Top 200 ReposEXPLORER
Browse agents, categories and pages
Back to results
Reported by sourceThe source says this happened. Top 200 Repos has not reproduced it.

Trace a disk-filling production bug from core dumps with an agent

B12 CTO Adam Marcus used Claude Code to analyze gigabyte core dumps filling web server disks and traced them to an RSS endpoint reading an endless radio stream.

The problem

How it works

While on call over the holidays, he had Claude Code suggest how to copy dumps out of a full container, then inspect them with file, readelf, gdb and custom Python parsers, approving each script only after checking it was read-only and local. The agent tied the SIGABRT dumps to an RSS view through Sentry profiling strings, found the offending URL in 6 of 8 dumps, and drafted SQL to identify the customer.

Results and limitations

He reports going from problem to production fix in about 2.5 hours with a roughly 20-line change using chunked reads and elapsed-time checks, after rejecting the agent's first fix as overcomplicated and reliant on a library the codebase does not use.

Before you try it

He did much of the hands-on work because the agent initially had no production or code access, and its memory parsing was noisy; the decisive clue came from Sentry data. He is unsure whether he would have found the root cause without it.

Tools and repositories

Tools
Claude Code · gdb · readelf · Docker · Sentry

Try it yourself: Investigate a production incident read-only first

Fill the fields to adapt the prompt. Empty fields stay as visible [placeholders].

Preview
Help me investigate [Incident summary] on [Affected system]. Start read-only: propose each command or script you want to run to inspect [Evidence to inspect], explain what it reads, and confirm it changes nothing. Wait for my approval before running each one. Keep a timeline in [Incident notes file] with findings, evidence and open hypotheses ranked by likelihood. Once you have a likely root cause, draft the smallest fix that matches the existing code style and libraries in [Code repository], plus a test. Do not restart services, delete files, query production databases or contact customers; give me the queries or messages to run myself.

Review every script before approving it and keep production access in human hands until the cause is clear.

Related videos

About anthropics/claude-code

About anthropics/claude-code

Independent creators. Listing a video implies no endorsement, sponsorship or partnership.

Sources

  1. Claude Code and core dumps (opens in a new tab)

    First-person account · blog.marcua.net · Published 28 Jan 2026 · Source checked 9 Nov 2026, 22:24 UTC

    What this source supports
    • Claude Code analyzed core dumps with gdb, readelf and Python
    • Root cause was an RSS parser reading an endless radio stream
    • Offending URL found in 6 of 8 dumps
    • Problem to production fix in about 2.5 hours, fix about 20 lines
Report a problem

Reported by source

Review pull requests automatically with Claude in GitHub Actions

Install the Claude Code GitHub Action so Claude reviews each pull request with inline comments and responds to @claude requests.

code.claude.comanthropics/claude-code
Reported by source

Answer technical questions by letting async agents run experiments

Simon Willison sends research questions to cloud coding agents such as Claude Code for web and Codex Cloud, which write and run experiments in a dedicated repo and open a PR.

simonwillison.net · 6 Nov 2025anthropics/claude-code, openai/codex
Planned, not done

Build a formula-driven Excel model with the Claude xlsx skill

Install Anthropic's xlsx skill in Claude Code so the agent writes live formulas, recalculates the workbook with LibreOffice and checks it for formula errors.

github.comanthropics/skills, anthropics/claude-code
Reported by source

Build an on-call investigation agent from your own alert history

Goutham Veeramachaneni connected Claude Code to Grafana's gcx CLI, his code and runbooks, then trained its skill on two weeks of past pages for his services.

gouthamve.dev · 21 Apr 2026anthropics/claude-code
Reported by source

Get a new OCR model running on unfamiliar GPU hardware with Claude Code in a sandbox

Simon Willison gave Claude Code full permissions inside a Docker container on an NVIDIA Spark and had it get DeepSeek-OCR working; it took four prompts and under 40 minutes, with one nudge from him.

simonwillison.net · 20 Oct 2025anthropics/claude-code, pytorch/pytorch, huggingface/transformers
Reported by source

Let a coding agent run overnight ML training experiments

Point a coding agent at autoresearch so it edits a small GPT training script, runs short timed experiments and keeps what improves.

github.comkarpathy/autoresearch, anthropics/claude-code, openai/codex

More with Claude Code

Reported by source

Run unattended ML training experiments with autoresearch

Red Hat's Roy Belio containerized Karpathy's autoresearch on OpenShift AI with H100 GPUs and let Claude Code run 198 training experiments over 24 hours.

developers.redhat.com · 7 Apr 2026karpathy/autoresearch, anthropics/claude-code
Reported by source

Give Claude your Google Calendar and Gmail through a self-run MCP server

The open-source Google Workspace MCP server exposes Calendar, Gmail and other Workspace tools to Claude Desktop, Claude Code and other MCP clients, using your own OAuth client and optional read-only mode.

github.com
Planned, not done

Let an agent decompile and annotate a binary in Ghidra through GhidraMCP

GhidraMCP exposes Ghidra's decompiler and renaming tools over MCP, so an agent such as Claude Code can list functions, read decompiled code and propose clearer names.

github.comNationalSecurityAgency/ghidra

View all: Claude Code