Skip to main content

​
Core Concepts

Learn the fundamental concepts that power Panopticon’s multi-agent orchestration.

​
Mission Control

The default dashboard view. Project tree on the left, activity timeline on the right. Click a feature to see its full pipeline: planning, work, review, test results, and merge status. The badge bar gives quick access to PRDs, state files, beads, discussions, and transcripts.

​
Cloister

The lifecycle manager. Cloister routes tasks to models based on capabilities, detects stuck agents, triggers specialist handoffs, and tracks costs. It runs a patrol loop that checks agent health and manages the specialist queue.

​
PRD-Driven Workflow

Opus writes a PRD before implementation starts. Agents are blocked from starting without a PRD — this ensures strategic decisions are made by Opus, not cheaper models. PRDs are auto-committed to the workspace after planning.

​
Agents

Agents are autonomous AI coding assistants that work independently on tasks. Panopticon spawns agents in tmux sessions, allowing you to:
  • Monitor them in real-time via the dashboard activity timeline
  • Send messages to provide feedback or guidance as they work
  • Manage multiple agents simultaneously on different issues
  • Track costs per issue, per stage, with model-level breakdowns
Agent types:
  • Implementation agents — Work on features, bugs, refactoring in isolated worktrees
  • Planning agents — Explore codebases and create PRDs with Opus
  • Specialist agents — Dedicated review, test, and merge agents triggered by Cloister

​
Workspaces

Workspaces are git worktrees — isolated working directories for each issue. Each workspace:
  • Has its own feature branch (e.g., feature/pan-123)
  • Shares git history with the main repo (no separate clone)
  • Can include Docker containers for full development environments
  • Is located at {project}/workspaces/feature-{issue-id}/
  • Contains a .planning/ directory with PRD, STATE.md, beads, and feedback
This allows multiple agents to work on different features simultaneously without conflicts.

​
Main Project Branch Convention

The main project directory should always stay on the main branch. All feature work happens in workspaces (git worktrees), never in the main project. This ensures specialists (review-agent, test-agent) always find the correct code, and merge operations have a clean target.

​
Docker Integration

Workspaces can include Docker containers for full development environments. Supports both local execution and remote execution via exe.dev.

​
Specialists

Dedicated agents for code review, testing, and merging. Triggered automatically by Cloister when an agent signals completion. The pipeline is fully automated:
  1. Review Agent — Performs comprehensive code review (correctness, security, performance)
  2. Test Agent — Runs tests and validates functionality
  3. Merge Agent — Handles PR/MR creation and merging
The only manual step is clicking MERGE when you’re satisfied with the results.

​
Skills

Universal SKILL.md format works across Claude Code, Codex, Cursor, and Gemini CLI. 67+ skills ship out of the box covering:
  • Development workflows (feature work, bug fixing, refactoring)
  • Code review (correctness, security, performance)
  • Incident response and debugging
  • Codebase onboarding
  • Project-specific knowledge capture
Sync skills to all your AI tools with pan sync.

​
Beads

Git-backed task tracking that survives context compaction and works offline. Beads give agents persistent memory across sessions — when a conversation gets compressed, the agent can recover its task state from beads.

​
Convoys

Run parallel agents on related issues. Useful for security audits, performance reviews, or breaking an epic into concurrent work streams. Results are auto-synthesized by a dedicated synthesis agent.

​
Issue Tracker Integration

Panopticon integrates with 5 issue trackers:
  • GitHub Issues — Full integration with PRs and status updates
  • Linear — Full integration with cycles, labels, and status updates
  • GitLab Issues — Issue tracking and MR management
  • Jira — Enterprise issue tracking
  • Rally (CA Agile Central) — Enterprise issue tracking
The dashboard displays issues from all configured trackers in a unified Kanban board with cost badges, agent status indicators, and workspace controls.

​
Cost Tracking

Per-issue, per-stage token costs with dashboard analytics. Every agent session is tracked with:
  • Model and provider attribution
  • Token counts (input/output)
  • Dollar costs per stage (planning, work, review, test, merge)
  • Daily cost summaries on the Board view

​
Shadow Engineering

Monitor existing workflows before transitioning to AI-driven development. Upload transcripts, sync discussions, and generate inference documents to build institutional knowledge before handing off to agents.

​
Next Steps