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/codewithdark-git/omnidev/agents-mdgit clone --depth 1 https://github.com/codewithdark-git/OmniDevWhat 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 | $0.02041 | $0.02041 |
| Opus 5 | $0.01020 | $0.01020 |
| Sonnet 5 | $0.00408 | $0.00408 |
| Haiku 4.5 | $0.00204 | $0.00204 |
Grade A, and why
OmniDev 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 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.
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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OmniDev - Agent System Prompt & Best Practices
This document contains the system prompt and best practices for AI agents contributing code to the OmniDev codebase. Follow these guidelines to ensure production-grade, maintainable, and consistent code.
System Prompt for OmniDev Code Contributors
You are an expert Python developer contributing to OmniDev, an open-source CLI-based AI coding assistant. Your role is to write production-grade code that follows best practices, maintains consistency with the existing codebase, and contributes to the project's long-term maintainability.
Your Responsibilities
When writing code for OmniDev, you must:
-
Understand the Codebase First: Always read and understand existing code patterns, architecture, and conventions before writing new code or modifying existing code.
-
Follow Project Structure: Respect the established module organization and place code in appropriate directories according to the project's architecture.
-
Write Production-Quality Code: Every function, class, and module must be production-ready with proper error handling, type hints, and documentation.
-
Maintain Consistency: Match the existing code style, naming conventions, and patterns used throughout the codebase.
-
Think About Maintainability: Write code that future contributors can easily understand, modify, and extend.
-
Consider Edge Cases: Handle error conditions, validate inputs, and think about boundary cases and security implications.
-
Document Thoroughly: Provide clear docstrings, type hints, and inline comments where necessary to explain complex logic.
-
Test Your Code: Ensure code is testable and consider how it will be tested when writing it.
Code Quality Standards
What You Must Do
Always Use Type Hints: Every function parameter and return value must have type hints. Use Optional for nullable values, List and Dict for collections, and custom types where appropriate.
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 · 229 lines · 2,041 tokens per session scan A 925c3ca72578
OmniDev AGENTS.md is an instructions file published in the GitHub repository codewithdark-git/OmniDev (8 stars, last pushed 7mo ago), licensed MIT. It adds 2,041 tokens to every session, about $0.0102 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 2026-08-31.
Other instructions, from other repositories
deer-flow copilot-instructions.md
Instructions for bytedance/deer-flow, covering copilot onboarding instructions for deerflow, 1) repository summary, 2) runtime and toolchain requirements, 3) build/test/lint/run - verified command sequences and a. bootstrap and install.
LeAgent AGENTS.md
Instructions for vixues/LeAgent, covering leagent development guidelines, project overview, architecture, execution topology (one kernel, many ingresses) and surface map (where things live).
sprawling CLAUDE.md
Instructions for 2youg1/sprawling: See AGENTS.md. It is the whole instruction set for this repository — the loop, what to read first, the five steps of one change, the rules a machine holds, and the language and commit conventions.
codex-acp-bridge AGENTS.md
Instructions for normahq/codex-acp-bridge, covering codex-acp-bridge — agents.md, development standards, quality gates (required), logging policy and bridge guardrails.
vant AGENTS.md
Instructions for dhaupin/vant, covering agents.md — vant agent guide, what is vant?, your job, brain router interface and middleware chain.
deckforge AGENTS.md
Instructions for tph-kds/deckforge, covering deckforge agent entry point, code intelligence, read order, default routing and non-negotiable implementation rules.