repowiserepowise
Sign in
Mnehmos/llm-driven-proof-search
OverviewDocsArchitectureKnowledge GraphFilesCode HealthRefactoring

People & History

CommitsContributorsDecisions
ChatPro
Stats
repowiserepowise
ExplorePricingDocs
Sign inIndex repoIndex your repo free
repowiseMnehmos/llm-driven-proof-search
LL
LL

Mnehmos / llm-driven-proof-search

jsondevelope20b029259.6K linessynced 18h ago

Code health

9.4out of 10Excellent

This codebase scores 9.4 out of 10 on defect risk, which we rate excellent. It also scores maintainability 9.6 and static performance risk 9.9 out of 10. The three are scored separately and never blended into one number. The files you change most are the weak spot: 19 of 2,459 files are git hotspots, and they average 6.9.

Full health report →
Documentation381pages0 with model-written prose, 381 built from the indexScore validation3/2026.35× baselineOf the 20 lowest-health files, 3 were bug-fixed in the last 6 months — 26.35× the 1% baselineDead code2exportsUnused exports that nothing in the graph reaches
Lines of code
259.6K
Files
2,459
Symbols
3,903
Modules
13
Languages
7

Recent activity

All commits →

Commits

No commits indexed yet.

Decisions

  • Hash-Chained Trajectory Eventsactive · 18h ago
  • Canonical vs. Episode-Local Storageactive · 18h ago
  • Lean Sandbox Platform Isolationactive · 18h ago
  • ArithmeticKit v1 — divisor sums, valuations, Pell recurrences, modular periodicityproposed · 18h ago
  • FiniteCertificateKit extraction + A/B separationproposed · 18h ago
  • correct stale benchmark_suite_create cross-reference in SetTrust doc commentproposed · 18h ago

Needs attention

57 open
  • medium severity. ProposedArithmeticKit v1 — divisor sums, valuations, Pell recurrences, modular periodicityAuto-proposed decision awaiting review
  • medium severity. ProposedFiniteCertificateKit extraction + A/B separationAuto-proposed decision awaiting review
  • medium severity. Proposedcorrect stale benchmark_suite_create cross-reference in SetTrust doc commentAuto-proposed decision awaiting review
  • medium severity. Proposeddrop stale exposition_observe tool name from live error messageAuto-proposed decision awaiting review
  • medium severity. Proposedmathcorpus_export MCP tool — emit conformant MCIP v1 bundleAuto-proposed decision awaiting review

Where the risk concentrates

All 19 hotspots →

Ranked by prior bug fixes and change frequency, mined from full git history rather than from the code alone.

FileChurnPrior fixesMaintainersCommits 90d
lib.rscrates/proofsearch-mcp/src99.9th11bug magnet1bus factor 171
family5-subap-closures.leanErdosProblems/erdos-647/proof/campaign99.7th01bus factor 16
mod.rscrates/proofsearch-core/src/lean99.6th21bus factor 110
Erdos647_ExactBaseSurvivorState.leanErdosProblems/erdos-647/proof99.5th01bus factor 15
mcip.rscrates/proofsearch-core/src99.3th11bus factor 17

Composition

Open the graph →
json 42%markdown 27%lean 22%python 5%rust 3%Other 0%

Explore this codebase

  • Docs381 pages across 13 modules→
  • ChatAsk this codebase a question and get an answer with its sources→
  • Files2,459 files with per-file docs, health and history→
  • ArchitectureDependency graph, layers, and 2 entry points→
  • Code healthPer-file scores, 1,523 open findings, coverage and refactoring targets→
  • Knowledge graphEntities, communities, and the paths between them→
  • Change couplingFiles that keep changing together, mined from commit history→
  • CommitsChange-risk ranked history with agent provenance→
  • ContributorsBus factor, per-file maintainers, and the human/agent split→
  • StatsSize class, origin, lifetime churn, rhythm and records→
  • CostsWhat indexing this snapshot cost, by model and by run→