What is xbcode AGENTS.md?

Repository instructions for xbcode, a TypeScript command-line AI agent with a terminal interface. They explain the project structure, commands, API modes, and its five built-in tools, including a tool that delegates work to another agent.

Use them when editing xbcode, running its development or build commands, or changing its agent loop, tools, types, or task handling.

They help a coding agent understand how the program is organized before changing or testing it.

xbcode AGENTS.md — Instructions file by lwmxiaobei

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/lwmxiaobei/xbcode/agents-md

Clone the repo

git clone --depth 1 https://github.com/lwmxiaobei/xbcode

Made for: Codex, OpenCode.

Per session 634 This file is loaded in full into every session.

When invoked 634 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	$0.00634	$0.00634
Opus 5	$0.00317	$0.00317
Sonnet 5	$0.00127	$0.00127
Haiku 4.5	$0.00063	$0.00063

Measured 2d ago against content hash 33a31e16b443, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

xbcode 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 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.

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 · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to Codex (Codex.ai/code) when working with code in this repository.

Project Overview

A TypeScript CLI agent (similar to Codex) built with OpenAI SDK + Ink (React for CLI). It implements an agent loop with tool use, streaming output, and a terminal UI.

Commands

npm run dev      # Run in development (tsx, no compile)
npm run build    # Compile TypeScript to dist/
npm start        # Run compiled output

Architecture

Multi-file architecture: src/index.tsx (UI), src/agent.ts (agent loop), src/tools.ts (tool definitions & handlers), src/types.ts, src/todo.ts.

Dual API mode: Supports both OpenAI Responses API (default) and Chat Completions API (for DeepSeek-compatible endpoints). Auto-detected via OPENAI_BASE_URL or set explicitly with OPENAI_API_MODE.

Agent loop: agentLoop() (Responses API) and agentLoopWithChatCompletions() (Chat Completions) implement the core think-act cycle. Both loop until LLM returns no tool calls.

Tools: 5 built-in tools — bash, read_file, write_file, edit_file, task. The task tool dispatches work to an independent sub-agent with a clean context (no parent history). Sub-agents have base tools only (no recursive task). Max 30 rounds per sub-agent. All tools return strings (errors included). Tool schema uses JSON Schema format with additionalProperties: false.

UI layer: React components rendered via Ink. UiBridge interface connects agent logic to UI updates (streaming deltas, tool call display).

State: AgentState holds previousResponseId (Responses API chain) or chatHistory (Chat Completions message array).

Environment Variables

Configure in .env at project root:

OPENAI_API_KEY — required
MODEL_ID — default gpt-4.1
OPENAI_BASE_URL — optional, for compatible endpoints
OPENAI_API_MODE — responses or chat-completions (auto-detected)
SHOW_THINKING=1 — display model reasoning
REASONING_EFFORT — thinking intensity for reasoning models (minimal / low / medium / high / xhigh / max)

Read the full file on GitHub · 49 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.

2d ago First seen · 49 lines · 634 tokens per session scan A 33a31e16b443

Subscribe to this mod's changes

xbcode AGENTS.md is an instructions file published in the GitHub repository lwmxiaobei/xbcode (48 stars, last pushed 19d ago), licensed MIT. It adds 634 tokens to every session, about $0.0032 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.

Backend and APIs Languages Planning

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

buildNext

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).

microsoft/vscode · 6,785 tokens

xbcode AGENTS.md