Skip to main content
subagent CX Codex

infrarsi-answerer — Claude Code subagent: features and setup

The infrarsi-answerer Claude Code subagent handles a single InfraRSI search request and saves its result in the request folder. The infrarsi-optimize skill starts it by passing that folder.

no license ★ 99 updated 2026-11-12

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/agents/infrarsi-answerer.md
Open on GitHub

What infrarsi-answerer does

The subagent reads the request files and creates an answer in the format they specify. It opens README.md, then reads system.txt and prompt.txt; it also checks schema.json when that file exists. Most requests call for a JSON object in answer.json, though the request can ask for plain text.

It writes to the filename given in README.md and uses Read, Write, Glob, and Grep. Its scope is one request folder, not the rest of the project. The infrarsi-optimize skill must hand over the folder; this subagent is not for general questions about training.

What it helps with

  • answer one InfraRSI request from its folder
  • follow the instructions stored with a request
  • save the result in the requested file

Example prompts for the agent

  • Handle the InfraRSI request in requests/example.
  • Process the request passed by infrarsi-optimize and save the answer to its specified file.

How to install infrarsi-answerer

Manually: put the files in place

.claude/agents/infrarsi-answerer.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about infrarsi-answerer

How do I install infrarsi-answerer in Claude Code?

Add the agent file at .claude/agents/infrarsi-answerer.md.

What does infrarsi-answerer do?

It reads the files for one InfraRSI request and writes an answer to the specified file. The request files determine the output format.

When should infrarsi-answerer run?

It runs when infrarsi-optimize hands it a request folder. It is not meant to answer general training questions.

Similar subagents

All subagents for Agent setup: memory, context, orchestration →
tavily-research tavily-ai tavily-research — a skill for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode that runs tvly research, pulls sources from the web, and returns a cited report. Completes in 30–120 seconds. CX Codex +1 25,100installs mongodb-search-and-ai mongodb mongodb-search-and-ai — a skill for Atlas Search (full-text), Vector Search (semantic), and Hybrid Search in MongoDB. Guides you to choose a search type, build indexes, write queries, and tune performance via the MongoDB MCP server. CX Codex +1 6,300installs build-with-exa Exa build-with-exa — a skill for integrating Exa API into IDEs and agents. Provides semantic web search, page content extraction, structured answers, and long-running research via the Agent API — requires an Exa API key. CX Codex +1 5,200installs tavily-search veithly tavily-search connects Tavily AI search API to fetch fresh web information and real-time facts. Helpful whenever an agent needs recent updates from outside its training data. CX Codex +1 3,700installs Podcast Transcripts On-Demand petabloom Podcast Transcripts On-Demand — an MCP server for real-time access to podcast transcripts. Search episodes by keyword, topic, or show name; retrieve full transcripts directly in your IDE. CX Codex +1 2,007installs 12306 Ticket Search Server DeniseLewis200081 12306 Ticket Search Server — an MCP server that connects AI agents to China's 12306 rail network. Search for direct routes, transfer options, and train schedules in real time. CX Codex +1 1,829installs

From the same set19

The whole set →
summarizer The summarizer Claude Code prompt condenses an infrastructure optimization search into a factual handoff. It keeps candidate results and unresolved hypotheses for later turns. GP ChatGPT ★ 99repo stars verifier The verifier Claude Code prompt checks one infrastructure change before it moves to screening. It can veto a candidate based on a checklist or the parent result. GP ChatGPT ★ 99repo stars weak_proposer The weak_proposer Claude Code prompt tunes Megatron-Core training for speed. It proposes config changes, runs trials and identifies the fastest valid candidate. GP ChatGPT ★ 99repo stars reflect The reflect Claude Code prompt revises an optimizer package using the trace from a finished task. It turns observed evidence into rules for later tasks instead of carrying over one task’s settings. GP ChatGPT ★ 99repo stars proposer proposer is a Claude Code and ChatGPT prompt that tunes training throughput in InfraRSI by proposing configuration and overlay changes while preserving fixed task settings. GP ChatGPT ★ 99repo stars weak-model-protocol The weak-model-protocol Claude Code skill sets rules for an optimizer driven by a weaker or cheaper language model. It activates when actions are malformed, context runs short, or the provider returns errors. CX Codex +1 ★ 99repo stars optimize-data-path The optimize-data-path Claude Code skill optimizes data and state transfers between the host and GPU without changing the data contract. It is triggered by costly loading, host synchronization, or optimizer-state transfers. CX Codex +1 ★ 99repo stars learn-optimization-skills The learn-optimization-skills Claude Code skill guides an optimizer’s learning between development tasks and records reusable lessons. It runs for post-task reflection or when a search turns up a reusable finding. CX Codex +1 ★ 99repo stars

Project sponsors

Companies that keep this analytics open