What is AgentHalo AGENTS.md?

Project instructions for Agent Halo, a desktop status ring that shows the state of coding agents such as Codex and Claude Code. They define its product intent, interface style, architecture, and shared behavior.

Use them when developing, reviewing, or verifying Agent Halo features, shared specifications, interface changes, and cross-platform behavior.

They keep changes consistent across the app and its Windows and macOS versions. They also set expectations for quiet visuals, lifecycle states, and privacy.

How NePixe1/AgentHalo configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to NePixe1/AgentHalo. 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/NePixe1/AgentHalo/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/NePixe1/AgentHalo

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/nepixe1/agenthalo/agents-md/github.svg)](https://agentmods.dev/instructions/nepixe1/agenthalo/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/nepixe1/agenthalo/agents-md"><img src="https://agentmods.dev/badge/instructions/nepixe1/agenthalo/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/nepixe1/agenthalo/agents-md"><img src="https://agentmods.dev/badge/instructions/nepixe1/agenthalo/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,212 This file is loaded in full into every session.

When invoked 2,212 The same file — it is already loaded in full.

Security scan B 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.

Model	Per session	Once invoked
Fable 5.1	$0.02212	$0.02212
Opus 5.5	$0.00885	$0.00885
Sonnet 5.5	$0.00442	$0.00442
Haiku 4.5	$0.00221	$0.00221

Measured 24d ago against content hash 41f948e21e88, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

AgentHalo AGENTS.md scanned grade B 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 24d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- **macOS** Claude: lifecycle hooks + status line proxy in `~/.claude/settings.json`

AGENTS.md · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

UI design principle

The entire UI must stay minimal and refined : ambient-first, low visual noise, restrained typography and chrome, no decorative clutter. Prefer calm density over busy panels; do not invent extra rows, badges, or copy that break the premium quiet aesthetic. Details panels, menus, and hover surfaces should match the halo itself—readable at a glance, never loud.

Product intent

Agent Halo is a local, always-on-top desktop status ring for coding agents. Windows and macOS support Codex, Claude Code, Grok Build, and Pi. OpenCode and WorkBuddy are opt-in on both platforms. macOS also optionally supports Antigravity (agy, default off). Ambient first: readable in peripheral vision; honest lifecycle inference; privacy-first (no session upload). Product framing: docs/PRODUCT.md.

Architecture

Cross-platform behavior parameters come from a single contract:

Path	Role
`src/shared/spec/agent-halo.v2.json`	Canonical shared behavior (states, lifecycle, animation, settings surface)
`src/shared/spec/agent-halo.v2.schema.json`	Schema validation
`src/shared/README.md`	Generate / check workflow
`docs/CROSS_PLATFORM_SHARED_CONTRACT.md`	Architecture notes

Platform rendering and OS integration stay native:

Windows: C# / .NET under src/windows/
macOS: Swift under src/macos/

Generated constants (committed; do not edit by hand):

src/windows/GeneratedHaloSpec.cs
src/macos/Sources/AgentHaloCore/GeneratedHaloSpec.swift

Apps compile generated source; they do not load the JSON contract at runtime.

Shared generate / verify

python scripts/generate_shared.py
python scripts/generate_shared.py --check
python scripts/check_shared.py
python scripts/generate_app_icons.py   # regenerate .icns / .ico from assets/agent-halo-app-icon.png
# README mark is assets/agent-halo-readme-mark.png (pre-rounded; GitHub strips CSS radius)

Read the full file on GitHub · 176 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.

24d ago Changed · +7 lines · +95 tokens per session 41f948e21e88
26d ago Changed · +2 lines · +116 tokens per session a0ea5d039c23
2mo ago First seen · 167 lines · 2,001 tokens per session scan B 0f68a0127b9d

Subscribe to this mod's changes

AgentHalo AGENTS.md is an instructions file published in the GitHub repository NePixe1/AgentHalo (11 stars, last pushed 7d ago), licensed MIT. It adds 2,212 tokens to every session, about $0.0088 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

AgentHalo AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
AgentHalo AGENTS.mdNePixe1/AgentHalo	Instructions file	11	7d ago	MIT	B	2,212	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	1,907	GitHub Copilot

AgentHalo: Instructions file for Codex