hermes-ui AGENTS.md

hermes-ui AGENTS.md is an instructions file for Codex, OpenCode from przbadu/hermes-ui. It costs 1,006 tokens per session, scanned A, original, MIT.

A setup runbook for hermes-ui, a browser interface for a running Hermes gateway. The gateway supplies the interface, web requests, sign-in, and live connection.

In plain words
What is it for?
Checking prerequisites, building the interface, and serving it from the Hermes gateway on the same website origin.
Why use it?
It prevents a cross-origin setup that can break sign-in, session cookies, or the live WebSocket connection.

Instructions file for CodexOpenCode

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/przbadu/hermes-ui/agents-md
Clone the repo
git clone --depth 1 https://github.com/przbadu/hermes-ui

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 hermes-ui AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/przbadu/hermes-ui/agents-md.svg)](https://agentmods.dev/instructions/przbadu/hermes-ui/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/przbadu/hermes-ui/agents-md"><img src="https://agentmods.dev/badge/instructions/przbadu/hermes-ui/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,006 This file is loaded in full into every session.
When invoked 1,006 The same file — it is already loaded in full.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5 $0.01006 $0.01006
Opus 5 $0.00503 $0.00503
Sonnet 5 $0.00201 $0.00201
Haiku 4.5 $0.00101 $0.00101

Measured 4d ago against content hash f27c83a96fb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hermes-ui AGENTS.md scanned grade A 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.

Makes network callslowCapability

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

3. `curl -sf http://127.0.0.1:9119/api/status` confirms a gateway is reachable. Note its host and port. You will serve the UI from the gateway itself, so it must be one you can start or restart.
AGENTS.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Runbook for an AI agent (Hermes, Claude Code, and similar) to set up and run hermes-ui. Follow the steps in order. This uses the manual path only: build the bundle and serve it from the gateway. For the full human-facing reference, see README.md.

What you are setting up

hermes-ui is a browser UI for a running Hermes gateway. It has no backend of its own. The gateway serves the built bundle, so the UI, REST, auth, and the WebSocket all share the gateway's origin.

The one hard rule

The UI MUST be served same-origin with the gateway. The gateway rejects cross-origin browsers: CORS is locked to localhost, session cookies are SameSite=Lax, and the WebSocket closes foreign origins with close code 4403. Serving the bundle from the gateway (the steps below) satisfies this automatically. Do not host the bundle on a different origin and point it at the gateway; OAuth sign-in and the WebSocket will fail.

Preflight

Run these checks before changing anything.

  1. bun --version verifies the package manager and script runner. If it is missing, install it from https://bun.sh and stop if it cannot be installed.
  2. command -v hermes verifies the Hermes CLI that runs the gateway. If it is missing, the gateway is not installed here; ask the human where the gateway runs.
  3. curl -sf http://127.0.0.1:9119/api/status confirms a gateway is reachable. Note its host and port. You will serve the UI from the gateway itself, so it must be one you can start or restart.

Build

From the repo root:

cd app
bun install
bun run build

This produces app/dist/ containing index.html and an assets/ subdirectory. The build is a single large bundle, so expect it to take a few seconds and be tens of MB.

Serve (manual)

Serve the built bundle FROM the gateway so everything is same-origin. Prefer the ready-made runner, from the repo root:

./bin/prod                # builds if needed, then serves from the gateway
./bin/prod --port 9200    # extra args pass straight through to 'hermes serve'

Read the full file on GitHub · 93 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. 4d ago First seen · 93 lines · 1,006 tokens per session scan A f27c83a96fb4

Subscribe to this mod's changes

hermes-ui AGENTS.md is an instructions file published in the GitHub repository przbadu/hermes-ui (111 stars, last pushed 16d ago), licensed MIT. It adds 1,006 tokens to every session, about $0.0050 per session on Opus 5. A static security scan graded it A with 1 finding (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

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

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

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

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 · 4,345 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

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.

vercel/next.js · 7,296 tokens