What is askCode AGENTS.md?

A codebase guide for askCode.nvim, a Neovim plugin that connects the editor to several command-line AI agents. It explains the main files, entry points, tests, and conventions for adding or changing agents.

Use it when modifying plugin logic, agent integrations, Neovim commands, configuration, user-interface code, or tests.

It gives a coding agent enough structure to navigate the plugin without searching the whole repository blindly or missing project-specific rules.

askCode AGENTS.md — Instructions file by realEbi

Install

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.

agentmods

npx agentmods add instructions/realebi/askcode/agents-md

Clone the repo

git clone --depth 1 https://github.com/realEbi/askCode

Made for: Codex, OpenCode.

Per session 1,532 This file is loaded in full into every session.

When invoked 1,532 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.01532	$0.01532
Opus 5	$0.00766	$0.00766
Sonnet 5	$0.00306	$0.00306
Haiku 4.5	$0.00153	$0.00153

Measured yesterday against content hash ded0d9faebc9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

askCode 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.

AGENTS.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — askCode.nvim

A navigation guide for AI agents working in this codebase.

Directory Overview

lua/askCode/          ← all plugin logic lives here
├── init.lua          ← public API + conversation state (start here)
├── config.lua        ← dot-notation config system
├── runner.lua        ← thin vim.fn.jobstart wrapper
├── ui.lua            ← window/buffer creation and updates
├── utils.lua         ← file I/O, buffer reads, replacement parsing, debug log
└── agents/
    ├── init.lua      ← agent registry (maps name → module)
    ├── gemini.lua    ← Gemini CLI integration
    ├── kiro.lua      ← Kiro CLI integration
    ├── opencode.lua  ← OpenCode CLI integration
    └── claude.lua    ← Claude CLI integration
plugin/askCode.lua    ← Neovim commands + <Plug> keymaps (entry point)
tests/                ← MiniTest suite (one file per module)
scripts/minimal_init.lua  ← headless Neovim init used by make test
CODE-STANDARDS.md     ← authoritative coding standards and architecture
.agents/add-new-agent.md  ← step-by-step plan for adding a new agent
.claude/skills/add-agent/ ← Claude Code skill that automates adding a new agent

Key Entry Points

Feature work: start in lua/askCode/init.lua — it orchestrates all modules
Adding an agent: follow .agents/add-new-agent.md, or invoke the /add-agent Claude Code skill — create lua/askCode/agents/<name>.lua, register in agents/init.lua
Config changes: lua/askCode/config.lua — update M.default and annotations
UI changes: lua/askCode/ui.lua — show_window and update_window
Commands/keymaps: plugin/askCode.lua

Agent Interface

Every agent module must implement:

function M.prepare_command(prompt) → string   -- shell command to run
function M.parse_response(raw_output) → string|nil  -- clean the CLI output

M.agents.myagent = require("askCode.agents.myagent")

Then users set agent = "myagent" in their config.

Read the full file on GitHub · 123 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.

yesterday First seen · 123 lines · 1,532 tokens per session scan A ded0d9faebc9

Subscribe to this mod's changes

askCode AGENTS.md is an instructions file published in the GitHub repository realEbi/askCode (4 stars, last pushed 4mo ago), licensed MIT. It adds 1,532 tokens to every session, about $0.0077 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 2026-08-31.

Testing agent amazonqcli gemini-cli neovim

askCode AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AGENTS.md — askCode.nvim

Directory Overview

Key Entry Points

Agent Interface

What this file has done since we first saw it

Other instructions, from other repositories

open-vibe-island AGENTS.md

open-vibe-island CLAUDE.md

agents-in-a-box AGENTS.md

KittyCode AGENTS.md

agent-session-parser AGENTS.md

integration-architect-agent GEMINI.md