ideal-harness
Agent harness / control-plane around a stateless LLM: deterministic policy floor on PreToolUse/PostToolUse hooks, secret redactio…
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.
Contains
1 plugin.
Install
/plugin marketplace add bharat3645/The-Ideal-Harness
Then browse and install with /plugin install.
Source
Repository: https://github.com/bharat3645/The-Ideal-Harness
Maintain ideal-harness?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[ideal-harness on getagentictools](https://getagentictools.com/plugins/bharat3645-ideal-harness?ref=badge) Related plugins
JadeGate Skills The TLS of AI Tool Calls - 46 security-verified skills for MCP servers
java-to-react-modernizer Verification-gated, security-reviewed apm skill to modernize a Java app (Spring/JSP/Stripes) to React/JS — cost-bound agent gradi…
jpm-payments-skills J.P. Morgan Payments developer-experience marketplace. Distributes the jpm-payments-skills plugin (onboarding intake, OAuth code…
kurenn Claude Code plugins for Rails developers — Rails team simulation, audit, security workflows, and prompt refinement.
guard 🛡 Supply chain security CLI for pnpm projects
hotskills Discover, activate, and invoke Claude Code skills with security gating. Search skills.sh, activate with audit-based risk filterin…