Claude Copilot
An instruction layer for Claude Code that gives every developer access to a full team of specialists.
What Is Claude Copilot?
Claude Copilot is a set of instructions that sit on top of Claude Code. This is an independent, community-driven framework for Claude Code, unaffiliated with Microsoft Copilot or GitHub Copilot.
It's not separate software—it's markdown files (agents, commands, project instructions) and two CLI tools (cc and tc) that give Claude Code new capabilities:
| You Get | What It Does |
|---|
| Persistent Memory | Decisions, lessons, and progress survive across sessions (FTS5 keyword search) |
| 8 Specialist Agents | Lean agents with on-demand skill loading; design agents include creative methodology |
| Code-Bearing Skills | Skills with executable scripts; output enters context, not implementation code |
| Parallel Orchestration | Headless workers execute streams concurrently with /orchestrate |
| Pause & Resume | Context switch mid-task with /pause, return with /continue |
| Task Management | PRDs, tasks, and work products via tc CLI with minimal context usage |
| Stream Management | Parallel work streams with conflict detection and dependencies |
| Knowledge Search | Your company docs, available in every project via Known References registry |
| Extensions System | Override or extend agents with your company methodologies |
| Code-Execution Path | tc.api / cc.api facades for multi-step ops without CLI round-trip token cost |
| Context Engineering | Auto-compaction, continuation enforcement, activation modes |
When Claude Code reads these instructions, it transforms from a generic assistant into a full development team that remembers your work.
→ Why we built this
The Problem
Solo developers are expected to be experts in everything. AI assistants help, but they:
- Forget everything between sessions
- Give generic advice without context
- Lack proven processes for complex work
Teams face the same challenges at scale—plus knowledge silos, inconsistent standards, and AI that amplifies inconsistency.
→ Read the full problem statement
April 2026 Restructure
A diagnostic of 15 sessions (Apr 17-22 2026) found a 6% delegation rate — 94% of work stayed in the main session despite a 14-agent roster. A 5-day staging deployment saga (57 manual bash polling calls, 26 loops) exposed missing primitives. The April 2026 restructure fixes this with mechanical hook enforcement, a consolidated 8-agent roster, the tc deploy wait primitive, and model pinning so the cheap-and-fast model handles orchestration.
→ Full diagnostic and rationale
How It Works
