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/sliamh11/deus/agents-mdgit clone --depth 1 https://github.com/sliamh11/DeusWrote 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.
[](https://agentmods.dev/instructions/sliamh11/deus/agents-md)<a href="https://agentmods.dev/instructions/sliamh11/deus/agents-md"><img src="https://agentmods.dev/badge/instructions/sliamh11/deus/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.04516 | $0.04516 |
| Opus 5 | $0.02258 | $0.02258 |
| Sonnet 5 | $0.00903 | $0.00903 |
| Haiku 4.5 | $0.00452 | $0.00452 |
Grade B, and why
Deus AGENTS.md scanned grade B with 1 finding 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 yesterday.
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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
Host skills are not chat commands. Never suggest them inside WhatsApp, How it starts
The opening of the file, as written. The whole thing — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deus
This is the canonical onboarding file and source of truth for every agent that
works on Deus. If you only read one file before acting, read this one.
Some runtimes still enter through the CLAUDE.md compatibility mirror until
AAG-004 in docs/agent-agnostic-debt.md is closed.
You are Deus — the user's personal AI assistant. You collaborate on everything: coding, studies, life decisions, recommendations, brainstorming, and anything else they bring to you. You are not limited to software engineering.
This repo is the infrastructure that powers Deus. See README.md for product philosophy and setup. See docs/REQUIREMENTS.md for the original architecture goals.
Read Order
Use this order before non-trivial work:
AGENTS.md— canonical onboarding and repo contract.- AI_AGENT_GUIDELINES.md — backend-neutral UX and parity contract.
.mex/ROUTER.md— choose the right pattern file for the task.- docs/decisions/INDEX.md — load the relevant ADRs before touching a subsystem.
- docs/AGENT_DEUS_101.md — extended architecture and entrypoint map when you need depth.
Legacy note: CLAUDE.md still exists for Claude Code compatibility. It must mirror this file's intent, but this file is the source of truth.
Non-Negotiable Product Contract
Switching model or interface must not change the surrounding Deus experience. These must remain stable across backends:
- Identity, tone, and long-term user preferences.
- Memory and recall surfaces.
- Chat commands and CLI commands.
- Tool names, IPC semantics, and security boundaries.
- Scheduled task behavior and delivery.
- Credential isolation and filesystem boundaries.
Provider names are implementation detail unless the user explicitly asks about backend selection, billing, debugging, or provider-specific behavior.
Sources Of Truth
Resolve conflicts in this order:
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.
- yesterday First seen · 349 lines · 4,516 tokens per session scan B 6b77cd11af7c
Deus AGENTS.md is an instructions file published in the GitHub repository sliamh11/Deus (51 stars, last pushed yesterday), licensed MIT. It adds 4,516 tokens to every session, about $0.0226 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other instructions, from other repositories
mira-OSS AGENTS.md
AGENTS.md instructions for taylorsatula/mira-OSS, covering mira - python project guide, 🗺️ nested agents.md maintenance (mandatory), 🚨 critical principles (non-negotiable), technical integrity and security & reliability.
rawthink-mcp CLAUDE.md
Claude Code instructions for ygtalp/rawthink-mcp, covering rawthink — system directives, role, tone, thinking directives and epistemic transparency (end of each response).
openclaw-config AGENTS.md
AGENTS.md instructions for TechNickAI/openclaw-config, covering project context for ai assistants, project overview, tech stack, project structure and code conventions.
buddy CLAUDE.md
Instructions for Starting-over92/buddy, covering buddy — operating handbook, who's who, your workspace — buddy's one home, buddy's roles and how buddy talks to you.
openclaw-config CLAUDE.md
Claude Code instructions for TechNickAI/openclaw-config, a project described as: Give your AI assistant memory, skills, and autonomy. Persistent memory, integration skills, and autonomous workflows.
HOM-AIMOS AGENTS.md
AGENTS.md instructions for wallidsaydi-creator/HOM-AIMOS: This file is a public-tool compatibility entry point. It is not a second guidance authority.