Copilot Agent — Research agent for Claude Code
Runs GitHub Copilot CLI on the user's Copilot subscription.
How to install Copilot Agent
Installs to ~/.claude/agents/wherethetunnelends-quorum-copilot-agent.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/WhereTheTunnelEnds/quorum/HEAD/agents/copilot-agent.md -o ~/.claude/agents/wherethetunnelends-quorum-copilot-agent.md Restart Claude Code, or start a new session, for it to be picked up.
What Copilot Agent does
name: copilot-agent description: Runs GitHub Copilot CLI on the user's Copilot subscription. Three modes - consult (harness-enforced read-only analysis, second opinions, PR/issue/CI context via GitHub MCP), verify (runs named commands), and delegate (autonomous implementation in a worktree - reviewable and disposable, but NOT contained: measured writes reached the real checkout). Use for GitHub-flavored questions, repo conventions, PR review, or to offload implementation work off the Claude
Alternatives in Research
- Fable Worker Sonnet — Fable stage worker for tasks needing real reasoning — research synthesis, nontrivial code, analysis, document 837 ★
- CLI Explore Agent — Read-only code exploration via Bash + CLI semantic dual-source analysis, with schema-validated structured outp 530 ★
- Agentic Malware Analysis — Agentic malware analysis environment with MCP-connected disassemblers, RE tooling, and structured workflows fo 189 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Codex Agent
Runs OpenAI Codex on the user's ChatGPT subscription. Three modes - consult (OS-sandboxed read-only analysis,
Legal Opinion Writer
Use this agent when the user needs to draft a legal opinion (法律意见书), has a legal question that needs to be res
Industry Researcher
Industry Researcher. Owns deep competitive analysis, market sizing, trend monitoring, regulatory landscape, pe
Research Processor
Post-process research results — condense findings or deduplicate parallel agent outputs. Two modes.
Osf Analyze
Codebase structural analysis using codebase-retrieval. Traces dependencies, blast radius, call chains, and imp
Ds Pro
DSH (DeepSeek Harness) worker on the pro tier - stronger reasoning. Delegate harder subtasks: multi-file chang
Related Skills
Writing Craft
A blind tested skill for better creative writing. Nine signals three AI judges named after scoring 50 samples
Maestro Learn
User-invoked learning toolkit — guided reading, investigation, pattern extraction, or second opinions. Manual
Ask All
Ask GPT, Gemini, Grok, and any configured OpenRouter models in parallel for independent second opinions, then