hermex: Instructions file for Codex

AGENTS.md

hermex AGENTS.md is an instructions file for Codex, OpenCode from uzairansaruzi/hermex. It costs 4,574 tokens per session, scanned C, original, MIT.

A guide for Hermex, a native iPhone app that connects directly to a user’s own Hermes agent server. It lets people start and steer sessions, watch streaming work, browse files, and recover sessions from a phone.

In plain words
What is it for?
Use it when changing the iPhone client, its HTTPS connection to the Hermes server, session controls, live work display, workspace browsing, or recovery flows.
Why use it?
It clarifies that the phone is the control and review interface while the user’s server handles execution, tools, models, and data.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions subagents; mentions AGENTS.md; mentions Codex.

This is uzairansaruzi/hermex's own configuration. It tells Codex and OpenCode how to work on hermex itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything hermex configures →

About the project

Hermex is a native iPhone app for controlling a self-hosted Hermes AI agent running on a server you own. It lets people chat with the agent, manage sessions and scheduled tasks, browse skills and files, and inspect memory from iOS. The catalogue entries are add-ons for the Hermes agent that Hermex connects to.

uzairansaruzi/hermex · 1,261 stars · on GitHub · hermexapp.com

Reuse

Borrowing it

Nothing to install: this file belongs to uzairansaruzi/hermex. 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/uzairansaruzi/hermex/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/uzairansaruzi/hermex

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.

agentmods badge for hermex AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/uzairansaruzi/hermex/agents-md/github.svg)](https://agentmods.dev/instructions/uzairansaruzi/hermex/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/uzairansaruzi/hermex/agents-md"><img src="https://agentmods.dev/badge/instructions/uzairansaruzi/hermex/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.

agentmods 80×15 button for hermex AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/uzairansaruzi/hermex/agents-md"><img src="https://agentmods.dev/badge/instructions/uzairansaruzi/hermex/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,574 This file is loaded in full into every session.
When invoked 4,574 The same file — it is already loaded in full.
Security scan C 2 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.04574 $0.04574
Opus 5 $0.02287 $0.02287
Sonnet 5 $0.00915 $0.00915
Haiku 4.5 $0.00457 $0.00457

Measured 9d ago against content hash 7f71a2cee352, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

hermex AGENTS.md scanned grade C with 2 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 9d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

1. **Killing by pattern.** Never `pkill -f`, `pgrep | kill`, or `kill` a PID you found by matching a name, path, or worktree string. Your own agent process has this worktree's path in its argv, and this Mac runs several

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

2. **Touching the live server.** The maintainer's `hermes-webui` runs on another Mac behind a tunnel, holding real sessions and real credentials. Reading from it with `curl` is fine, and the best way to verify a contract
AGENTS.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hermex

Hermex is a native SwiftUI iPhone app for a self-hosted Hermes agent. It talks directly to the user's hermes-webui server over HTTPS and gives them a phone-native control surface: start and steer sessions, watch streaming work, browse the workspace, and recover from wherever they are. The Xcode target and scheme are HermesMobile; the App Store name is Hermex.

You can think of Hermex as an open source "bring-your-own-server" iPhone client for Hermes. The phone is the control and review plane; the server owns execution, tools, models, and the user's data.

What makes Hermex special?

Hermex is on the App Store and people run it against their own servers every day. It's important we maintain the things they rely on as we continue to iterate on the product. Here's a brief list of the things we can never compromise on.

1. Open at the core

Hermex is truly open. We share our roadmap (GitHub Issues), we share how we think about things, and of course we share all our code. There is no Hermex relay, hosted backend, analytics service, or tracking layer: agent work and data stay on the user's hardware. We work in the open, and should strive to stay that way.

2. Performance without compromise

Lots of apps have gotten bogged down with bad tech decisions and "slop". We have not, and we're proud of the performance of Hermex. We regularly audit for performance regressions, often caused by unnecessary view invalidation, unstable identity in lists, eager work in scrolling paths, and animations that ignore Reduce Motion. Make sure all changes are considerate of performance impact.

3. Remote ready

Hermex connects to servers wherever they live: on the same Mac over localhost, across a Tailscale tailnet, or through an HTTPS tunnel such as Cloudflare. Long-lived SSE streams over those hops, reattaching after backgrounding, and multiple configured servers are core to the product. Whether users are on their local network or half a world away from their Mac, we need to make sure new features are properly supported, and that nothing scoped to one server ever shows up under another.

Read the full file on GitHub · 169 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.

  1. 9d ago First seen · 169 lines · 4,574 tokens per session scan C 7f71a2cee352

Subscribe to this mod's changes

hermex AGENTS.md is an instructions file published in the GitHub repository uzairansaruzi/hermex (1,261 stars, last pushed today), licensed MIT. It adds 4,574 tokens to every session, about $0.0229 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

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 · 5,153 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

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens