Borrowing it
Nothing to install: this file belongs to Prof-Harita/terminaI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Prof-Harita/terminaI/main/AGENTS.mdgit clone --depth 1 https://github.com/Prof-Harita/terminaIWrote 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/prof-harita/terminai/agents-md)<a href="https://agentmods.dev/instructions/prof-harita/terminai/agents-md"><img src="https://agentmods.dev/badge/instructions/prof-harita/terminai/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/prof-harita/terminai/agents-md"><img src="https://agentmods.dev/badge/instructions/prof-harita/terminai/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.08528 | $0.08528 |
| Opus 5.5 | $0.03411 | $0.03411 |
| Sonnet 5.5 | $0.01706 | $0.01706 |
| Haiku 4.5 | $0.00853 | $0.00853 |
Grade A, and why
terminaI AGENTS.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 1mo 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
| `child_process` | Command isolation | How it starts
The opening of the file, as written. The whole thing — 1,128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — The Definitive Guide for AI Agents
Purpose: This document is the single source of truth for AI agents working on TerminAI. Read this completely before making any changes.
Last Updated: January 21, 2026
Scope: All packages, all workflows, all agents
Table of Contents
- Project Identity
- Architecture Overview
- The Golden Rules
- Package Guide
- Development Workflows
- Code Standards
- Safety & Governance
- Testing Protocol
- Documentation Guidelines
- Upstream Maintenance
- Common Pitfalls
- Quick Reference
Project Identity
What is TerminAI?
TerminAI is an AI-powered system operator — not just a coding assistant.
┌─────────────────────────────────────────────────────────────────────┐
│ TERMINAI THESIS │
│ │
│ "Google provides the intelligence. │
│ TerminAI provides the root access and the guardrails." │
│ │
│ We are building GOVERNED AUTONOMY for systems and servers. │
└─────────────────────────────────────────────────────────────────────┘
What Makes Us Different
| Capability | TerminAI | Others |
|---|---|---|
| Actually executes (not just suggests) | ✅ | Rare |
| Policy gating (approval before action) | ✅ | ❌ |
| Three-axis security (Outcome/Intent/Domain) | ✅ | ❌ |
| Audit trail (immutable, non-disableable) | ✅ | ❌ |
| Voice control (push-to-talk STT/TTS) | ✅ | ❌ |
| Agent-to-Agent protocol | ✅ | ❌ |
| Multi-LLM (Gemini, ChatGPT OAuth, OpenAI-compatible) | ✅ | Limited |
| Native Windows support | ✅ | Limited |
| Recipes engine (governed playbooks) | ✅ | ❌ |
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.
- 1mo ago First seen · 1,128 lines · 8,528 tokens per session scan A a6a18d72421c
terminaI AGENTS.md is an instructions file published in the GitHub repository Prof-Harita/terminaI (425 stars, last pushed yesterday), licensed Apache-2.0. It adds 8,528 tokens to every session, about $0.0341 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). 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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.