unit-cost
Skill2 starsChanged 25 days agoMITView on GitHub
Use when a printed SKU needs a unit-cost sheet (filament grams x price, machine time, labour, packaging, fees, shipping) before pricing. Runs the business-strategist in a fresh context and writes a reproducible cost script, table and CSV with a source and date on every input.
In this repository30 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- agent-reviewSkill
- ai-mesh-cleanSkill
- cad-buildSkill
- couponSkill
- curriculumSkill
- dfm-reviewSkill
- fileSkill
- gddSkill
- ip-checkSkill
- led-budgetSkill
- lesson-learnedSkill
- makerworld-publishSkill
- material-pickSkill
- mcp-new-toolSkill
- ortho-sheetSkill
- pi-power-budgetSkill
- preprint-checkSkill
- promo-planSkill
- qa-gateSkill
- render-criticSkill
- research-oneSkill
- research-topicSkill
- retopoSkill
- safety-sheetSkill
- sculptSkill
- slicer-questionSkill
- style-bibleSkill
- tech-packSkill
- verifySkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Before any price is quoted or listed for a printed part.
- Very specific: line 22
Write unit-cost.py: an INPUTS dict where every entry carries value, unit, condition, source_url, fetched.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Overview
Cost: $ARGUMENTS
Output on disk, in the project folder you name (default work\costing\<sku-slug>\): unit-cost.md, unit-cost.py, unit-cost.csv, and (if any input could not be fetched) research\inbox\business\unit-cost-<sku-slug>.md.
When to use
Before any price is quoted or listed for a printed part. Not for garments (POD quotes belong in /tech-pack), not for MakerWorld earnings (/makerworld-publish).
Steps
- Locate the slice. If the argument is a
.3mf, slice it with.venv\Scripts\python.exe tools\slice_cli.py <file.3mf>as described inknowledge\02-bambu-studio\cli-slicing.mdand readwork\slice\<stem>\result.json. Noresult.json, no sheet: stop and return "NEEDS: slice" with the exact command. - From
result.jsontake grams per filament and print time; record the 3MF path, profile name and printer model (fromknowledge\00-gear-inventory\) as the condition on those numbers. - Material price: fetch the filament's product page (https://us.store.bambulab.com/ or your regional Bambu store, or the vendor page for third-party spools) this run; record price per spool and net weight with the fetch date. Compute price per gram in the script, not by hand.
- Machine time: inputs are printer purchase price, assumed service hours, maintenance per hour and electricity (printer draw x rate). Each is a fetched value with URL or a
NEEDS MAKERplaceholder in the inputs dict; never a silent default. Structure follows https://formlabs.com/blog/how-to-calculate-3d-printer-cost/. - Labour (rate
NEEDS MAKER, minutes per unit from the batch plan), consumables, packaging (box, filler, label with vendor URL), shipping (fetch your carrier's service page, with weight and zone as the condition), channel fees (fetch https://www.etsy.com/legal/fees, https://www.shopify.com/pricing, or the MakerWorld terms pages). - Write
unit-cost.py: anINPUTSdict where every entry carriesvalue,unit,condition,source_url,fetched; functions per bucket; a margin table at three candidate prices after fees and shipping. Run it with.venv\Scripts\python.exe; it writesunit-cost.mdandunit-cost.csv. - Any input marked "not verified" goes as a row into
research\inbox\business\unit-cost-<sku-slug>.mdfor/verify. Return paths, the script's printed output, and numbered NEEDS MAKER questions.
Common rationalizations
| Rationalization | Reality |
| "Forty grams is a fair guess for a part this size." | Grams come from result.json. A guessed size can hide a print many times longer than planned. |
| "I know the spool price." | Prices change; fetch the product page this run and record the date. |
| "Labour at zero keeps it simple." | It hides the margin. Use a named NEEDS MAKER rate. |
| "I'll type the numbers into the table directly." | Every number in unit-cost.md is produced by unit-cost.py; otherwise it cannot be reproduced or audited. |
Red flags (stop and fix)
- A number in the table that the script did not print.
- An input without URL and fetch date that is not marked
NEEDS MAKERor "not verified". - Grams or hours with no
result.jsonpath. - A margin that omits fees or shipping.
Verification
result.jsonpath and 3MF path recorded inunit-cost.md..venv\Scripts\python.exe <output folder>\unit-cost.pyruns clean; output pasted in the return.- Every
INPUTSentry hassource_urlandfetched, or isNEEDS MAKER/ "not verified". - Margin table shows three prices after fees and shipping.
- Inbox claims file written if anything is "not verified"; paths returned.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

