Prompt Hardener analyzes prompt-injection-originated risk in LLM-based agents and applications.
Latest release v0.6.0 · 21 Apr 2026
3 files for Claude Code, Codex and OpenCode: agent-spec-builder, prompt-hardener AGENTS.md, prompt-hardener CLAUDE.md — 1,192 tokens loaded in every session.
AGENTS.md A 1,188 tok CLAUDE.md A 4 tok .agents/skills/agent-spec-builder/SKILL.md A 75 tok These files are cybozu/prompt-hardener's own configuration — they tell Claude Code, Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.