A float broke my refund rule, and Leviticus had an opinion

A developer built specdeck-spirit, a fork of the specdeck requirements tool that uses a local Gemma model to match the rationale behind each project rule to passages from a chosen spiritual text, surfacing kept passages in AGENTS.md and CLAUDE.md so coding agents see them alongside the rules. The tool ships with ten openly licensed English texts, including the King James Bible, Tanakh, Qur'an, Dhammapada, Bhagavad Gita, Kojiki, Tao Te Ching, Analects, Meditations and Book of Mormon, and accepts user-supplied texts via an add-text command. In the author's example, a rule banning floats in money code drew Leviticus 19:35 on just weights and measures from the Bible and Tanakh, a full-measure verse from Surah Hud in the Qur'an, and a rectification-of-names passage from the Analects, while the Kojiki and Book of Mormon returned no match.

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4 https://dev.to/challenges/hacktoberfest-week4-2026-10-26 I have a small tool called specdeck that keeps a project's rules as requirements, each with a statement, a reason and a check. Here's one from an example shop project. - id: rules.decimal-money statement: Money amounts shall be Decimal values, with no float anywhere in the shop package. rationale: A float total once made a refund one cent short and the accounts would not reconcile. For this week's challenge I added one layer on top. It takes the reason behind each rule and goes looking for it in a spiritual text you choose. When an agent then puts a float in the money code, this is what comes out. specdeck: rule rules.decimal-money broken "Ye shall do no unrighteousness in judgment, in meteyard, in weight, or in measure." Leviticus 19:35 FAILED tests/test rules.py::test money never touches float I know how that sounds. It's a little funny, and I think that's fine. But the verse is also correct. Somebody really did care about short measures thousands of years ago. specdeck-spirit https://github.com/BlaiseLabs/specdeck-spirit is a fork of specdeck. Everything specdeck does still works, and there's a new command on top. specdeck spirit fetch quran-pickthall specdeck spirit align --text quran-pickthall specdeck spirit show specdeck spirit keep rules.decimal-money specdeck spirit read For each reason in your spec and for the project's purpose, it proposes a passage, says how the passage bears on the reason, and suggests what to read further. You keep the ones that mean something to you and reject the rest. Passages you keep show up under the rule in AGENTS.md and CLAUDE.md, so the next agent session sees them too, and under the rule when it breaks. It comes with ten texts, which is what I could find openly licensed in English. That's the King James Bible, the Tanakh, the Qur'an, the Dhammapada, the Bhagavad Gita, the Kojiki, the Tao Te Ching, the Analects, the Meditations of Marcus Aurelius and the Book of Mormon. That list isn't a judgement about what counts, so specdeck spirit add-text takes any text of your own. To be plain about what's new, specdeck itself existed before this week. The spirit layer, its tests and the fork are what I built for this challenge. Here's the same rule, the same reason, and what came back from each text on a local Gemma. | Text | Passage for "a float made a refund one cent short" | |---|---| | Bible | "Ye shall do no unrighteousness in judgment, in meteyard, in weight, or in measure." Leviticus 19:35 | | Tanakh | The same verse, in the 1917 translation | | Qur'an | "O my people Give full measure and full weight in justice, and wrong not people in respect of their goods." Surah Hud 11:85 | | Dhammapada | "Life is hard for the conscientious, always seeking purity, neither clinging nor rude, pure of livelihood and discerning." Dhammapada 245 | | Analects | Confucius on rectifying names, because if names aren't correct, affairs can't succeed XIII.III | | Kojiki | No passage fits | | Book of Mormon | No passage fits | Each search only ever sees one text, so nothing here was comparing notes. The Bible and the Tanakh share that verse, so them agreeing makes sense, but the Qur'an got to the same idea through its own verse and the Analects got to something close from a completely different direction. An honest measure turns out to be a very old concern. The rule about tests landed somewhere I liked too. Its reason says a failing rule test is the rule being broken, not a flaky test to skip, and the Qur'an came back with "Confound not truth with falsehood, nor knowingly conceal the truth" Surah