Bug Hunt Swarm

Finds the cause of a hard bug by running several read-only subagents in parallel, each attacking it from a different angle (change history, code path, data and state, environment, reproduction), then checking their evidence, ranking the hypotheses and naming the one experiment that would confirm the leader. It diagnoses and does not fix. Use when someone says "hunt this bug with multiple agents", "swarm on this regression", "investigate in parallel", "find the root cause", or when a failure is intermittent, crosses components, or has resisted a first look.

213 stars 34 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add TerminalSkills/skills --skill bug-hunt-swarm
Manual install
git clone --depth 1 https://github.com/TerminalSkills/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/skills/bug-hunt-swarm ~/.claude/skills/bug-hunt-swarm

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Bug Hunt Swarm

## Overview

A bug without an obvious cause is a search problem, and a single investigator tends to settle on the first believable story. In this procedure the main agent writes a case file, sends three to five read-only investigators at it at the same time, each with its own angle, and then acts as a sceptical judge: it re-checks the evidence, ranks the hypotheses against every symptom and picks the cheapest experiment that separates the leaders.

Nothing in the repository is changed. The product is a diagnosis report; fixing starts only after the user has read it.

## Instructions

### 1. Decide whether a swarm is worth it

Swarm when at least two of these hold: ten minutes of direct reading has not localised the cause; the symptom crosses components; it is intermittent; it works in one environment and fails in another; it is a regression with many candidate commits.

Investigate alone when a stack trace points at a line you can read and explain, when one deterministic test fails in one file, or when the cause is known and only the fix is wanted. Each investigator has its own context and costs about as much as a full agent run, so five investigators cost roughly five times one.

### 2. Write the case file

Investigators start with an empty context and see only what the brief contains. Gather the facts first, reading only:
Read the full skill on GitHub

Details

Skill name
bug-hunt-swarm
Path
skills/bug-hunt-swarm/SKILL.md
License
Apache-2.0
Repo updated
8 November 2026

FAQ

What does the Bug Hunt Swarm skill do?

Finds the cause of a hard bug by running several read-only subagents in parallel, each attacking it from a different angle (change history, code path, data and state, environment, reproduction), then checking their evidence, ranking the hypotheses and naming the one experiment that would confirm the leader. It diagnoses and does not fix. Use when someone says "hunt this bug with multiple agents", "swarm on this regression", "investigate in parallel", "find the root cause", or when a failure is intermittent, crosses components, or has resisted a first look.

How do I install the Bug Hunt Swarm skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add TerminalSkills/skills --skill bug-hunt-swarm. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Bug Hunt Swarm popular?

It lives in TerminalSkills/skills, which has 213 GitHub stars and 34 forks.

Related skills

3dsmax Rendering

213

TerminalSkills/skills

Scripts and configures production rendering in Autodesk 3ds Max with the V-Ray and Corona renderers: output size and files, render elements, denoising, light mix, batch and command-line rendering, and network rendering. Use when a user asks to set up a production render, render several cameras in one batch, render from the command line or on a render farm, add render passes for compositing, or cut render time for archviz and product shots.

Other34

3dsmax Scripting

213

TerminalSkills/skills

Covers scripting Autodesk 3ds Max, the 3D modeling and rendering application, with MAXScript and Python (pymxs): scene manipulation, object creation, material assignment, camera and light setup, batch operations, and file I/O. Use when tasks involve automating repetitive 3ds Max workflows, batch processing scenes, running scripts headless with 3dsmaxbatch, creating custom tools, or scripting scene setup for archviz, product visualization, or VFX.

Productivity & Notes34

3proxy

213

TerminalSkills/skills

3proxy is a small open-source proxy server that runs HTTP/HTTPS, SOCKS4/5, SNI and TCP/UDP port-mapping proxies from one config file. Use when a user asks to set up an HTTP or SOCKS5 proxy, add proxy users and passwords, write 3proxy access rules, chain or rotate upstream (parent) proxies, limit bandwidth, connections or monthly traffic per user, run 3proxy in Docker, or fix a 3proxy.cfg that will not start.

DevOps & Cloud34

Cerebras

213

TerminalSkills/skills

Cerebras Inference is a hosted LLM API that runs open models on Cerebras wafer-scale chips at thousands of tokens per second, through an OpenAI-compatible endpoint. Use when a user wants the lowest-latency chat, code completion or agent loop, asks how to call the Cerebras API or SDK, needs streaming, tool calling, strict JSON schema output or reasoning control, or hits a "model not found" error from a retired Cerebras model ID.

AI, LLMs & Agents34

Browser Use

213

TerminalSkills/skills

Browser Use is an open-source Python library that lets an LLM agent drive a real browser to navigate sites, fill forms, click and extract data from a plain-English task. Use when the user wants an AI agent to automate a website, scrape pages that need clicking or login, return structured data from the web, add browser tools to a coding agent, or run browser agents locally or in the cloud.

AI, LLMs & Agents34

Chromadb

213

TerminalSkills/skills

Assists with storing, searching, and managing vector embeddings using ChromaDB. Use when building RAG pipelines, semantic search engines, or recommendation systems. Trigger words: chromadb, chroma, vector database, embeddings, semantic search, similarity search, vector store, rag.

AI, LLMs & Agents34

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.