aiwaku.nvim: Instructions file for Codex

AGENTS.md

aiwaku.nvim AGENTS.md is an instructions file for Codex, OpenCode from juhaku/aiwaku.nvim. It costs 1,250 tokens per session, scanned A, original, MIT.

A repository guide for aiwaku.nvim, a Neovim plugin that runs command-line AI tools inside a tmux sidebar terminal. It describes the project layout and validation expectations.

In plain words
What is it for?
It is for making and checking changes to this Lua-based Neovim plugin.
Why use it?
It gives contributors the project context and tells them how to verify changes without inventing new tooling.

Instructions file for CodexOpenCode

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

This is juhaku/aiwaku.nvim's own configuration. It tells Codex and OpenCode how to work on aiwaku.nvim 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 aiwaku.nvim configures →

Reuse

Borrowing it

Nothing to install: this file belongs to juhaku/aiwaku.nvim. 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/juhaku/aiwaku.nvim/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/juhaku/aiwaku.nvim

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 aiwaku.nvim AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/juhaku/aiwaku.nvim/agents-md.svg)](https://agentmods.dev/instructions/juhaku/aiwaku.nvim/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/juhaku/aiwaku.nvim/agents-md"><img src="https://agentmods.dev/badge/instructions/juhaku/aiwaku.nvim/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,250 This file is loaded in full into every session.
When invoked 1,250 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.01250 $0.01250
Opus 5 $0.00625 $0.00625
Sonnet 5 $0.00250 $0.00250
Haiku 4.5 $0.00125 $0.00125

Measured 5d ago against content hash 828d71863120, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

aiwaku.nvim 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 5d 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.

AGENTS.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for automated contributors working in this repository.

Project overview

aiwaku.nvim is a Neovim plugin that runs a user-selected CLI AI tool inside a tmux session and shows it in a persistent sidebar terminal. The plugin is tool-agnostic: users can configure copilot, claude, opencode, aider, or another CLI tool.

Key runtime requirements:

  • tmux >= 3.0
  • Neovim >= 0.10
  • nvim-lua/plenary.nvim
  • Optional integrations: stevearc/dressing.nvim, nvimtools/none-ls.nvim

Validation expectations

This repository does not currently define dedicated build, test, or lint commands.

  • Do not invent new validation tooling just for a change.
  • For documentation-only edits, do a manual diff review and run git diff --check.
  • For Lua changes, do a manual diff review plus at least one concrete targeted verification step when possible.
  • Keep validation proportional to the change, and explicitly note when no automated test command exists.

Repository layout

  • README.md — primary user-facing documentation and setup guide.
  • doc/aiwaku.nvim.txt — Vim help documentation. Keep it in sync with README.md for user-facing behavior.
  • lua/aiwaku/config.lua — configuration defaults and command normalization logic.
  • lua/aiwaku/init.lua — public API surface and setup entrypoint.
  • lua/aiwaku/state.lua — shared runtime state singleton.
  • lua/aiwaku/session.lua — session lifecycle orchestration.
  • lua/aiwaku/tmux.lua — tmux command construction, shelling-out, and session parsing.
  • lua/aiwaku/window.lua — sidebar split/window management.
  • lua/aiwaku/terminal.lua — terminal buffer creation and terminal-local setup.
  • lua/aiwaku/send.lua — dispatches visual selections and whole buffers into the active terminal job.
  • lua/aiwaku/lsp-code-actions.lua — optional null-ls/none-ls integration.
  • lua/aiwaku/types.lua — Lua type annotations used by the development workflow.
  • lua/aiwaku/words.lua — word lists used for generated human-readable session names.
  • .github/copilot-instructions.md — repo-specific working guidance.
  • .github/instructions/lua.instructions.md — Lua-specific generation and review rules.
  • .github/instructions/context.instructions.md — guidance for recording and verifying fixes when generated changes and review diverge.

Read the full file on GitHub · 105 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. 5d ago First seen · 105 lines · 1,250 tokens per session scan A 828d71863120

Subscribe to this mod's changes

aiwaku.nvim AGENTS.md is an instructions file published in the GitHub repository juhaku/aiwaku.nvim (11 stars, last pushed 3mo ago), licensed MIT. It adds 1,250 tokens to every session, about $0.0063 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 2026-09-02.

Related

Other instructions, from other repositories