Static analyzer for AI coding-agent context — and an Agent Skill your agent can run. Measures always-on context cost of CLAUDE.md, AGENTS.md and Agent Skills; finds skills that won't load, redundant instructions, stale paths and duplicate names. Claude Code, Codex, Cursor, Gemini CLI. Research project.
Evidence-based static security analysis of the Prestige Client loader and injector chain, with hashes, disassembly, IOCs and YARA rules.
A zero-symbol static analysis engine that extracts and mathematically ranks the Windows RPC attack surface using an AHP-based risk model.
Audit du maillage interne dans Claude Code — graphe de liens, pages orphelines, couverture pilier/enfants, ancres. CLI Python zéro dépendance.
Audit a codebase for dead, duplicated, or drift-prone code and report every finding for approval before editing.
Fast static analysis and health checks for Godot projects (broken paths, duplicate UIDs, oversized textures, orphan resources, CLI + editor plugin).
Detects API drift between installed and target dependency versions, locates affected call sites, and produces verified migration PRs.
Static analysis for PyTorch training code — catches VRAM leaks and silent convergence bugs, and predicts OOM before you rent the GPU.
Global-readiness toolkit for international forms across HTML, JSX, Vue, Svelte, and CI.
Find accidentally committed secrets before they cost you money. One Python file, zero dependencies, CI-ready.
Opinionated Oxlint rules for rejecting low-evidence TypeScript and JavaScript patterns
Deterministic evidence for code changes: what changed, what verification ran, and what remains unverified.
Detect and remove invisible Unicode security hazards. Trojan Source detection, CI checks, and safe RTL handling.
A practical Codex skill for evidence-backed repository health audits
A compiler-precise code property graph (CPG) with an embedded columnar graph store and a navigation layer built for security reasoning over source code.