https://github.com/inth3shadows/runecho

One cheap layer against AI coding mistakes — not the whole answer. Checks every agent Edit/Write against an index of your repo's real symbols, and asks before a write lands on one that doesn't exist. Catches bare calls, consts, type refs: 4 of 9 in our real-hallucination benchmark. Qualified calls out of scope. Deterministic, ~0 tokens, no LLM.

ai-tooling anthropic claude-code claude-code-plugin codebase-analysis developer-tools git-hooks go golang hallucination-prevention hooks llm mcp mcp-server security static-analysis

Last synced: 23 Jul 2026

https://github.com/inth3shadows/terse

Lossless-first compression layer for AI-agent tool outputs — selective per-tool, byte-faithful, no decode step.

Last synced: 23 Jul 2026

https://github.com/inth3shadows/codeshot

Claude Code companion: click code blocks in your terminal to stage them in a new Windows Terminal or iTerm2 tab

Last synced: 23 Jul 2026

https://github.com/inth3shadows/boundary-probe

Deterministic network boundary diagnosis with evidence-backed remediation

Last synced: 23 Jul 2026