How to Use: Jan Model Runtime Library Map from Library Inventory (No Invented Token Counts)

You pasted a messy Jan inventory and need a clean deliverable without invented numbers. This PromptDig prompt turns only what you already listed into a structured map or checklist for model runtime library map handoffs.

What this prompt does

It locks your inventory, version, workspace label, and domain fields, then builds a ledger plus a table that refuses fake metrics. Missing cells stay NOT IN INPUTS instead of guessing.

Use it when you already have real stubs from Jan and want a teachable map for this job, not a generic template swap from another vendor. The Generate steps name Jan nouns on purpose so a title swap into another category would fail the swap-title test.

The deliverable is aimed at Jan maps. Reviewers should see Inventory nouns echoed in the table rows, not marketing fluff. Cap style limits stay soft unless you add them later in Extra.

How to fill the brackets

1. Paste your Inventory with concrete nouns only. Prefer two labeled rows so the example shape stays visible after you swap names.
2. Lock Version to what you actually run. If you do not know the version, write unknown rather than guessing a marketing release name.
3. Fill Workspace and SpecNames only when you already have labels you are allowed to quote.
4. Complete the domain fields that match this job (ModelCues, RuntimeCues, and LibraryNotes). Leave blanks as UNKNOWN instead of inventing token counts, context windows, or runtime totals.
5. Set Banned and Never to the phrases you refuse. Keep Format and Lang explicit.

Who it is for

Builders who inherit messy Jan library inventories. It is also useful when a teammate hands you a partial export and you need a map that stays honest about gaps.

How to run it

1. Open Jan Model Runtime Library Map from Library Inventory (No Invented Token Counts) on PromptDig.
2. Copy the prompt into ChatGPT, Claude, or Gemini.
3. Replace every bracket with your locked fields.
4. Ask for the ledger first if you want a quick honesty check, then the full table.
5. Compare the output rows to your Inventory. Cut any invented token counts, context windows, or runtime totals.

What good output looks like

A strong run opens with an honesty ledger that restates your nouns, then a numbered map with one row per stub. Spec names stay limited to SpecNames. Version lock refuses features you did not name. The refuse list and compliance pass quote Banned and Never hits instead of inventing metrics.

If a cell was blank in Inputs, the model should write NOT IN INPUTS. That is success, not a failure.

Common mistakes

• Swapping in a Ollama or LM Studio workflow and keeping the same body. The prompt should teach Jan language.
• Asking the model to invent token counts, context windows, or runtime totals so the table looks complete. Refuse that and keep gaps visible.
• Pasting bare URLs without labeled links when you share the result. Prefer clear titles.

Why inventory-first maps beat guesswork

Most failed runs happen when the model fills empty cells with confident fiction. This prompt is built to refuse that pattern. It asks for an honesty ledger first so you can see which nouns were actually locked before any table rows appear.

Keep your Inventory short and concrete. Two labeled stubs are enough for a teachable example. If a teammate later adds more stubs, re-run with the same Version and SpecNames so the map stays comparable across handoffs.

When you share the result with a reviewer, point them at the refuse list and the gaps bullets. Those sections are the audit trail. They show what the model was not allowed to invent, which is the whole point of this PromptDig job.

Related links

• Open the live prompt: Jan Model Runtime Library Map from Library Inventory (No Invented Token Counts)
• Browse more prompts
• Share a prompt

Bottom line

Ship the map your Inventory already supports. Keep Jan nouns specific, keep invented metrics out, and leave missing fields marked so the next human can fill them for real.