hermes-gpt: Instructions file for Codex

AGENTS.md

hermes-gpt AGENTS.md is an instructions file for Codex, OpenCode from asimons81/hermes-gpt. It costs 1,149 tokens per session, scanned A, original, MIT.

A repository-wide instruction file for coding agents working on the Hermes GPT project.

In plain words
What is it for?
It guides code and documentation changes, protects product rules such as the local network boundary, and directs agents to the relevant tests and operational documents.
Why use it?
It tells agents which files and sources to trust, helping prevent changes based on outdated plans or incorrect documentation.

Instructions file for CodexOpenCode

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

This is asimons81/hermes-gpt's own configuration. It tells Codex and OpenCode how to work on hermes-gpt 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 hermes-gpt configures →

Reuse

Borrowing it

Nothing to install: this file belongs to asimons81/hermes-gpt. 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/asimons81/hermes-gpt/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/asimons81/hermes-gpt

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-gpt AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/asimons81/hermes-gpt/agents-md/github.svg)](https://agentmods.dev/instructions/asimons81/hermes-gpt/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/asimons81/hermes-gpt/agents-md"><img src="https://agentmods.dev/badge/instructions/asimons81/hermes-gpt/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 hermes-gpt AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/asimons81/hermes-gpt/agents-md"><img src="https://agentmods.dev/badge/instructions/asimons81/hermes-gpt/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,149 This file is loaded in full into every session.
When invoked 1,149 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01149 $0.01149
Opus 5.5 $0.00460 $0.00460
Sonnet 5.5 $0.00230 $0.00230
Haiku 4.5 $0.00115 $0.00115

Measured 16d ago against content hash dd1c64f5a7c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hermes-gpt 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 16d 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 · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

These instructions apply to the entire hermes-gpt repository.

Start here

Before changing code or documentation:

  1. Read docs/README.md for the documentation authority map.
  2. Read pyproject.toml for the checked-out package version and shipped modules/docs.
  3. Read the current operational document for the subsystem you are touching.
  4. Inspect the implementation module and its tests before changing behavioral claims.

Do not treat docs/design/*, docs/releases/*, or FEASIBILITY.md as current runtime instructions. They preserve design and release history.

Source-of-truth precedence

When sources disagree:

  1. current implementation and tests;
  2. current operational docs;
  3. current release notes / CHANGELOG;
  4. historical design, risk, counsel, release-plan, and feasibility artifacts.

Never change runtime behavior solely to make it match a historical plan. First determine whether the implementation or the documentation is the intended current contract.

Product invariants

Preserve these unless the task explicitly changes the security model and includes corresponding tests/docs:

  • local loopback is the default network boundary;
  • public unauthenticated Operator hosting is unsupported;
  • default behavior is read-only;
  • mutating Operator actions are opt-in and dry-run-first;
  • direct mutation requires server direct mode plus per-call gates;
  • Owner Mode is break-glass and does not bypass secret-path protections;
  • .env, auth/token stores, SSH/AWS secrets, vault secrets, and secret-looking files remain denied;
  • protected subprocess paths use fixed argv and shell=False;
  • raw prompts are not persisted in Operator audit records;
  • Mission Control excludes raw messages, memory bodies, transcripts, request dumps, credentials, and profile-secret bodies;
  • Work Contract completion is validated from observed state and fails closed when evidence is missing;
  • Swarm orchestration has bounded concurrency/rework and a final human approval gate;
  • Codex may review Swarm work but is never an implementation owner.

Read the full file on GitHub · 123 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. 16d ago Changed · +4 lines · +219 tokens per session dd1c64f5a7c9
  2. 2mo ago First seen · 119 lines · 930 tokens per session scan A e9fc7ada41fb

Subscribe to this mod's changes

hermes-gpt AGENTS.md is an instructions file published in the GitHub repository asimons81/hermes-gpt (238 stars, last pushed 8d ago), licensed MIT. It adds 1,149 tokens to every session, about $0.0046 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 2026-08-30.

Related

hermes-gpt AGENTS.md compared with instructions from other repositories

hermes-gpt AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
hermes-gpt AGENTS.mdasimons81/hermes-gptInstructions file2388d agoMITA1,149Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode