← ~/library/ lm-studio /
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.
11 steps · 623 words · Markdown format · Reviewed 2026-10-12
Tools: freeran in Claude Coderan in Ollamaself-checkdone checkchecked 2026-10-12Open WebUILM StudioJanAny text chatClaude CodeOllamachat onlyalways on7B okcoding
What the pill colors mean
- paidfree alternativefree what running it costs you beyond the file: a paid service, a paid service with a free route (hover it), or nothing
- DockerAPI key what you must bring: software, an account or a key
- ran in (tool)self-checkdone check evidence: we ran it in that tool, or the file carries its own check
- checked 2026-10-12 the day it was last checked against official docs; not a run
- Any AI where it works; each brief page says where to put it
- shellchat only what your AI app must be able to do
- on demand when your AI reads it
- frontier the smallest model it was written for
- codingbuilding what it is for, and the build stage it fits
Checking access…
Get this brief
Checkout is temporarily unavailable. Read the skills sample or try the hooks sample. Free for any AI.
/library
Library
Start here for your next AI project.
$9 / month
- Pick any individual .mds and packs
- All 492 library briefs and new additions
- 2 video-to-.md conversions every month
- Early-member price. It is planned to move to $15 in one or two months; if you subscribe now your price stays $9 for as long as you stay subscribed.
- Cancel any time
/library-plus-video
Library + 5 videos
Turn your video backlog into next steps.
$15 / month
- Everything in Library
- 5 total video-to-.md conversions every month
- Reviewed and delivered to your email
- Cancel any time
/daily-video
Library + daily videos
Something new to build, every day.
$20 / month
- Everything in Library
- At least one video a day, more as capacity allows
- One video processed at a time
- Cancel any time
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
Checked against the official page on 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
Checked against the official page on 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
Checked against the official page on 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
Checked against the official page on 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
Checked against the official page on 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
Checked against the official page on 2026-10-12.