qwen Code, Ollama, LocalAI, and Manus). It features sidebar/tab chat panels, conversation persistence, multi-agent brainstorm mode (any 2 of 11 agents with 5 collaboration strategies), autonomous mode with safety classification, @-mention agent routing, permission controls, plan selection, context compaction, and a three-tier agent loading system for personas and skills.
Build Commands
npm run compile # Production build (webpack)
npm run watch # Development build with watch mode
npm run lint # ESLint check (src/**/*.ts)
npm run sync-agents # Sync plugins from wshobson/agents repo
npm run sync-agents:force # Force sync (ignores 24h cache)
npx vsce package # Package extension as .vsix
Output: dist/extension.js from entry point src/extension.ts (webpack bundles with ts-loader, target: node, CommonJS2).
Note: Tests are not yet implemented (npm run test exists but has no test files).
Development
Press F5 in VSCode to launch Extension Development Host for debugging. Set breakpoints in TypeScript files and filter Debug Console with [Mysti] for extension logs.
CLI requirements: At least one of these CLIs must be installed for the extension to function:
npm install -g @anthropic-ai/claude-code(Claude Code)npm install -g @google/gemini-cli(Gemini)npm install -g @github/copilot-cli(GitHub Copilot)- Codex CLI (OpenAI - follow their installation guide)
npm install -g cline(Cline)curl https://cursor.com/install -fsS | bash(Cursor)npm install -g openclaw@latest(OpenClaw)npm i -g opencode-ai@latest(OpenCode)npm install -g @qwen-code/qwen-code@latest(Qwen Code)- Ollama (install from ollama.com)
- LocalAI (install from localai.io)
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.
- 6d ago First seen · 251 lines · 3,393 tokens per session scan C 3d2d82b66b35
Mysti CLAUDE.md is an instructions file published in the GitHub repository DeepMyst/Mysti (1,137 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 3,393 tokens to every session, about $0.0170 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
puppyone AGENTS.md
Instructions for puppyone-ai/puppyone, covering puppyone (contextbase), connect, collaborate, platform and active development directories.
Meterless AGENTS.md
Instructions for Meterless/Meterless, covering agent instructions for meterless, routing table, isolation rule, repo-wide rules and non-coding agents.
obsidian-ai CLAUDE.md
Instructions for spencermarx/obsidian-ai, covering claude.md, project overview, build & development commands, architecture and key design decisions.
backend-pro-max-skill CLAUDE.md
Instructions for shashankswe2020-ux/backend-pro-max-skill, covering claude.md, project overview, search command, useful flags and domains.
harness-books CLAUDE.md
Claude Code instructions for wquguru/harness-books, a project described as: 📚 Two books on harness engineering — the design philosophies behind Claude Code & Codex: constraints, query loops, context governance, multi-agent verification. harness-books.agentway.dev.
arcanum-artifex copilot-instructions.md
Copilot instructions for MarieLynneBlock/arcanum-artifex, covering copilot instructions, project, working mode, agent quick start and standards.