Module 05 · Shared context index
runnableContext Engine
Index once, reuse context across agents.
Runnable v0.1 slice available on GitHub — architecture and scope below.
Problem
An agent working across 15 repositories can spend more tokens rediscovering the codebase than answering the question. Every tool builds its own partial picture, then throws much of that work away.
Where it sits
Sits beneath agents and delivery modules as a shared index. It is meant to expose relevant context over MCP so each tool does not repeatedly scan the same repositories.
The Context Engine is designed for environments where a change may touch 15 repositories, shared libraries, architecture notes, and service contracts. It keeps an index that other modules and agents can query instead of repeatedly reading everything from scratch—so teammates are not re-burning tokens on the same corpus.
MCP is the access layer, not the product story. The useful part is a portable, inspectable context contract: what was indexed, where an answer came from, and which source should be opened when more detail is needed.
How it fits
This is the shared index that the other modules lean on. Stage Gate and Shadow Versioning can retrieve project material; agents calling through Smart Router can resolve service context without folding indexing into their own runtimes.
Capabilities
- Intended indexing across many repositories
- Shared retrieval for multiple agents and Mirevox modules
- MCP access to focused source context
- Source references that people can inspect directly
- Less repeated repository scanning and token use
- Portable context contracts independent of one coding assistant
Other modules
- Smart RouterModel access gets scattered across provider keys, endpoints, deployment rules, and separate UIs. Even a VS Code assistant and a home chatbot can end up repeating the same integration work.
- Evals & English GovernanceEach model platform has its own eval screens, scoring terms, and policy controls. Teams end up comparing results by hand, while governance rules live in documents that do not map cleanly to provider settings.
- Stage GateAI-assisted projects can jump from an appointment straight into generated code. The missing middle—prerequisites, requirements, decisions, and clear advance criteria—is usually spread across documents and understood by only a few people.
- Shadow VersioningOne project can have its brief in Confluence, approvals in SharePoint, code in Git, and evidence in a testing system. Humans see one piece of work, but the tools expose unrelated histories and technical version language.
- Data LineageOnce a prompt crosses a gateway, it can be hard to explain which provider, region, model, or internal service handled it. Existing lineage tools cover data estates well, but AI request paths often need a smaller, trace-linked view.
- AI-DORAAI coding agents inflate commit counts and PR volume, hiding code churn, review bottlenecks, and rework. Traditional DORA dashboards track deployment frequency without telling you if half the AI-written lines were reverted two weeks later.