agentsclimarketplace

Mission control rag retrieval design

Skill MN755/Codex-Mission_Control/.codex/plugins/mission-control/skills/mission-control-rag-retrieval-design

An Open Source Platform For Building Projects With OpenAI's Codex, Claude CLI, And Other Coding LLMs Using Multi-Agent Swarms And Customizable Workflows. Runs On Windows, MacOS, And Linux.

Install
npx -y skills add MN755/Codex-Mission_Control --skill mission-control-rag-retrieval-design

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Design retrieval, indexing, chunking, ranking, and RAG workflows through Mission Control. Use for docs search, code search, semantic recall, and context-pack construction.

SKILL.md

1.8 KB, as published. Nobody here has run it

Mission Control RAG Retrieval Design

Purpose

Design retrieval systems that support agent work without turning context into a random pile of embeddings.

The Codex chat agent is not the Mission Control Manager. It is the bridge between the user and the Mission Control Manager.

Use when

  • The user wants semantic search, RAG, retrievers, or context packs.
  • Large docs or codebases need selective context.
  • Retrieval quality needs evaluation.

Workflow

  1. Ask Mission Control to define corpus, chunking, metadata, ranking, and freshness rules.
  2. Choose local-first or API-backed retrieval based on policy.
  3. Define context-pack boundaries and citation expectations.
  4. Plan retrieval evaluation with representative questions.

Mission Control calls

Tools:

  • mission_control_start_task
  • mission_control_get_status

Resources:

  • mission-control://projects/{project_id}/codebase-map
  • mission-control://projects/{project_id}/agent-contracts
  • mission-control://projects/{project_id}/validation-summary

User-facing output

  • Summarize corpus scope, retrieval design, freshness, privacy posture, eval plan, and limitations.

Approval behavior

Ask before sending private content to external embedding or vector services.

Never do

  • Do not imply semantic search is accurate without evals.
  • Do not leak secrets into indexes.
  • Do not use stale indexes without saying so.

Failure and fallback

If no retriever exists, propose a simple lexical baseline before vector search.

Example invocation

Use Mission Control to design a local-first RAG path for this docs folder.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.