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/minmaxflow/mini-kode/agents-mdgit clone --depth 1 https://github.com/minmaxflow/mini-kodeWhat 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 | $0.00631 | $0.00631 |
| Opus 5 | $0.00316 | $0.00316 |
| Sonnet 5 | $0.00126 | $0.00126 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
mini-kode AGENTS.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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mini-Kode - Development Guide
Technology Stack
- TypeScript - Static typing
- pnpm - Package management
- Bun - Runtime and build tool
- Ink - CLI UI with React
- OpenAI SDK - LLM integration
- Vitest - Testing framework
- Zod - Runtime type validation
- Commander - CLI framework
Architecture
Core Design
- Tool Pattern: All tools implement
Tool<Input, Output>interface - Concurrency: Readonly tools execute concurrently, writing tools sequentially
- Streaming: LLM responses stream progressively
- Permissions: Project-level + Session-level control
- Dual Mode: Interactive UI and non-interactive execution
Key Modules
- Tools (
src/tools/): Tool system with concurrency control - Permissions (
src/permissions/): Two-layer permission system - LLM (
src/llm/): Streaming client and tool integration - UI (
src/ui/): Ink-based CLI interface - Config (
src/config/): Multi-layer configuration system - Agent (
src/agent/): Core agent logic and session management
Development Commands
pnpm run dev # Development mode with file watching
pnpm run build # Build with Bun (output to dist/index.mjs)
pnpm run test # Run tests with Vitest
pnpm run lint # Type check with TypeScript
pnpm run format # Format code with Prettier
Code Style Guidelines
Import Organization
- Node.js built-in libraries (
fs,path,os,crypto) - Third-party libraries (
react,ink,chalk,zod,openai) - Relative file imports (
./types,../utils)
Each section separated by a blank line, alphabetically sorted within sections.
Code Formatting
- Use
pnpm run formatto format all TypeScript/TSX and Markdown files - Ensure all generated code follows import organization rules
- Run format command before committing changes
Comment Language
All comments must be in English for consistency.
Key Features
- Dual Mode Support: Interactive UI and non-interactive execution
- Flexible LLM Support: DeepSeek, OpenAI, and custom API providers
- Fine-grained Permissions: Project-level and session-level control
- Streaming Responses: Real-time output during execution
- Configuration Management: Multi-layer config with CLI commands
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 · 85 lines · 631 tokens per session scan A 112c3b7587a3
mini-kode AGENTS.md is an instructions file published in the GitHub repository minmaxflow/mini-kode (304 stars, last pushed 10mo ago), licensed MIT. It adds 631 tokens to every session, about $0.0032 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
seektty AGENTS.md
Instructions for Hilbert-beinghappy/seektty: This repository ships one out-of-tree DeepSeek Harness Bundle. Harness remains the only owner of Agent, Session, model, settings, permissions, Profile, plugin, and persistence state.
amp-acp AGENTS.md
Instructions for tao12345666333/amp-acp, covering agents.md, commands, architecture and code style.
roamcode AGENTS.md
Instructions for burakgon/roamcode, covering repository instructions for coding agents, public-repository safety, stable release and ota contract, releasing a stable version and ota changes.
dev-workspace AGENTS.md
Instructions for iwe-org/dev-workspace, covering agent operating manual, start of every session, the operating loop, conventions and iwe basics.
ob-1 AGENTS.md
Instructions for Overbrilliant/ob-1, covering agents.md, project index, stack, commands and key files.
kumo-coding-agent AGENTS.md
Instructions for kumo-ai/kumo-coding-agent: All instructions, routing tables, and rules are in CLAUDE.md. Read that file as the entry point for this agent.