What is hermes-console AGENTS.md?

Repository instructions for Hermes Console, a local-first monorepo for inspecting Hermes Agent setups. A monorepo is one repository containing multiple related applications or packages.

Use them when changing the runtime package, local API, or Vite React web interface, while keeping parsing logic out of the web app.

They define the product boundaries and code organisation, helping changes stay small, readable, and in the right part of the project.

How shan8851/hermes-console configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to shan8851/hermes-console. 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/shan8851/hermes-console/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/shan8851/hermes-console

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/shan8851/hermes-console/agents-md/github.svg)](https://agentmods.dev/instructions/shan8851/hermes-console/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/shan8851/hermes-console/agents-md"><img src="https://agentmods.dev/badge/instructions/shan8851/hermes-console/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/shan8851/hermes-console/agents-md"><img src="https://agentmods.dev/badge/instructions/shan8851/hermes-console/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 534 This file is loaded in full into every session.

When invoked 534 The same file — it is already loaded in full.

Security scan A 0 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.

Model	Per session	Once invoked
Fable 5.1	$0.00534	$0.00534
Opus 5.5	$0.00214	$0.00214
Sonnet 5.5	$0.00107	$0.00107
Haiku 4.5	$0.00053	$0.00053

Measured 2mo ago against content hash f4a30165eeb0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hermes-console 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 2mo 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 · 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 — Hermes Console

What this is

Hermes Console is a local-first monorepo for inspecting Hermes Agent setups.

Current workspace shape:

packages/runtime for pure schemas, types, and domain helpers
apps/api for filesystem reads, CLI diagnostics, and the local HTTP boundary
apps/web for the Vite React UI

It is:

Hermes-native
read-mostly at launch
visibility-first, not chat-first
intended as a clean, focused product

Product priorities

When working in this repo, optimise for:

legibility
calm operator UX
simple local setup
modular code structure
strong naming and obvious file organisation
small, testable units

Non-goals for v1

Do not let the repo drift into:

generic multi-agent platform abstractions
terminal emulator work
chat-client parity work
full file manager/editor scope
enterprise auth / RBAC theatre
Shan-specific bespoke workflow surfaces as core primitives

Code structure expectations

Prefer small composable components over giant page files.
Keep reader/parsing logic in apps/api or packages/runtime, never in apps/web.
Keep packages/runtime pure and framework-agnostic.
Create explicit internal types for each source family.
Prefer strong names that explain intent: CronJobsTable, readSkillsIndex, formatMemoryUsage.
Keep file and folder structure obvious and domain-led.
Avoid catch-all utils dumping grounds when a domain module is clearer.

Testing expectations

Add unit tests for:

readers
parsers
normalizers
schedule / usage / warning calculations
any non-trivial UI state helpers

If logic is important enough to deserve a helper, it usually deserves a test.

Local config expectations

Expect .env.local for local overrides. Planned important env vars:

HERMES_CONSOLE_HERMES_DIR
HERMES_CONSOLE_WORKSPACE_DIR
PORT

Default assumption is a standard Hermes setup under ~/.hermes.

UX expectations

Dark-first.
Giles-style information clarity.
Hermes-style branding and accents.
Dense but breathable layouts.
Make important state obvious in one screen when possible.
Avoid noisy dashboards and fake enterprise complexity.

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.

2mo ago First seen · 93 lines · 534 tokens per session scan A f4a30165eeb0

Subscribe to this mod's changes

hermes-console AGENTS.md is an instructions file published in the GitHub repository shan8851/hermes-console (10 stars, last pushed 5mo ago), licensed MIT. It adds 534 tokens to every session, about $0.0021 per session on Opus 5.5. 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.

hermes-console AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
hermes-console AGENTS.mdshan8851/hermes-console	Instructions file	10	5mo ago	MIT	A	534	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

hermes-console: Instructions file for Codex