Skip to main content
prompt GP ChatGPT

summarizer — Claude Code prompt: what it does, how to install

The summarizer Claude Code prompt condenses an infrastructure optimization search into a factual handoff. It keeps candidate results and unresolved hypotheses for later turns.

no license ★ 99 updated 2026-11-12

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

What summarizer does

summarizer turns earlier discussion of infrastructure optimization into a compact record for the next steps. It keeps candidate IDs and changes, screening outcomes with reasons, StepTime and peak memory, the current best result, failures and their causes, plus hypotheses still under review.

It removes repetition and speculation, retaining only details present in the conversation. The reply must fit within limit_tokens and contain exactly one JSON object with a summary key. In Claude Code, install it as .claude/commands/summarizer.md.

What it helps with

  • condense earlier turns in an infrastructure optimization search
  • carry screening outcomes and rejection reasons into later turns
  • preserve the current best result and unresolved hypotheses

Example prompts for the agent

  • Summarize the earlier infrastructure optimization search so we can continue.
  • Record candidate changes, screening results, StepTime, and peak memory.
  • Return the current best, failure causes, and open hypotheses as JSON.

How to install summarizer

Manually: put the files in place

.claude/commands/summarizer.md

Questions about summarizer

How do I install summarizer in Claude Code?

Save the prompt as .claude/commands/summarizer.md.

What does summarizer do?

It condenses an infrastructure optimization search into a factual handoff, retaining candidate checks, metrics, failures, and unresolved hypotheses.

What format does summarizer return?

It returns one JSON object with a summary key. The summary stays within limit_tokens.

Similar prompts

All prompts for DevOps and infrastructure →

From the same set19

The whole set →
infrarsi-answerer 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. CX Codex ★ 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