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.
npx agentmods add instructions/philipp-lm/viableos/claude-mdgit clone --depth 1 https://github.com/philipp-lm/ViableOSWrote 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/philipp-lm/viableos/claude-md)<a href="https://agentmods.dev/instructions/philipp-lm/viableos/claude-md"><img src="https://agentmods.dev/badge/instructions/philipp-lm/viableos/claude-md.svg" alt="Measured on agentmods" 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 | $0.01027 | $0.01027 |
| Opus 5 | $0.00513 | $0.00513 |
| Sonnet 5 | $0.00205 | $0.00205 |
| Haiku 4.5 | $0.00103 | $0.00103 |
Grade A, and why
ViableOS 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 6d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — ViableOS
Projekt
ViableOS — "The operating system for viable AI agent organizations." Design-Tool das Organisationen auf Basis des Viable System Model (VSM) strukturiert und Agent-Konfigurationen generiert.
Tech Stack
- Backend: Python 3.10+, FastAPI, LiteLLM, PyMuPDF
- Frontend: React 19, TypeScript, Vite, Tailwind CSS 4, Zustand
- Kein DB — alles in-memory (Sessions, FileStore). Ephemeral by design.
Architektur
src/viableos/
├── api/
│ ├── chat_routes.py # Chat SSE streaming + file upload
│ └── routes.py # Wizard/config API endpoints
├── chat/
│ ├── engine.py # LiteLLM streaming, multimodal messages
│ ├── session.py # In-memory session + message store
│ ├── files.py # FileStore: PDF/image/text upload processing
│ └── system_prompt.py # 650-line VSM expert prompt (NEVER expose theory to user)
├── checker.py # Viability checks (S1-S5) + community warnings
├── assessment_transformer.py # Assessment JSON → viable_system config
├── budget.py # Token budget calculation
├── coordination.py # Auto-generated coordination rules
├── generator.py # OpenClaw package generator
└── langgraph_generator.py
frontend/src/
├── components/chat/ # ChatWindow, MessageBubble, ProviderSelector, AssessmentPreview
├── components/wizard/ # 6-step wizard (Template→Units→Budget→Identity→HITL→Review)
├── store/ # Zustand stores (useChatStore, useConfigStore)
├── api/client.ts # Typed API client
└── types/index.ts # All TypeScript interfaces
Chat Flow
- User chattet mit VSM-Experte (LiteLLM streaming via SSE)
- Kann PDFs, Screenshots, Dateien hochladen (drag&drop, paste, paperclip)
- LLM führt 4-Phasen Assessment-Interview
- "Finalize Assessment" extrahiert JSON aus letzter Assistant-Message
- "Use in Wizard" transformiert → öffnet Config-Wizard
- Wizard Step 6 (ReviewStep) ruft
/api/checkfür Viability-Report
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.
- 6d ago First seen · 100 lines · 1,027 tokens per session scan A faa7bd7dee5d
ViableOS CLAUDE.md is an instructions file published in the GitHub repository philipp-lm/ViableOS (10 stars, last pushed 6mo ago), licensed MIT. It adds 1,027 tokens to every session, about $0.0051 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 2026-08-31.
Other instructions, from other repositories
takt AGENTS.md
AGENTS.md instructions for nrslib/takt, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
rondoflow CLAUDE.md
Claude Code instructions for rondoflow/rondoflow, covering rondoflow, project overview, tech stack, development and setup.
dos-kernel AGENTS.md
Instructions for anthony-chaudhary/dos-kernel, covering what dos is (the 30-second version), run it yourself first — the 60-second proof, when the user asks you about dos (the consumer moves), build, test, and check your work and the layout in one screen.
PuPu CLAUDE.md
Claude Code instructions for haoxiang-xu/PuPu, covering gitnexus — code intelligence, always do, never do, resources and cli.
dos-kernel GEMINI.md
Instructions for anthony-chaudhary/dos-kernel, covering dos — the part that doesn't believe the agents, the rule, why this matters and setup.
claude-org-ja CLAUDE.md
Claude Code instructions for suisya-systems/claude-org-ja, covering secretary, 事実は出典付きで書く（citation-or-abstain）, 起動時, コミュニケーション and 輸送層（transport）両系 — 既定 renga / opt-in broker.