What is hailux AGENTS.md?

Repository instructions for Hailux, a Rust application with a text-based interface and an optional web interface. They describe its layout, commit naming rules, build commands, tests, formatting, and checks.

Use them while developing Hailux to build it, run tests and lint checks, format Rust code, and build the web frontend.

They give coding agents the project's required development and review rules, reducing inconsistent commits and changes that fail its build or checks.

How dongdong306/hailux configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to dongdong306/hailux. 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/dongdong306/hailux/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/dongdong306/hailux

Made for: Claude Code, 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/dongdong306/hailux/agents-md.svg)](https://agentmods.dev/instructions/dongdong306/hailux/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/dongdong306/hailux/agents-md"><img src="https://agentmods.dev/badge/instructions/dongdong306/hailux/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 3,813 This file is loaded in full into every session.

When invoked 3,813 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 5.1	$0.03813	$0.03813
Opus 5	$0.01906	$0.01906
Sonnet 5	$0.00763	$0.00763
Haiku 4.5	$0.00381	$0.00381

Measured 6d ago against content hash 7732219ee80d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

hailux 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 6d 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 · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Instructions for the hailux repository, injected into every coding session's system prompt. Note: hailux itself loads AGENTS.md (case-insensitive) from ~/.hailux/ (global) and ancestor dirs of the work dir — running hailux inside this repo picks up this very file (work-dir file has highest priority).

Commit Convention

All commit messages must be in English.
Follow Conventional Commits: feat:, fix:, docs:, refactor:, chore:, ci:, etc.
Never add "generated by AI/Claude" attribution lines.

Build & Test

cargo build          # build (edition 2024 — requires Rust 1.96.0+; feature "web" on by default)
cargo run            # launch the TUI app
cargo run -- --web   # launch the Web UI (default 127.0.0.1:18080)
cargo test           # inline #[cfg(test)] modules across src/* + tests/integration.rs
cargo test --lib     # unit tests only (faster inner loop)
cargo clippy -- -D warnings   # CI gate — match before pushing
cargo fmt            # CI runs `cargo fmt --check`

# Web frontend (required when feature "web" is on; Node 22 in CI)
cd web && npm install && npm run build   # = tsc -b && vite build → web/dist (rust-embed)
cargo build --no-default-features        # TUI-only build, no Node needed

build.rs auto-runs npm run build if web/dist/index.html is missing or a placeholder — still build the frontend manually after touching web/src.
CI (.github/workflows/ci.yml): frontend build → fmt check → clippy → test → build, on Ubuntu + Windows.
Release via release-please (.release-please-manifest.json); scripts/generate-changelog.sh feeds it.

What hailux Is

A terminal-based AI coding assistant (like OpenCode/Claude Code) written in Rust, with an optional Web UI. It uses async-openai with a bring-your-own-transport custom layer to support DeepSeek-style reasoning_content fields. TUI: ratatui + crossterm. Web: axum SSE + REST + embedded static assets (web/, React + assistant-ui + zustand + vite). Features streaming chat, tool calling, MCP protocol, progressive skill system, subagent delegation, and custom slash commands.

Read the full file on GitHub · 201 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.

6d ago First seen · 201 lines · 3,813 tokens per session scan A 7732219ee80d

Subscribe to this mod's changes

hailux AGENTS.md is an instructions file published in the GitHub repository dongdong306/hailux (5 stars, last pushed 13d ago), licensed MIT. It adds 3,813 tokens to every session, about $0.0191 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.

ai ai-agent cli code-assistant ratatui

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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

vscode buildNext.instructions.md

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

hailux: Instructions file for Claude Code