kopi: Instructions file for Codex

AGENTS.md

kopi AGENTS.md is an instructions file for Codex, OpenCode from kopi-vm/kopi. It costs 3,182 tokens per session, scanned A, original, Apache-2.0.

A project instruction file for coding agents working on Kopi, a Rust tool that switches between Java Development Kit versions. It sets the project's documentation rules, structure, and operating context.

In plain words
What is it for?
It guides code comments, commit messages, README files, API documentation, tests, and user documentation for Kopi.
Why use it?
It gives an agent the project-specific rules it needs before changing code or documentation, such as writing all documentation in English.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is kopi-vm/kopi's own configuration. It tells Codex and OpenCode how to work on kopi itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything kopi configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kopi-vm/kopi. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kopi-vm/kopi/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/kopi-vm/kopi

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for kopi AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kopi-vm/kopi/agents-md/github.svg)](https://agentmods.dev/instructions/kopi-vm/kopi/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/kopi-vm/kopi/agents-md"><img src="https://agentmods.dev/badge/instructions/kopi-vm/kopi/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.

agentmods 80×15 button for kopi AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kopi-vm/kopi/agents-md"><img src="https://agentmods.dev/badge/instructions/kopi-vm/kopi/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,182 This file is loaded in full into every session.
When invoked 3,182 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.03182 $0.03182
Opus 5.5 $0.01273 $0.01273
Sonnet 5.5 $0.00636 $0.00636
Haiku 4.5 $0.00318 $0.00318

Measured 2d ago against content hash 088dd1bed2fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kopi 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- When writing code that calls external Web APIs, implement at least one unit test that includes the actual JSON response obtained from calling the API with curl
AGENTS.md · 288 lines

How it starts

The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Documentation Language Policy

All documentation output in this project must be written in English, including:

  • Code comments
  • Commit messages
  • Architecture Decision Records (ADRs)
  • README files
  • API documentation
  • Error messages
  • User-facing documentation
  • Test descriptions
  • TODO comments
  • Any other written documentation

Project Overview

Kopi is a JDK version management tool written in Rust that integrates with your shell to seamlessly switch between different Java Development Kit versions. It fetches JDK metadata from foojay.io and provides a simple, fast interface similar to tools like volta, nvm, and pyenv.

Key features:

  • Automatic JDK version switching based on project configuration
  • Multiple JDK vendor support (AdoptOpenJDK, Amazon Corretto, Azul Zulu, etc.)
  • Shell integration via shims for transparent version management
  • Project-specific JDK pinning via .kopi-version or .java-version files
  • Fast performance using Rust

User Documentation

The user-facing documentation for Kopi is maintained in a separate repository at ../kopi-vm.github.io/. This repository uses MkDocs to generate and publish documentation for end users.

Agent Operating Environment

Planning and Tooling Discipline

  • Use the planning tool for any task that is not trivially simple; plans must include at least two steps and be updated as work progresses. Skip planning only for the simplest ~25% of tasks.
  • At the start of each session, run serena__activate_project to bind Serena to the current repository context.
  • After activation, run serena__check_onboarding_performed; if it indicates onboarding is incomplete, execute serena__onboarding before proceeding.
  • At the start of each task, run bun scripts/trace-status.ts --write to regenerate docs/traceability.md and identify any traceability gaps before continuing.
  • Before insert/replace/delete edits, invoke serena__think_about_task_adherence; after gathering significant context, call serena__think_about_collected_information to confirm understanding.
  • Follow the Traceable Development Lifecycle (TDL) for non-trivial work and ensure traceability artifacts stay in sync.

Read the full file on GitHub · 288 lines

Changes

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.

  1. 2d ago First seen · 288 lines · 3,182 tokens per session scan A 088dd1bed2fa

Subscribe to this mod's changes

kopi AGENTS.md is an instructions file published in the GitHub repository kopi-vm/kopi (29 stars, last pushed 1y ago), licensed Apache-2.0. It adds 3,182 tokens to every session, about $0.0127 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-11.

Related

kopi AGENTS.md compared with instructions from other repositories

kopi AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
kopi AGENTS.mdkopi-vm/kopiInstructions file291y agoApache-2.0A3,182Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file280kyesterdayMITA4,325Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,086GitHub Copilot