Skip to content
← Back to projects

Prompt Governance

Prompt Control Plane

Score, route, enforce policy, lock config, and audit prompt decisions before they ever reach a model. Ships as an npm package, MCP server, and GitHub Action.

2026 TypeScriptMCPnpmGitHub ActionEnterprise
20 MCP tools11 CLI commandsZero LLM calls inside

The problem

Most organizations now monitor models, versions, and tokens, but the prompt layer is still unmanaged text. That means no clear answer to basic governance questions: who changed this instruction, what risk did it introduce, and can the behavior be reproduced later?

What I built

Prompt Control Plane is a deterministic governance layer for prompts. It adds structure before execution: risk scoring, policy enforcement, cross-provider routing, and a tamper-evident audit trail. It ships in three useful surfaces at once:

  • an MCP server for AI-native workflows
  • a CLI for local and CI usage
  • a GitHub Action for pull-request quality gates

Why it matters

The differentiator is that the engine itself does not call an LLM. It enforces rules, structure, and repeatability around the prompt surface, which keeps the system deterministic, cheaper to run, and easier to reason about in production.

Distribution

More Projects

See what else I've built

Hiring tools, prompt governance, automation systems, and open-source utilities.