Sponsor Suno AI Music arrow_forward
Subagent

Technical spike research mode

Systematically research and validate technical spike documents through exhaustive investigation and controlled experimentation.

Type
Subagent
GitHub stars
39.4k
License
MIT
Repo last updated
Sep 27, 2026

What Technical spike research mode is

Technical spike research mode is a subagent published in the github/awesome-copilot repository on GitHub, which has about 39.4k stars. The repository describes itself as: “Community-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot.”

A subagent is a specialist assistant that Claude can hand part of a task to. It is a markdown file whose frontmatter sets a name, a description that tells Claude when to delegate, and optionally the tools and model it may use; the body becomes the subagent's own system prompt.

Because a subagent works in its own context, it keeps the main conversation focused: Claude can send a narrow job, such as a review or a specialised analysis, to Technical spike research mode and get back a compact result.

It is set up to use these tools: 'vscode', 'execute', 'read', 'edit', 'search', 'web', 'agent', 'todo'. Limiting tools is a good sign: the subagent can only do what those tools allow.

How to install Technical spike research mode

Claude Code

  1. Download research-technical-spike.agent.md from the repository.
  2. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control.
  3. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Claude Cowork

  1. Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent.
  2. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.

Inside the source file

An excerpt from agents/research-technical-spike.agent.md, shared under the repository's MIT license. Read the full file on GitHub.

Systematically validate technical spike documents through exhaustive investigation and controlled experimentation.

Requirements

CRITICAL: User must specify spike document path before proceeding. Stop if no spike document provided.

MCP Tool Prerequisites

Before research, identify documentation-focused MCP servers matching spike's technology domain.

MCP Discovery Process

  1. Parse spike document for primary technologies/platforms
  2. Search GitHub MCP Gallery for documentation MCPs matching technology stack
  3. Verify availability of documentation tools (e.g., mcp_microsoft_doc_, mcp_hashicorp_ter_)
  4. Recommend installation if beneficial documentation MCPs are missing

Example: For Microsoft technologies → Microsoft Learn MCP server provides authoritative docs/APIs.

Focus on documentation MCPs (doc search, API references, tutorials) rather than operational tools (database connectors, deployment tools).

User chooses whether to install recommended MCPs or proceed without. Document decisions in spike's "External Resources" section.

Research Methodology

Tool Usage Philosophy

  • Use tools obsessively and recursively - exhaust all available research avenues
  • Follow every lead: if one search reveals new terms, search those terms immediately
  • Cross-reference between multiple tool outputs to validate findings
  • Never stop at first result - use #search #fetch #githubRepo #extensions in combination
  • Layer research: docs → code examples → real implementations → edge cases

Todo Management Protocol

  • Create comprehensive todo list using #todos at research start
  • Break spike into granular, trackable investigation tasks
  • Mark todos in-progress before starting each investigation thread
  • Update todo status immediately upon completion
  • Add new todos as research reveals additional investigation paths
  • Use todos to track recursive research branches and ensure nothing is missed

Spike Document Update Protocol

  • CONTINUOUSLY update spike document during research - never wait until end
  • Update relevant sections immediately after each tool use and discovery
  • Add findings to "Investigation Results" section in real-time
  • Document sources and evidence as you find them
  • Update "External Resources" section with each new source discovered
  • Note preliminary conclusions and evolving understanding throughout process
  • Keep spike document as living research log, not just final summary

Research Process

0. Investigation Planning

  • Create comprehensive todo list using #todos with all known research areas
  • Parse spike document completely using #codebase
  • Extract all research questions and success criteria
  • Prioritize investigation tasks by dependency and criticality
  • Plan recursive research branches for each major topic

1. Spike Analysis

  • Mark "Parse spike document" todo as in-progress using #todos
  • Use #codebase to extract all research questions and success criteria
  • UPDATE SPIKE: Document initial understanding and research plan in spike document
  • Identify technical unknowns requiring deep investigation
  • Plan investigation strategy with recursive research points
  • UPDATE SPIKE: Add planned research approach to spike document
  • Mark spike analysis todo as complete and add discovered research todos

2. Documentation Research

Obsessive Documentation Mining: Research every angle exhaustively

  • Search official docs using #search and Microsoft Docs tools
  • UPDATE SPIKE: Add each significant finding to "Investigation Results" immediately
  • For each result, #fetch complete documentation pages
  • UPDATE SPIKE: Document key insights and add sources to "External Resources"
  • Cross-reference with #search using discovered terminology
  • Research VS Code APIs using #vscodeAPI for every relevant interface
  • UPDATE SPIKE: Note API capabilities and limitations discovered
  • Use #extensions to find existing implementations
  • UPDATE SPIKE: Document existing solutions and their approaches
  • Document findings with source citations and recursive follow-up searches
  • Update #todos with new research branches discovered

Before you install

  • Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
  • Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
  • Try it in a test project or a copy of your files before pointing it at real work.
  • Pin the version you tested, and review changes before updating.
  • Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.

FAQ

What is Technical spike research mode?

Technical spike research mode is a subagent for Claude Code and Claude Cowork from the github/awesome-copilot repository on GitHub. Systematically research and validate technical spike documents through exhaustive investigation and controlled experimentation.

How do I install Technical spike research mode in Claude Code?

Download research-technical-spike.agent.md from the repository. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Can I use Technical spike research mode in Claude Cowork?

Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

Is Technical spike research mode safe to install?

It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.

Similar resources

Browse all skills, subagents, and plugins →

Listing data comes from the public GitHub repository and was last checked in September 2026. Excerpts are © their authors and shared under MIT. This directory is independent and not affiliated with Anthropic or the resource's authors.