the signals and their derived score are provisional and subject to change.
validate manually before sharing.
3bec134e4375707a9909d463a45fb3c8fe29cfe6d7a8cf911396578e01f637e6d4bc15e34292f4f6Authored: 5 months ago (Thu, 26 Mar 2026 19:11:06 +0000)Match: Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>a872dfdbe2583812af7baec64c7aff19e5044ad1Authored: 5 months ago (Tue, 10 Mar 2026 18:58:28 +0000)Match: Made-with: Cursora872dfdbe2583812af7baec64c7aff19e5044ad1Authored: 5 months ago (Tue, 10 Mar 2026 18:58:28 +0000)Match: Made-with: Cursora872dfdbe2583812af7baec64c7aff19e5044ad1Authored: 5 months ago (Tue, 10 Mar 2026 18:58:28 +0000)Match: Made-with: CursorAGENTS.mdTool: agents-md# AGENTS.md
Guide for AI agents working on Sharkord. Read [CONTRIBUTING.md](CONTRIBUTING.md) for
project scope and PR rules — this file covers how the code is organized.
Core principle from CONTRIBUTING: **no over-engineering**. Follow the existing pattern,
add the smallest thing that works, don't introduce unneeded abstractions or dependencies for a
single use case, only if absolutely necessary. If you find yourself writing a lot of new code, check if it can be
done with existing helpers or patterns fiCLAUDE.mdTool: claude-codeRead @AGENTS.mdnone