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.
npx agentmods add instructions/agent37-platform/minions/agents-mdgit clone --depth 1 https://github.com/agent37-platform/minionsWhat 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 | $0.03477 | $0.03477 |
| Opus 5 | $0.01739 | $0.01739 |
| Sonnet 5 | $0.00695 | $0.00695 |
| Haiku 4.5 | $0.00348 | $0.00348 |
Grade A, and why
minions 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to coding agents when working with code in this repository.
Engineering practices
We're a startup. You're probably used to writing enterprise code — code that tries to handle every possible edge case and has fallbacks for everything. That's not how we do things around here: our number one rule is to keep things simple. We handle ONLY the most important cases.
We try to only add new functionality that is small (that is, simple and few lines of code) or absolutely necessary. If a change is not small or absolutely necessary, don't make it.
What This Is
Minions is an autonomous task management system with a Kanban board UI. Users create tasks via a chat interface; each task is a Hermes agent session that autonomously decides how to execute — doing the work itself, spawning child sessions, or creating Hermes cron jobs shown in Minions as Scheduled Tasks. Successful agent runs move tasks to review automatically. The user never talks to child sessions directly; recurring work is managed from the Scheduled Tasks page.
Prerequisites
- Node.js v18+
- Hermes agent installed with its Python venv (default location:
~/.hermes/hermes-agent/)
The server spawns a Python worker subprocess that imports Hermes AIAgent directly — no hermes gateway process or HTTP API is involved. The Python executable is resolved in this order:
HERMES_PYTHONenv var (explicit path)HERMES_AGENT_DIR/venv/bin/python(ifHERMES_AGENT_DIRis set)~/.hermes/hermes-agent/venv/bin/python(default)python3(system fallback)
Commands
npm run dev # dev mode: tsx watch + Vite dev server on :6969
npm run build # production build: server (tsc) + client (vite) + copy .sql/.py assets
npm run start # run compiled production build
npm run prod # build + run production in one command
npm test # Python worker checks + TypeScript component tests
No linter is configured.
Architecture
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.
- 2d ago First seen · 209 lines · 3,477 tokens per session scan A 338e845d2396
minions AGENTS.md is an instructions file published in the GitHub repository agent37-platform/minions (622 stars, last pushed 18d ago), licensed MIT. It adds 3,477 tokens to every session, about $0.0174 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.
Other instructions, from other repositories
DevoxxGenieIDEAPlugin GEMINI.md
Instructions for devoxx/DevoxxGenieIDEAPlugin, a project described as: DevoxxGenie is an agentic plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code. Latest version now also supports Spec Driven Development…
traverse AGENTS.md
Instructions for traverse-framework/traverse, covering traverse — agent coordination, agent coordination, 1. check for claude code claim, 2. check for claude code branch and 3. claim the ticket (only if pre-flight passes).
recruiting-copilot AGENTS.md
Instructions for Viy1204/recruiting-copilot, covering agents.md —— recruiting-copilot 源码/模板仓库, 先判断是使用还是维护, 本仓库结构 and 红线（对所有 agent 生效）.
rpikit AGENTS.md
Instructions for bostonaholic/rpikit, covering agent instructions, project overview, architecture & components, development and git workflow.
ESAA-Core AGENTS.md
Instructions for elzobrito/ESAA-Core, covering agents.md — contrato operacional codex/esaa, 1. autoridade e termos, 2. cli e runner, ou configure o runner uma vez por sessão and 3. concorrência.
oh-my-symphony AGENTS.md
Instructions for cskwork/oh-my-symphony, covering agents.md: codex cli entry point, source of truth: skills/symphony-skill, available skill (operator-facing), symphony-skill and worker-side guidance.