Agent harness / control-plane around a stateless LLM: deterministic policy floor on PreToolUse/PostToolUse hooks, secret redaction, injection fencing, tool-result compression, code-graph memory, orchestration. Five plugin modules for Claude Code (Tier 1) or any MCP host (Tier 2). MIT.
3 files for Claude Code, Codex and OpenCode: The-Ideal-Harness, The-Ideal-Harness AGENTS.md, The-Ideal-Harness CLAUDE.md — 5,796 tokens loaded in every session.
AGENTS.md A 1,996 tok CLAUDE.md C 3,800 tok .claude/settings.json A — These files are bharat3645/The-Ideal-Harness'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.