Omnigraph is a graph database that stores operational context and coordination data in a lakehouse, combining graph traversal, vector search, and full-text search. It is designed for fleets of software agents that enrich shared knowledge on separate branches and merge reviewed changes; the catalogue add-ons help agents operate and coordinate through Omnigraph.
Borrowing it
Nothing to install: this file belongs to ModernRelay/omnigraph. 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/ModernRelay/omnigraph/main/AGENTS.mdgit clone --depth 1 https://github.com/ModernRelay/omnigraphWrote 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/modernrelay/omnigraph/agents-md)<a href="https://agentmods.dev/instructions/modernrelay/omnigraph/agents-md"><img src="https://agentmods.dev/badge/instructions/modernrelay/omnigraph/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/modernrelay/omnigraph/agents-md"><img src="https://agentmods.dev/badge/instructions/modernrelay/omnigraph/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 | $0.03346 | $0.03346 |
| Opus 5.5 | $0.01338 | $0.01338 |
| Sonnet 5.5 | $0.00669 | $0.00669 |
| Haiku 4.5 | $0.00335 | $0.00335 |
Grade A, and why
omnigraph AGENTS.md scanned grade A 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl -sL <url> | pandoc -f html -t markdown`. How it starts
The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Omnigraph agent guide
This file is the always-on map for coding agents. Keep it short: current detail
belongs in docs/, exact behavior in code and tests, decisions in RFCs, and
open work in issues.
Required reading
Before every task and every change:
- Read architectural invariants. Apply the hard invariants and deny-list to implementation and review work.
- Consult the domain map in Lance alignment. Fetch and
read the complete content of every page in the matching domain plus every
page that is even slightly relevant. The index and summaries are not
substitutes for the upstream pages. A reliable local form is
curl -sL <url> | pandoc -f html -t markdown. - Read testing. Find the existing owner and run a clean focused baseline before changing tests. Extend an existing assertion, fixture, or parameterization before creating a parallel setup.
Tools that support @ imports include these automatically:
@docs/dev/invariants.md @docs/dev/lance.md @docs/dev/testing.md
CLAUDE.md is a symlink to this file. Edit AGENTS.md only.
Repository snapshot
- Version surveyed: 0.14.1
- Rust stable, edition 2024; toolchain pinned in
rust-toolchain.toml - Storage substrate: Lance 13.0.0
- Workspace: compiler, planner (logical/physical plans and optimizer), storage,
omnigraph-core(the engine's shared base:OmniError, Lance dataset access, request instrumentation, Lance native ref control (branch_control), dataset addressing),omnigraph-catalog(the__manifestcatalog: graph branch registrations and lineage, the publish),omnigraph-seams(the one seam type every test-time substitution uses; RFC 0066), engine (omnigraph-enginepackage), policy, API types, cluster, CLI,omnigraph-skill(rooted atskills/; embeds theskills/omnigraphagent skill in the CLI and MCP),omnigraph-mcp(MCP protocol and catalog), server, Azure admission wrapper, benchmark harness,omnigraph-gqt(the.gqtlogic-test corpus and its runner; one libtest test per case), andomnigraph-dst(deterministic simulation testing; needs--cfg tokio_unstable, set by the workspace.cargo/config.tomlfor every build — the workspace test gate excludes the crate by name) - License: MIT
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.
- 5d ago Changed · +10 lines · +171 tokens per session 65c823feb351
- 9d ago Changed · +8 lines · +140 tokens per session 4197158000e7
- 15d ago Changed 8bb28be34467
- 16d ago Changed · +14 tokens per session 5367acc8b8b5
- 16d ago Changed 92e86100e7c2
- 21d ago Changed · +6 lines · +95 tokens per session 0115223e13cc
- 22d ago Changed fb9df078c665
- 26d ago Changed · +2 lines · +68 tokens per session 3a1427bd27d2
- 27d ago Changed · +4 lines · +78 tokens per session 609225be1318
- 28d ago First seen · 220 lines · 2,780 tokens per session scan A 8357d045b594
omnigraph AGENTS.md is an instructions file published in the GitHub repository ModernRelay/omnigraph (1,898 stars, last pushed today), licensed MIT. It adds 3,346 tokens to every session, about $0.0134 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
omnigraph AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| omnigraph AGENTS.mdModernRelay/omnigraph | Instructions file | 1.9k | today | MIT | A | 3,346 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |