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.
npx agentmods add instructions/nepixe1/agenthalo/agents-mdgit clone --depth 1 https://github.com/NePixe1/AgentHaloWrote 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.
[](https://agentmods.dev/instructions/nepixe1/agenthalo/agents-md)<a href="https://agentmods.dev/instructions/nepixe1/agenthalo/agents-md"><img src="https://agentmods.dev/badge/instructions/nepixe1/agenthalo/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.02001 | $0.02001 |
| Opus 5 | $0.01001 | $0.01001 |
| Sonnet 5 | $0.00400 | $0.00400 |
| Haiku 4.5 | $0.00200 | $0.00200 |
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 4d 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` How it starts
The opening of the file, as written. The whole thing — 167 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; macOS 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.cssrc/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)
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.
- 4d ago First seen · 167 lines · 2,001 tokens per session scan B 0f68a0127b9d
AgentHalo AGENTS.md is an instructions file published in the GitHub repository NePixe1/AgentHalo (10 stars, last pushed 9d ago), licensed MIT. It adds 2,001 tokens to every session, about $0.0100 per session on Opus 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.
Other instructions, from other repositories
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.