compound-workflows

compound-workflows

Fork of Every's compound-engineering for Claude Code. Longer sessions without context exhaustion, session recovery when things go wrong, task tracking that survives compaction, multi-model red team (PAL + Claude), fewer plan iterations, and memory that persists across sessions.

• What is Compound Engineering?
• Why Fork?
• What's Different
• Install
• Update
• Commands
• Dependencies
• Key Concept: Disk-Persisted Agents
• Roadmap
• Attribution

What is Compound Engineering?

Compound engineering is a methodology where each unit of engineering work makes subsequent units easier. You document solutions, capture decisions with their rationale, and build institutional knowledge that compounds over time.

Compound workflows generalize this idea beyond software engineering to all knowledge work — an opinionated way to use Claude Code for research, planning, decision-making, and implementation. The cycle remains the same: brainstorm → plan → work → review → compound.

The plugin captures best-practice patterns and makes them shareable, while remaining configurable to individual user preferences.

Why Fork?

Ambitious tasks in Claude Code hit walls:

• Context exhaustion — Agent outputs fill up context and trigger compaction. → Agents write to disk and return summaries, so sessions last longer.
• State loss — Work progress disappears on compaction. → /compact-prep and /recover handle planned and unplanned session boundaries; beads tracking survives across compactions.
• Plan iteration overhead — Plans require many rounds to reach quality. → Readiness checks and consolidation catch issues earlier, preventing the fix-introduces-new-bug cycle.
• Single-model blind spots — One model can't catch its own assumptions. → Red team challenges from multiple providers (Gemini, OpenAI, Claude) surface what a single model misses.
• Knowledge loss — Context learned in one session is gone in the next. → Tiered memory management promotes frequently-used knowledge to where it's auto-loaded.

What's Different

	compound-engineering	compound-workflows
Agent outputs	In-context (fills up)	Sessions last longer — agents write to disk, not context
Plan quality	Unbounded iteration	Plans reach quality faster — readiness checks and auto-consolidation catch issues early
Red team	Single model	3 models in parallel surface what a single model misses
Task tracking	TodoWrite only	Survives compaction — beads preferred, TodoWrite fallback
Session recovery	Manual	/do:compact-prep (proactive) + /recover (reactive)
Memory management	None	What you learn in one session carries to the next (in progress)
Process analysis	None	See where your time goes and which tasks take longer than expected

Install

/plugin marketplace add adamfeldman/compound-workflows
/plugin install compound-workflows

Warning: Do not install alongside compound-engineering. This plugin bundles all agents and skills. Installing both will cause agent name conflicts. Run /do:setup to detect and resolve conflicts.

Then run setup to detect your environment:

/do:setup

Update

From your terminal:

claude plugin update compound-workflows@compound-workflows-marketplace

Or use the interactive /plugin menu inside Claude Code.

Commands

Command	Purpose
/do:setup	Detect environment, configure directories, recommend enhancements
/do:brainstorm	Explore requirements through collaborative dialogue
/do:plan	Transform ideas into implementation plans with research agents
/do:deepen-plan	Enhance plans with parallel multi-model research + red-team challenges
/do:work	Execute plans autonomously with progress tracking
/do:review	Multi-agent code review from multiple perspectives
/do:compound	Document solved problems to build institutional knowledge
/do:compact-prep	Save your work before compaction — checklist for memory, commits, and resume
/do:abandon	Session-end capture without resumption
/compound-workflows:recover	Recover context from dead/exhausted sessions via JSONL log parsing

/compound:* aliases still work during the v3.0 transition period.

Workflow Cycle