Borrowing it
Nothing to install: this file belongs to omnirexflora-labs/omnicoreagent. 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/omnirexflora-labs/omnicoreagent/main/AGENTS.mdgit clone --depth 1 https://github.com/omnirexflora-labs/omnicoreagentWrote 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/omnirexflora-labs/omnicoreagent/agents-md)<a href="https://agentmods.dev/instructions/omnirexflora-labs/omnicoreagent/agents-md"><img src="https://agentmods.dev/badge/instructions/omnirexflora-labs/omnicoreagent/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/omnirexflora-labs/omnicoreagent/agents-md"><img src="https://agentmods.dev/badge/instructions/omnirexflora-labs/omnicoreagent/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 | $0.01120 | $0.01120 |
| Opus 5.5 | $0.00448 | $0.00448 |
| Sonnet 5.5 | $0.00224 | $0.00224 |
| Haiku 4.5 | $0.00112 | $0.00112 |
Grade A, and why
omnicoreagent 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 10d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — a map of OmniCoreAgent for coding agents
OmniCoreAgent is an open agent runtime for Python. It includes the harness (the loop, tools, memory, workspace and sub-agents) and adds the policy, sandbox, durable run record, budgets and the evidence of every run. This file tells an agent where things are and how to work here. People are welcome too; the README is the tour.
Answer a question from the right place
| You want to know | Look in |
|---|---|
| How to use a feature | docs/ — the published docs; start at docs/index.mdx; the nav is docs.json at the repository root, not in docs/ |
| What an option does, exactly | the source it is defined in (below); every setting has a comment |
| Why something is built the way it is | engineering/architecture/ — one plan per piece of work, with the decisions |
| What broke in real use and how it was fixed | engineering/validation/production-proving.md |
| A complete, runnable example | cookbook/ and apps/steward/ |
Where the code is
Everything is under src/omnicoreagent/.
| Package | What it holds | Start at |
|---|---|---|
core/runtime/ |
OmniCoreAgent, its configuration (AgentConfig and friends) |
omnicore_agent.py, config.py |
core/agents/ |
the loop: steps, model calls, tool calls, the final answer | base.py, llm_step.py, native_tools.py |
core/tools/ |
local tools, the execute tool, code mode (Monty), result offloading |
local_tools_registry.py, code_mode.py |
core/telemetry/ |
traces, the trajectory builder, stores, exporters, redaction | recorder.py, trajectory.py |
core/memory_store/, core/workspace/ |
session memory backends; the agent's files | |
core/guardrails/, core/skills/, core/summarizer/ |
prompt-injection guard; skills; context summaries | |
core/credentials.py |
the runtime's own credentials, kept from the model and every record | |
governance/ |
policies (allow, ask, deny), approvals, budgets, capability descriptors | defaults.py, capabilities.py |
sandbox/ |
sandbox providers: Docker, E2B, Modal, Daytona, Vercel, HTTP, local |
base.py |
mcp_clients_connection/ |
MCP client: transports, OAuth, reconnects | client.py |
background/ |
scheduled and manual background runs, task stores | |
serve/ |
OmniServe: the REST/SSE server and its CLI (omniserve) |
|
cli/ |
the omnicoreagent CLI: run (headless) and harbor |
__init__.py, headless.py, harbor.py |
harbor/ |
running this agent on Harbor / Terminal-Bench | agent.py, trial.py |
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.
- 10d ago Changed · +1 tokens per session 6d1a016bdd52
- 16d ago Changed · +15 tokens per session 570593ebeb67
- 19d ago Changed · +5 tokens per session 0ee4d8f6cc11
- 20d ago First seen · 70 lines · 1,099 tokens per session scan A abe818433598
omnicoreagent AGENTS.md is an instructions file published in the GitHub repository omnirexflora-labs/omnicoreagent (252 stars, last pushed 6d ago), licensed MIT. It adds 1,120 tokens to every session, about $0.0045 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 2026-09-26.
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.
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.
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).