agentmods.dev

ODS CLAUDE.md

ODS CLAUDE.md is an instructions file for coding agents from Osmantic/ODS. It costs 2,157 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for ODS, a fully local AI stack that runs language models, chat, voice, agents, workflows, retrieval-augmented generation, image creation, and privacy tools on a user’s hardware. They describe its Bash, Python, and React/Vite code and installation structure.

In plain words
What is it for?
Use them when changing installation scripts, hardware and operating-system support, dashboard services, AI features, or the web interface.
Why use it?
They show an agent where the installer, services, dashboard, platform-specific code, and deployment steps belong.

Instructions file

5.8k +674 2d ago A scan 2,157 tokens original Apache-2.0
View the source file Osmantic/ODS
Install

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.

agentmods
npx agentmods add instructions/osmantic/ods/claude-md
Clone the repo
git clone --depth 1 https://github.com/Osmantic/ODS
Per session 2,157 This file is loaded in full into every session.
When invoked 2,157 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.02157 $0.02157
Opus 5 $0.01078 $0.01078
Sonnet 5 $0.00431 $0.00431
Haiku 4.5 $0.00216 $0.00216

Measured 3d ago against content hash 5ac1b6216930, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

CLAUDE.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 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 order
  • installers/lib/ — pure function libraries (constants, logging, UI, GPU detection, tier mapping, packaging, compose selection)
  • installers/phases/ — 13 sequential install steps (01-preflight through 13-summary), each sourced by install-core
  • installers/macos/, installers/windows/ — platform-specific installer variants
  • extensions/services/ — 24 bundled service manifests, each a directory with manifest.yaml + optional compose.yaml and GPU overlays
  • extensions/library/ — optional extension catalog, templates, workflows, and manifest schema used by the dashboard Extensions page
  • docker-compose.base.yml — core service definitions; docker-compose.{amd,nvidia,apple}.yml are GPU overlays
  • ods-cli — main Bash CLI for managing the stack; keep changes narrow and follow docs/ODS_CLI_DECOMPOSITION.md for behavior-preserving split work
  • config/ — backend configs (backends/amd.json, nvidia.json, etc.), GPU database, LiteLLM config, hardware classes
  • extensions/services/dashboard-api/ — Python FastAPI backend (with routers/, 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)

Read the full file on GitHub · 164 lines

Changes

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.

  1. 3d ago First seen · 164 lines · 2,157 tokens per session scan A 5ac1b6216930

Subscribe to this mod's changes

ODS CLAUDE.md is an instructions file published in the GitHub repository Osmantic/ODS (5,819 stars, last pushed 2d ago), licensed Apache-2.0. It adds 2,157 tokens to every session, about $0.0108 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 2026-08-30.

LLMai-agentsamdcomfyuidockerself-hosted
Related

Other instructions, from other repositories

tianji AGENTS.md

Instructions for msgbyte/tianji, covering contributor guide, development tips, translation files, testing instructions and pr instructions.

msgbyte/tianji · 228 tokens

meme-search CLAUDE.md

Instructions for neonwatty/meme-search, covering claude.md, 📁 file organization guidelines, 🤖 task agent usage guidelines, when to use task agents and documentation lookup pattern.

neonwatty/meme-search · 2,697 tokens

sandboxd AGENTS.md

Instructions for tastyeffectco/sandboxd, covering agents.md — operating sandboxd, what this is, prerequisites, install and core api.

tastyeffectco/sandboxd · 2,187 tokens

homelab-monitor CLAUDE.md

Instructions for SikamikanikoBG/homelab-monitor, covering claude.md and conventions.

SikamikanikoBG/homelab-monitor · 138 tokens

moira AGENTS.md

Instructions for moira-mcp/moira, covering agents.md, what moira is, repository layout, build & run (fresh clone) and image: line and uncomment the build: block, then.

moira-mcp/moira · 3,583 tokens

piper CLAUDE.md

Instructions for piperbox/piper, covering claude.md, what this is, coding principles, 1. think before coding and 2. simplicity first.

piperbox/piper · 2,684 tokens