ODS is a system for turning a PC, Mac, or Linux computer into a private local AI server, meaning a machine that runs models and related AI services itself. It supports local model inference, chat, voice, agents, workflows, document retrieval, search, and image generation. The catalogue includes commands and an instruction for operating or configuring this system.
Borrowing it
Nothing to install: this file belongs to Osmantic/ODS. 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/Osmantic/ODS/main/CLAUDE.mdgit clone --depth 1 https://github.com/Osmantic/ODSWrote 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/osmantic/ods/claude-md)<a href="https://agentmods.dev/instructions/osmantic/ods/claude-md"><img src="https://agentmods.dev/badge/instructions/osmantic/ods/claude-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/osmantic/ods/claude-md"><img src="https://agentmods.dev/badge/instructions/osmantic/ods/claude-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 | $0.02312 | $0.02312 |
| Opus 5.5 | $0.00925 | $0.00925 |
| Sonnet 5.5 | $0.00462 | $0.00462 |
| Haiku 4.5 | $0.00231 | $0.00231 |
Grade A, and why
ODS CLAUDE.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 23d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
ODS is a fully local AI stack (LLM inference, chat, voice, agents, workflows, RAG, image generation, privacy tools) deployed on user hardware with a single command. It supports Linux (NVIDIA + AMD), Windows (WSL2), and macOS (Apple Silicon). The project is primarily Bash (installer/CLI), Python (dashboard-api, services), and React/Vite (dashboard UI).
Repository Structure
The repo has two layers:
- Root level — outer wrapper with top-level README, install scripts (
install.sh,install.ps1), and CI workflows (.github/workflows/) ods/— the core product containing all deployable code
Within ods/:
install-core.sh— thin orchestrator that sources libs then runs phases in orderinstallers/lib/— pure function libraries (constants, logging, UI, GPU detection, tier mapping, packaging, compose selection)installers/phases/— 14 sequential phase files (01-preflightthrough13-summary, plus02b-external-services), each sourced by install-coreinstallers/macos/,installers/windows/— platform-specific installer variantsextensions/services/— 31 bundled services, each a directory withmanifest.yaml+ optionalcompose.yamland GPU overlaysextensions/library/— optional extension catalog, templates, workflows, and manifest schema used by the dashboard Extensions pagedocker-compose.base.yml— core service definitions;docker-compose.{amd,nvidia,apple}.ymlare GPU overlaysods-cli— main Bash CLI for managing the stack; keep changes narrow and followdocs/ODS_CLI_DECOMPOSITION.mdfor behavior-preserving split workconfig/— backend configs (backends/amd.json,nvidia.json, etc.), GPU database, LiteLLM config, hardware classesextensions/services/dashboard-api/— Python FastAPI backend (withrouters/,tests/)extensions/services/dashboard/— React + Vite + Tailwind frontend (src/)scripts/— operational scripts (health checks, model management, compose stack resolution, doctor, preflight)tests/— shell-based tests (tier map, contracts, smoke tests, integration)lib/— shared Bash utilities (safe-env, service-registry, progress, QR code)
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.
- 23d ago Changed 923eb309d503
- 24d ago Changed · +3 lines · +155 tokens per session 2ccd2c855ce8
- 2mo ago First seen · 164 lines · 2,157 tokens per session scan A 5ac1b6216930
ODS CLAUDE.md is an instructions file published in the GitHub repository Osmantic/ODS (7,712 stars, last pushed today), licensed Apache-2.0. It adds 2,312 tokens to every session, about $0.0092 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 2026-08-30.
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.