Al-Baqara 2:42 . The full output for ten texts is in SPIRIT.md https://github.com/BlaiseLabs/specdeck-spirit/blob/main/examples/agent-rules/SPIRIT.md . You can also clone the repo and run examples/agent-rules/spirit-demo.sh , which uses the saved results and doesn't need a model. A reason like "the float made a refund one cent short" shares no words with Leviticus, so plain search finds nothing. It takes three steps. The third step is the design decision I care about most. People read these as scripture, and a model that writes a verse that doesn't exist would be putting words in a holy text. So the model only ever answers with a number. The quote comes out of the fetched text, and specdeck spirit check compares every quote with the text again. There's a test that has the model try to slip in its own wording, and it can't. Being allowed to say nothing mattered as well. The prompt says none fitting is a fine answer, and 9 of the 50 reason and text pairs came back with no passage. The Kojiki declined three of its five, which seems right for a chronicle of deities when you ask it about internationalization. Choices go in a spirit.yaml you commit with your project. A passage stays a proposal until a person keeps it, one you reject isn't offered again, and if a reason changes, check tells you the passage is out of date. I wanted some check that this wasn't just pattern matching on nothing. For each passage it chose, I gave Gemma that passage and a random one from the same text, with no sign of which was which, and asked it to score each from 0 to 3 on whether it speaks to the concern. Chosen passages averaged 1.98 and random ones 0.49, and the chosen one scored higher in 32 of 41. That's the same model marking its own homework, so all it shows is that it beats chance. Reading through them, some are good and some are a stretch. Leviticus 19:35 came back for a rule about UTC timestamps too, and that's mostly the word "measure" doing the work. And all 41 passages affirmed the reason. The prompt allows a passage to challenge you, and none did, which I'd like to fix, since a text that only ever agrees with you isn't doing much. I should say this wasn't my plan for the week. I spent most of it on a project that tried to rewrite LLM code into lines humans had already written, using an index of millions of Python files. It kept not working, but it did teach me something. In one small program, the person's request decided at most 10 of 70 observable behaviours and the model decided 58 on its own. What gets lost with LLM code isn't so much who typed it. It's the why. Then I ran out of time, and I had a tool that already stores the why. Honoring the past is part of this week's prompt, and these are about the oldest writings on why anyone should bother doing things right. One limit comes with that. Old translations are the ones anyone may share, so they carry the views of their translators, and many Muslims hold that a translation of the Qur'an is an interpretation and not the Qur'an itself. This isn't religious advice either. A model finding a connection doesn't mean a tradition teaches it. The challenge's closing date is Halloween, right as Día de los Muertos begins, and both are about the dead still having something to say to us. I think that's what this is, in a small and slightly ridiculous way. Somebody wrote down that a false weight is wrong long before anyone had a refund to get wrong, and now it prints under my test failure. A fork of specdeck https://github.com/BlaiseLabs/specdeck that reads the why of each rule in your spec next to a spiritual text you choose. specdeck keeps each rule as a requirement with a statement, a reason and a check. This fork adds one layer on top of those reasons. For each one, open models running on your own machine look through the Bible, the Qur'an, the Dhammapada, the Kojiki or any text you add, and propose the passage that speaks to it. You keep the ones that mean something to you and reject the rest. When a rule breaks, its passage is printed under it. specdeck: rule rules.decimal-money broken "Ye shall do no unrighteousness in judgment, in meteyard, in weight, or in measure." Leviticus 19:35 Everything else specdeck does is unchanged, and it's all documented below the line further down. You need Ollama https://ollama.com with two open models. ollama pull gemma4:12b-it-qat … The original, without the spirit layer, is at BlaiseLabs/specdeck https://github.com/BlaiseLabs/specdeck . I built this with a lot of help from an AI coding assistant. The idea and the design decisions are mine.