🔌

ideal-harness-guard

🔌Plugin

bharat3645/The-Ideal-Harness

What it does

Enforcement floor below the LLM: deny-wins policy, permission defaults, injection defense, secret redaction + broker, skill vetting, drift-guard, sandbox.

🏪

Part of

bharat3645/The-Ideal-Harness

Installation

Add marketplace in Claude Code:

/plugin marketplace add bharat3645/The-Ideal-Harness

Step 2. Install plugin:

/plugin install ideal-harness-guard@ideal-harness # the enforcement floor

Last UpdatedJun 26, 2026

View on GitHub Back to Plugins

More from this repository5

🔌

ideal-harness-orchestrate🔌Plugin

Orchestration & control flow: durable task ledger, tool registry, loop/no-progress guard, spend governor, API retry/backoff, session resume/checkpoint, plus subagent-driven-development and brainstorming skills.

🔌

ideal-harness-compress🔌Plugin

Deterministic, cache-safe tool_result compression (JSON sampling, log RLE, stack-trace collapse) with a Compress-Cache-Retrieve store, plus the caveman output-side terse mode.

🔌

ideal-harness-core🔌Plugin

Substrate: plugin loader, skill templating + multi-host generation, validation, bootstrap skill. Required by all other modules.

🔌

ideal-harness-memory🔌Plugin

Structural code-graph with token-budgeted subgraph retrieval + episodic memory with BM25 relevance ranking and a curator that reconciles claims against tool-call evidence.

🏪

bharat3645/The-Ideal-Harness🏪Marketplace

A Claude Code-native agent harness with an MCP-portable enforcement and tooling core. Clean-room synthesis of best-of-breed harness ideas — zero overlap, safety enforced below the LLM.