agentleFS
Sign inStart free
KadihxKadihx/jev-x-kit/CLAUDE.md

jev-x-kit

CLAUDE.md4 starsChanged 52 days agoMITView on GitHub

When a task touches personal development, rationality, decision-making, cognitive bias, habit formation, or philosophy, ground the answer in the Research Hub (src/datacenter/) instead of ad-hoc free text or popular advice. 1. Query the hub first: npm run hub -- query "<question>" or the hub_query MCP tool — before answering from general/parametric knowledge. 2. Source pool (11 sources, 3 tiers — see src/datacenter/source-configs.ts): - mental-models: Farnam Street (fs-blog), LessWrong (lesswrong), Derek Sivers book notes (sivers), Julian Shapiro guides (julian) - library:…

  • In this repositoryOne other file it gives its agents.

The file

We split this CLAUDE.md 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
  1. Very specific:

    When a task touches personal development, rationality, decision-making, cognitive bias, habit formation, or philosophy, ground the answer …

    line 5
  2. Very specific:

    No hallucinated citations: if the hub returns no VERIFIED/PROBABLE passage, say so explicitly and fall back to jev_research (4-channel …

    line 21

≈ “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 — jev-x-kit operating rules

Research Hub methodology (binding rule)

When a task touches personal development, rationality, decision-making, cognitive bias, habit formation, or philosophy, ground the answer in the Research Hub (src/datacenter/) instead of ad-hoc free text or popular advice.

  1. Query the hub first: npm run hub -- query "<question>" or the hub_query MCP tool — before answering from general/parametric knowledge.
  2. Source pool (11 sources, 3 tiers — see src/datacenter/source-configs.ts):
    • mental-models: Farnam Street (fs-blog), LessWrong (lesswrong), Derek Sivers book notes (sivers), Julian Shapiro guides (julian)
    • library: Internet Archive / Open Library (archive, openlibrary), Project Gutenberg (gutenberg), Wikibooks (wikibooks)
    • academic: PhilArchive (philarchive), PsyArXiv (psyarxiv), CORE (core)
  3. Answer discipline (enforced in src/datacenter/query.ts's system prompt): prefer rational models and cognitive-science findings over popular advice; cite the source id in brackets, e.g. [fs-blog]; structure as core model -> evidence -> concrete step-by-step actions.
  4. No hallucinated citations: if the hub returns no VERIFIED/PROBABLE passage, say so explicitly and fall back to jev_research (4-channel web/academic/code/social) instead of inventing a source URL.
  5. Keep the hub fresh: npm run hub -- crawl (nightly window 02:00-06:00 Europe/Berlin) or the hub_crawl MCP tool; pass --force only for manual/off-hours runs.

This rule persists across sessions — treat data/research-hub.sqlite as the project's general knowledge dataset for this domain, not a one-off report.

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