What is hermes-profiles AGENTS.md?

A guide for AI coding agents working in the Hermes Profiles repository, which organizes reusable instructions into agent profiles and shared skills. It explains the repository layout, profile files, and symbolic links between profiles and skills.

Use it when creating, updating, or using Hermes agent profiles, shared skills, profile metadata, or the links that connect profiles to skills.

It gives agents a consistent way to understand the repository and follow each profile’s instructions without duplicating skill files.

How magnus919/hermes-profiles configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to magnus919/hermes-profiles. 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/magnus919/hermes-profiles/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/magnus919/hermes-profiles

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/magnus919/hermes-profiles/agents-md.svg)](https://agentmods.dev/instructions/magnus919/hermes-profiles/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/magnus919/hermes-profiles/agents-md"><img src="https://agentmods.dev/badge/instructions/magnus919/hermes-profiles/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 798 This file is loaded in full into every session.

When invoked 798 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	$0.00798	$0.00798
Opus 5	$0.00399	$0.00399
Sonnet 5	$0.00160	$0.00160
Haiku 4.5	$0.00080	$0.00080

Measured 8d ago against content hash 2e6067756b86, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

hermes-profiles 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 8d 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 · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hermes Profiles — Agent Guide

This file helps AI agents understand how to interact with this repository.

Repository Structure

hermes-profiles/
├── skills/                          ← Shared skill pool (actual files)
│   ├── artifact-pyramids/
│   ├── architecture/
│   │   ├── adr-authoring/
│   │   ├── arc42-context/
│   │   ├── architect-pyramid/
│   │   └── c4-diagramming/
│   ├── chief-of-staff-methodology/
│   ├── mermaid-diagrams/
│   └── product-methodology/
├── profiles/                        ← Agent profiles (symlinks to skills)
│   ├── chief-of-staff/
│   ├── technical-architect/
│   ├── product-manager/
│   └── site-reliability-engineer/
├── .github/ISSUE_TEMPLATE/
├── CONTRIBUTING.md
├── LICENSE
└── README.md

How Profiles Work

Each profile is a directory containing:

File	Purpose
`SOUL.md`	Identity document — first principles, methodology, output contract
`profile.yaml`	Metadata — description, required/recommended skills
`README.md`	Human-facing usage guide
`AGENTS.md`	Agent-facing trigger patterns and handoff protocol

Profiles do NOT contain skill files directly. Each profile's skills/ directory contains relative symlinks back to the shared skills/ pool at the repo root. This means one copy of each skill serves every profile.

Skill Conventions

Skills in the shared pool follow progressive disclosure:

SKILL.md is a thin index with trigger conditions and loading instructions
Methodology detail lives in references/ loaded on demand via skill_view(name, file_path=path)
Skills should work on a vanilla Hermes install — no dependencies on council, cashew, or agent-specific infrastructure

Symlink Rules

All symlinks must be relative, not absolute
From profiles/<name>/skills/, target is ../../../skills/<skill-name>
From profiles/<name>/skills/<category>/, target is ../../../../skills/<category>/<skill-name> (or make the category itself a symlink)
Symlinks are tracked by git (mode 120000). They recreate correctly on git clone (macOS/Linux).

Read the full file on GitHub · 85 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.

8d ago First seen · 85 lines · 798 tokens per session scan A 2e6067756b86

Subscribe to this mod's changes

hermes-profiles AGENTS.md is an instructions file published in the GitHub repository magnus919/hermes-profiles (149 stars, last pushed 2mo ago), licensed MIT. It adds 798 tokens to every session, about $0.0040 per session on Opus 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.

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

hermes-profiles: Instructions file for Codex