agentleFS
Sign inStart free
AstralumeLanAstralumeLan/prophet-toolkit/llms.txt

prophet-toolkit

llms.txt1 starsChanged 12 days agoMITView on GitHub

Offline JSON CLI for traditional divination, astrology, and source retrieval. Explicit rules, warnings, and time uncertainty; fictional examples only. Prophet is for cultural research and reproducible algorithm comparisons. Runtime is offline after dependency setup. Calculations and historical texts do not establish predictive validity. Preserve privacy and third-party licences.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 1

    1. AstralumeLan/Prophet-toolkit★ 1100% same

    Edited · 0

    None found.

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository5 other files it gives its agents.

The file

Create a free account to mount
Files
llms.txt
# Prophet v0.2.0

> Offline JSON CLI for traditional divination, astrology, and source retrieval. Explicit rules, warnings, and time uncertainty; fictional examples only.

Prophet is for cultural research and reproducible algorithm comparisons. Runtime is
offline after dependency setup. Calculations and historical texts do not establish
predictive validity. Preserve privacy and third-party licences.

## Start here

- [English overview](README.en.md): Installation, engines, and examples.
- [AI client guide](docs/for-ai.md): Tool manifest, MCP configuration, schemas, and workflow.
- [Agent instructions](AGENTS.md): Setup, tests, contribution rules, and invariants.
- [Output schemas](schemas/): Generated JSON Schema contracts per CLI command.
- [Shared design](docs/SPEC.md): Layering, contracts, uncertainty, and validation.
- [Inputs and persistence](docs/core.md): Precision, solar time, cache and draw policies.

## Engines

- [Bazi](docs/bazi.md): Pillars, periods, and daily queries.
- [Ziwei](docs/ziwei.md): Charts, comparisons, and horoscopes.
- [Liuyao](docs/liuyao.md): Manual, time, and coin methods.
- [Meihua](docs/meihua.md): Time, numbers, and random methods.
- [Qimen](docs/qimen.md): Declared chart methods and rules.
- [Huangli](docs/huangli.md): Day and hour calendar fields.
- [Western astrology](docs/western.md): Natal and related calculations.
- [Tarot](docs/tarot.md): RWS card lookup and reusable draws.
- [Vedic astrology](docs/vedic.md): Lahiri charts, periods, and strength.

## Sources and validation

- [Corpus](docs/corpus.md): Local search, neighbours, provenance, and opt-in restrictions.
- [Validation](docs/validate.md): Comparison scope and shared dependency caveats.
- [Third-party notices](THIRD_PARTY_NOTICES.md): Licences and source attribution.

## Optional

- [Full documentation](llms-full.txt): Concatenated public technical docs.
- [Changelog](CHANGELOG.md): Version history.
- [Security](SECURITY.md): Supported releases and private reporting.
- [Conduct](CODE_OF_CONDUCT.md): Community standards.

## Agent Skills, Evidence and Cross-check

- [Workflow and evidence contract](docs/agent-workflows.md): CLI, JSON paths, limits and review.
- [Bazi skill](skills/bazi/SKILL.md): Staged analysis and evidence critic.
- [Ziwei skill](skills/ziwei/SKILL.md): Palaces, transformations, timing and critic.
- [Cross-check skill](skills/cross-check/SKILL.md): Independent interpretations and qualified comparisons.
- [Evidence item schema](schemas/evidence-item.schema.json): Required claim metadata.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free