Borrowing it
Nothing to install: this file belongs to getomnico/omni. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/getomnico/omni/master/AGENTS.mdgit clone --depth 1 https://github.com/getomnico/omniWrote 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/getomnico/omni/agents-md)<a href="https://agentmods.dev/instructions/getomnico/omni/agents-md"><img src="https://agentmods.dev/badge/instructions/getomnico/omni/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/getomnico/omni/agents-md"><img src="https://agentmods.dev/badge/instructions/getomnico/omni/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.02148 | $0.02148 |
| Opus 5.5 | $0.00859 | $0.00859 |
| Sonnet 5.5 | $0.00430 | $0.00430 |
| Haiku 4.5 | $0.00215 | $0.00215 |
Grade A, and why
omni 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 1mo 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Omni
Omni is an open-source, self-hosted AI agent for the workplace. It connects to the apps a team already uses (Google Drive, Gmail, Slack, Confluence, etc.), syncs their data into a unified BM25 and pgvector index, and provides an agent harness that can search, reason over, and act on that data using any major cloud or private (self-hosted) model provider.
Core Philosophy
The core philosophy behind the project is simplicity: use Postgres (ParadeDB) as the primary application storage system and hybrid (text + vector) search index, minimizing operational complexity.
Features
- Built-in connectors that sync workplace app data through source-appropriate polling or webhook mechanisms (Google Drive, Gmail, Slack, Confluence, Jira, and many more), with one container per connector
- Each connector can sync data across multiple related apps. E.g., the google connector syncs data from Drive, Gmail and Chat.
- An agent harness (omni-ai) that orchestrates LLM agents with tools for index search, file download, bash/python execution, and more, including auto-compaction, context management and memory
- A unified index (BM25 + pgvector) over all connected sources, with a search UI and LLM summarization of results
- Model flexibility: works with all major cloud LLM providers (OpenAI, Anthropic, Gemini, AWS Bedrock, etc.) as well as private/self-hosted models, plus pluggable embedding providers (Jina AI, Cohere, OpenAI, etc.)
- A web-based chat UI for interacting with the agent.
Architecture
Omni's main application services run as separate containers, alongside one container per connector.
Why one container per connector? To allow developers full control over packaging their dependencies without affecting other connectors.
Core Services & Code Organization
- All core services are under services/ and web/ a. omni-searcher (services/searcher): handles all index search requests b. omni-indexer (services/indexer): handles all writes to the index c. omni-ai (services/ai): orchestrates all LLM interactions, agents d. omni-web (web/): frontend SvelteKit app e. omni-connector-manager (services/connector-manager): orchestrates all connector containers f. omni-sandbox (services/sandbox): Sandbox container for bash and python execution, file manipulation
- One container per connector, built-in connectors are in connectors/ a. omni-google-connector (drive & gmail) b. omni-slack-connector c. omni-atlassian-connector (confluence & jira), and so on
- Connector SDKs in Python, TypeScript and Rust under sdk/
- Database migrations: services/migrations.
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.
- 1mo ago Changed · +5 lines · +96 tokens per session 848d5fd8d14e
- 1mo ago First seen · 125 lines · 2,052 tokens per session scan A 7e7accb3a0db
omni AGENTS.md is an instructions file published in the GitHub repository getomnico/omni (807 stars, last pushed 26d ago), licensed Apache-2.0. It adds 2,148 tokens to every session, about $0.0086 per session on Opus 5.5. 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 2026-09-03.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.