agentleFS
Sign inStart free
alainatoralainator/worldcodex/CLAUDE.md

worldcodex

CLAUDE.md2 starsChanged 7 months agoMITView on GitHub

Evidence hierarchy: canon source > derived lore page > cross-referenced inference > "it feels right." Mechanism over association: if you can't state the causal chain back to foundational physics/biology, it's not proven. Only the author pushes changes. Claude Code proposes via clearly marked suggestions. Never commit, push, or overwrite canon-status files without explicit author approval.

The file

We split this CLAUDE.md into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use in-universe terminology in science files, human-readable names only in narrative/applied content

    line 11
  2. Distinctive:

    Do NOT commit, push, or overwrite canon files without explicit author approval

    line 17
  3. Distinctive:

    After writing: update _index.md, GLOSSARY.md, MASTER-TIMELINE.md

    line 19
  4. Distinctive:

    NEVER write "TODO", "placeholder", "will flesh out", or deferral language without explicit user approval — deferred worldbuilding tends to …

    line 20
  5. Distinctive:

    Only the author pushes changes.

    line 37

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
CLAUDE.md

CLAUDE.md — Worldbuilding Repository

<!-- Replace this line with: one sentence describing your universe -->

Rules (priority: canon > mechanistic coherence > voice/tone > minimal changes > style)

Evidence hierarchy: canon source > derived lore page > cross-referenced inference > "it feels right." Mechanism over association: if you can't state the causal chain back to foundational physics/biology, it's not proven.

  1. Your foundational axiom governs everything — every mechanism must reduce to it
  2. Use in-universe terminology in science files, human-readable names only in narrative/applied content
  3. One entity per file, kebab-case filenames, YAML frontmatter (title, tags, status)
  4. Science prose: academic third-person, present tense for laws, past tense for observations, no bullet-list physics, no meta-commentary
  5. Cross-link with relative markdown paths; flag contradictions with <!-- REVIEW: -->
  6. Dependency order: foundations → physics → chemistry → biology → applied → civilizations
  7. In-universe cited science is canon science — no disclaimers, no "inspired by"
  8. Do NOT commit, push, or overwrite canon files without explicit author approval
  9. Cross-civilization differences are NOT contradictions — different species interpret differently
  10. After writing: update _index.md, GLOSSARY.md, MASTER-TIMELINE.md
  11. NEVER write "TODO", "placeholder", "will flesh out", or deferral language without explicit user approval — deferred worldbuilding tends to never get done
  12. During long sessions, keep .claude/CURRENT_TASK.md updated with current focus, canon decisions made, and next concrete step

Locked Spellings

<!-- Add your universe's proper nouns here, one per line -->

Key Files

<!-- Suggested structure — create these files for your universe: -->
  • reference/core-canon-locked.md — Locked canon decisions (READ ONLY)
  • GLOSSARY.md — Term definitions
  • MASTER-TIMELINE.md — Chronological event log
<!-- Add your universe's key reference files here -->

Change Control

Only the author pushes changes. Claude Code proposes via clearly marked suggestions. Never commit, push, or overwrite canon-status files without explicit author approval.

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