Community project / Agent and developer tooling

strayguard

Pre-commit hook that uses Jev Choice to flag scratch files, output dumps, build output, and local-only files; sends new-file paths, sizes, nearby tracked names, and up to 40 lines of eligible text to TypeSafe. Local rules suppress contents for matched secret-file paths, but unmatched text may contain secrets; on API failure or without a key, it falls back to local rules, and non-interactive warnings do not block unless strict mode is enabled.

Open the original resource ↗ See it in the full directory Start a reading list → Browse all Agent and developer tooling

Download share card ↓

This is an independent community listing. Check the source, license, data handling, and evaluation caveats before relying on a project. Inclusion is not an endorsement or security review.

Found an outdated or inaccurate detail? Report a correction →

Explore more in Agent and developer tooling

• 

  Supercov

  Code quality for coding agents: Jev scores each source file so the agent knows what to fix first.

  Read listing →
• 

  Switchboard

  Local Claude Code and Codex wrapper that assesses a new conversation's task with Jev, applies local confidence policy to choose the model and reasoning effort, and pins that route through follow-ups, tool calls, and resume to avoid unnecessary prompt-cache disruption. It preserves native authentication and sends task text to the configured TypeSafe, Vercel, or OpenRouter Jev endpoint; raw prompt history is stored only when explicitly enabled.

  Read listing →
• 

  System One-assisted compaction

  Archived Rust example that asks a configured OpenRouter decision model to score which tool outputs are worth keeping during context compaction; it compares the ordering with an age-based policy on a synthetic session, not a live-agent outcome.

  Read listing →