# A CLAUDE.md for apps with no file system

> Put your working rules in the system prompt of Open WebUI, LM Studio or Jan, save them to the preset, and prove they loaded.

Page: https://videotomd.com/b/text-system-prompt-no-file-system/
Tool: LM Studio · Tags: lm-studio, open-webui, jan, system-prompt, presets · 623 words, about 810 tokens
Pills: free · ran in Claude Code · ran in Ollama · self-check · done check · checked 2026-10-12 · Open WebUI · LM Studio · Jan · Any text chat · Claude Code · Ollama · chat only · always on · 7B ok · coding

## Recipe

- Kind: runtime-config
- Stage: not set
- Loads: always on
- Works in: Open WebUI, LM Studio, Jan, Any text chat, Claude Code, Ollama
- Needs: chat only
- Bring: nothing
- Cost: free
- Model: 7B ok
- Tested in: Claude Code, Ollama
- Checked: 2026-10-12
- For: coding

## When this is useful
- You run a local model in Open WebUI, LM Studio or Jan and there is no file for it to read at startup.
- Every new chat forgets your rules, so you paste them again and sometimes forget.
- You want to know whether the rules are in the model's context or only in your head.


## Change it to
- Ollama: the same block goes in a Modelfile as `SYSTEM """..."""` with `PARAMETER num_ctx 8192`; the Ollama harness row gives the commands.
- Chat-only web app (ChatGPT, Claude.ai, Gemini): paste the block as the first message of each chat, or into the app's custom-instructions field where one exists.
- Short version for a 7B model: keep rules 1, 2 and 6 only; small models follow three rules better than six.
- Coding agent with a file system: this is `AGENTS.md` or `CLAUDE.md`; the harness rows give the path.


## If your AI needs to look something up
- Search: `open webui workspace models system prompt` and fetch https://docs.openwebui.com/features/workspace/models; `lm studio presets` and https://lmstudio.ai/docs/app/presets; `jan assistants instructions` and https://jan.ai/docs/desktop/assistants.


## Put it here

Always on: put it where your tool reads instructions every session:

- Open WebUI: Workspace → Models → your model → System Prompt: paste the text and save. Long reference goes in Knowledge and is retrieved, not always loaded. Reload: start a new chat. Check it loaded: the model's System Prompt field; ask the model to repeat one rule. Source: https://docs.openwebui.com/features/workspace/models (checked 2026-10-12).
- LM Studio: Paste the text into the System Prompt field, set the context length, and save it as a preset so it survives a restart. Server: http://localhost:1234/v1. Reload: reload the preset. Check it loaded: the preset in the app; ask the model to repeat one rule. Source: https://lmstudio.ai/docs/app/presets (checked 2026-10-12).
- Jan: Settings → Assistants → instructions: paste the text and save. Reload: new thread. Check it loaded: Settings → Assistants; ask the model to repeat one rule. Source: https://jan.ai/docs/desktop/assistants (checked 2026-10-12).
- Any text chat: Paste the whole file as your first message, then your task. A chat cannot read files or run commands: it must hand you the command and wait for the output. Reload: paste it again in a new chat. Check it loaded: ask it to repeat one rule from the file; a general answer means it is not in context. Source: https://videotomd.com/use-with-your-ai/ (checked 2026-10-12).
- Claude Code: Save as CLAUDE.md in the project root, or .claude/CLAUDE.md. Other agents share the repo: put the shared rules in AGENTS.md and make CLAUDE.md one line, @AGENTS.md. Commit it. Start a new session: the file is read at launch. Reload: new session (or /memory to open the files). Check it loaded: /context lists the Memory files it read; /skills, /agents, /hooks list the rest; the InstructionsLoaded hook event fires once per loaded instruction file. Source: https://code.claude.com/docs/en/memory (checked 2026-10-12).
- Ollama: Put the text in a Modelfile as SYSTEM """...""" with FROM <model> and PARAMETER num_ctx <n>, then `ollama create <name> -f Modelfile` and run <name>. Chat-only: paste it as the first message instead. Reload: ollama create again. Check it loaded: `ollama show --modelfile <name>` prints the SYSTEM; `ollama ps` shows the loaded context size. Source: https://docs.ollama.com/modelfile (checked 2026-10-12).

## Access

Membership: plans at https://videotomd.com/pricing/, or email then a plan at https://videotomd.com/b/text-system-prompt-no-file-system/. A member's browser downloads the file there; an AI without that session needs the member to attach it.