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/manusa/ai-cli/agents-mdgit clone --depth 1 https://github.com/manusa/ai-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 | $0.01241 | $0.01241 |
| Opus 5 | $0.00620 | $0.00620 |
| Sonnet 5 | $0.00248 | $0.00248 |
| Haiku 4.5 | $0.00124 | $0.00124 |
Grade A, and why
ai-cli 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 yesterday.
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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ai-cli - AI Agents Instructions
Always reference these instructions first and fallback to search or bash commands only when you encounter unexpected information that does not match the info here.
This file provides guidance to AI coding agents (GitHub Copilot, Claude Code, etc.) when working with code in this repository.
Project Overview
ai-cli is a command-line interface (CLI) tool that enables users to interact with AI models and tools in a safe, automated, and tailored manner.
It supports multiple inference providers and a variety of tools, allowing users to create AI-powered workflows directly from the terminal.
The main difference between ai-cli and other AI tools is its support for policies, discovery of providers and tools, and extensibility through plugins.
By using policies, organization admins can set rules for AI interactions and tool usage, ensuring compliance and safety for enterprise users.
The discovery feature allows the CLI to automatically find and use available inference providers and tools based on the user's environment, making it easy to get started without extensive configuration.
The extensible architecture allows developers to add new plugins, tools, and providers, making ai-cli a flexible solution for various AI use cases.
Development Commands
Build and Development
make build # Build the project (includes clean, tidy, format, lint)
make test # Run all tests
make format # Format Go code
make tidy # Tidy Go modules
make lint # Run golangci-lint
make clean # Clean build artifacts
Running the Application
./ai-cli help # Show available commands after building
./ai-cli chat # Start TUI-based chat session
./ai-cli discover # Discover available tools and providers
./ai-cli version # Show version information
Testing
go test ./... # Run all tests
go test -v ./pkg/cmd/... # Run tests for specific package with verbose output
go test -count=1 -v ./... # Run tests without cache
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.
- yesterday First seen · 135 lines · 1,241 tokens per session scan A 73d3c2b3e44c
ai-cli AGENTS.md is an instructions file published in the GitHub repository manusa/ai-cli (27 stars, last pushed 10mo ago), licensed Apache-2.0. It adds 1,241 tokens to every session, about $0.0062 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
mcp-for-beginners AGENTS.md
Instructions for microsoft/mcp-for-beginners, covering agents.md, project overview, key technologies, architecture and setup commands.
fast-agent AGENTS.md
Instructions for evalstate/fast-agent, covering fast-agent contributor notes and architectural orientation.
jupyter-mcp-server copilot-instructions.md
Instructions for datalayer/jupyter-mcp-server, covering jupyter mcp server, working effectively, environment setup, build and install (critical: network limitations) and standard installation (may fail with network issues).
mcp-dotnet-samples AGENTS.md
Instructions for microsoft/mcp-dotnet-samples, covering agents.md - mcp .net samples, project overview, project structure and architecture, repository organization and sample components.
Embody AGENTS.md
Instructions for dylanroscover/Embody, covering embody + envoy - ai instructions, critical rules, td python rules, network layout rules and mcp server safety rules.
html-tools CLAUDE.md
Instructions for chicogong/html-tools, covering claude.md, 项目概述, 开发命令, 数据与生成边界 and 首页架构.