hermes-multi-agent-workflow AGENTS.md

hermes-multi-agent-workflow AGENTS.md is an instructions file for Codex, OpenCode from tonbistudio/hermes-multi-agent-workflow. It costs 1,375 tokens per session, scanned A, original, MIT.

Repository instructions for Hermes Multi-Agent Workflow, a reusable system that collects items, removes duplicates, scores them, researches them, routes them, and delivers results after one human approval step.

In plain words
What is it for?
Use it when adapting the workflow to a new subject area, mainly by changing triage.yaml and its referenced templates.
Why use it?
It explains which parts are reusable and where the project-specific settings belong, reducing unnecessary changes to the shared engine.

Instructions file for CodexOpenCode

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

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/tonbistudio/hermes-multi-agent-workflow/agents-md
Clone the repo
git clone --depth 1 https://github.com/tonbistudio/hermes-multi-agent-workflow

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-multi-agent-workflow AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tonbistudio/hermes-multi-agent-workflow/agents-md.svg)](https://agentmods.dev/instructions/tonbistudio/hermes-multi-agent-workflow/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/tonbistudio/hermes-multi-agent-workflow/agents-md"><img src="https://agentmods.dev/badge/instructions/tonbistudio/hermes-multi-agent-workflow/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,375 This file is loaded in full into every session.
When invoked 1,375 The same file — it is already loaded in full.
Security scan A 0 findings. 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 5.1 $0.01375 $0.01375
Opus 5 $0.00687 $0.00687
Sonnet 5 $0.00275 $0.00275
Haiku 4.5 $0.00137 $0.00137

Measured 6d ago against content hash 97d84d688cb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

hermes-multi-agent-workflow 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 6d 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 · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — read this first

You are an AI coding agent helping a human adapt this template to their own work. This file is your map. Read it fully before you touch anything.

What this repository is

The Hermes Multi-Agent Workflow: a reusable skeleton for an autonomous, multi-agent triage pipeline that

detects items from sources → dedupsscores them against a rubric → researches in parallel → routes to one of several paths → stops at one human gatefulfillsdelivers.

It is a template, not a finished product. Out of the box it is wired as a worked example (finding pain points about AI agents, then building a fix or making an explainer video). The human who cloned this wants to repoint it at their domain. Your job is to help them do that.

The single most important rule

The domain lives in triage.yaml, not in the Python. The engine/ package is generic and should stay that way. When the human says "make this about X," your default move is to edit triage.yaml and the markdown templates it points at — not to edit engine/.

You touch engine/ only to add a new mechanism (a new kind of step, a new scoring mode, an embedding backend). You never edit it to encode a topic.

If you find yourself writing the human's subject matter into a .py file, stop — that belongs in config.

Orientation: what's generic vs. what's theirs

Generic engine (rarely edit) The human's domain (edit freely)
engine/config.py — loads/validates triage.yaml triage.yaml — the whole pipeline definition
engine/engine.py — deterministic step logic paths/rails/*.md — what may be built
engine/scoring.py — applies the rubric paths/specs/*.md — output formats
engine/routing.py — applies the route map paths/proposals/*.md — gate messages
engine/dedup.py — similarity skills/templates/*/SKILL.md — scout + orchestrator behavior
engine/item_vault.py, kanban_store.py, frontmatter.py, intake_parser.py env: profiles, models, board name, schedules
proposal_actions.py — gate handler (config-driven)

Read the full file on GitHub · 107 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. 6d ago First seen · 107 lines · 1,375 tokens per session scan A 97d84d688cb2

Subscribe to this mod's changes

hermes-multi-agent-workflow AGENTS.md is an instructions file published in the GitHub repository tonbistudio/hermes-multi-agent-workflow (457 stars, last pushed 3mo ago), licensed MIT. It adds 1,375 tokens to every session, about $0.0069 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.

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

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

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

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

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

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