Pro Workflow
Battle-tested Claude Code patterns from power users who ship production code daily.
Self-correcting memory, parallel worktrees, quality gates, and the 80/20 AI coding ratio —
24 Skills, 8 Agents, 24 Hooks, 21 Commands, 3 Contexts, 7 Guides.
01 Core Architecture
Command → Agent → Skill
Command
User input
Slash commands
→
Agent
Orchestrate
Plan & Review
→
Skill
Execute
Domain logic
- Agents cannot call each other directly — use
Task(subagent_type=...)
- Progressive skill disclosure: only surface what’s needed now
- Skills use context: fork for isolation
02 The 8 Patterns
Karpathy’s 80/20 Ratio
| Pattern | What It Does |
|---|
| Self-Correction | Claude learns from corrections automatically |
| Parallel Worktrees | Zero dead time — native claude -w |
| Wrap-Up Ritual | End sessions with intention, capture learnings |
| Split Memory | Modular CLAUDE.md for complex projects |
| 80/20 Review | Batch reviews at checkpoints, not every change |
| Model Selection | Opus 4.6 & Sonnet 4.6 adaptive thinking |
| Context Discipline | Manage your 200k token budget |
| Learning Log | Auto-document insights from sessions |
03 Components
Everything Included
Platforms
Claude Code
Cursor
SkillKit (32+ agents)
Database
SQLite + FTS5
10 Categories
Full-Text Search
04 Self-Correction Loop
Compounding Improvements
1
Correct
User fixes mistake
→
→
→
4
Persist
LEARNED.md / DB
“Small corrections compound into massive accuracy gains over time.”
Remember this
Add to rules
Don’t do that again
05 Split Memory
Modular CLAUDE.md
CLAUDE.md
Entry point — imports all modules
LEARNED.md
Auto-populated
Context Discipline
| Rule | Why |
|---|
| Read before edit | Understand context |
| Compact at boundaries | Free token budget |
| <10 MCPs, <80 tools | Reduce noise |
| Subagents isolate | Protect main context |
| CLAUDE.md ≤ 150 lines | Avoid instruction drift |
06 Hooks & Automation
24 Hook Events
PreToolUse
Edit tracking, quality gates
Pre-Commit
Lint & typecheck reminder
PostToolUse
console.log, secrets scan
Test Failure
Auto-learn from failures
SessionStart
Load learnings, show stats
SessionEnd
Save stats to SQLite
PromptSubmit
Drift detection at 6+ edits
PreCompact
Save state before compact
Stop
Context-aware reminders
ConfigChange
Detect settings drift
Notification
Permission logging
SubagentStart
Agent lifecycle logging
SubagentStop
Collect agent results
TaskCompleted
Quality gate on completion
PermissionRequest
Flag dangerous ops
PostToolUseFailure
Track failures
TeammateIdle
Detect blockers
Setup
Auto-detect project type
PermissionDenied
Track denial patterns
WorktreeCreate
Parallel session tracking
WorktreeRemove
Cleanup on removal
CwdChanged
Env injection on cd
TaskCreated
Validate task quality
LLM Gate
AI commit & secret scan
07 Specialized Agents
8 Specialized Agents
Break down complex tasks into step-by-step plans. Never edits — only reads and proposes.
Multi-file changes
Architecture
>10 tool calls
Logic, edge cases, error handling, security, performance, and test coverage audit.
Critical
High
Medium
Low
Assess readiness with worktree isolation. Scores 0–100 across 5 dimensions.
Orchestrator
Memory-Enabled
Multi-phase feature development. Research > Plan > Implement > Review workflow.
/develop
Multi-Phase
Validation Gates
Debugger
Hypothesis-Driven
Systematic bug investigation with root cause analysis and fix verification.
Root Cause
Reproduce
Verify Fix
Context Engineer
Token-Aware
Audit context window: CLAUDE.md size, skill overhead, MCP tool counts.
Permission Analyst
New in v3.2
Analyze denial patterns and generate optimized allow/deny rules by risk tier.
Token usage analysis, cache optimization, and model selection recommendations.
08 Scout: Confidence Scoring
5 Dimensions × 20 pts
GO
≥70 — Proceed with confidence
HOLD
<70 — Identify gaps first
Context Modes
Dev
Code first
Iterate quickly
Review
Security focus
Read-only audit
Research
Explore broadly
Summarize findings
09 Development Workflow
Research → Plan → Implement
R
Research
Feasibility analysis. Scout scores readiness.
Output: GO / HOLD decision
P
Plan
Product requirements + architecture.
Planner agent breaks down steps
I
Implement
Phased execution with frequent commits.
Reviewer validates at checkpoints
Validation gate between each phase — must pass before proceeding.
“80% of my code is written by AI, 20% is spent reviewing and correcting it.”
— Andrej Karpathy
10 Skills Library
24 Skills
| Skill | What It Does |
|---|
| pro-workflow | Core 8 patterns |
| smart-commit | Quality gates + conventional commits |
| wrap-up | Session ritual with learning capture |
| learn-rule | Persist corrections to memory |
| parallel-worktrees | Git worktree setup for zero dead time |
| replay-learnings | Surface relevant past patterns |
| session-handoff | Resume docs for next session |
| insights | Analytics, heatmaps, trends |
| deslop | Remove AI code slop before commit |
| context-optimizer | Token management and MCP audit |
| orchestrate | Multi-phase dev workflow |
| permission-tuner | Optimize allow/deny rules |
| compact-guard | Protect context through compaction |
| cost-tracker | Session cost awareness + budgets |
| auto-setup | Auto-configure quality gates |
| mcp-audit | MCP overhead analysis |
| llm-gate | AI-powered quality gates |
| file-watcher | Reactive file change workflows |
+ 7 more: context-engineering, batch-orchestration, thoroughness-scoring, sprint-status, agent-teams, safe-mode
11 Model Selection
Right Model, Right Task
| Task | Model |
|---|
| Quick fixes | Haiku 4.5 |
| Features | Sonnet 4.6 (adaptive thinking) |
| Refactors | Opus 4.6 (adaptive thinking) |
| Architecture | Opus 4.6 (1M context beta) |
| Hard bugs | Opus 4.6 (1M context beta) |
Wrap-Up Ritual (5 Steps)
-
1
Changes audit — git status, uncommitted, TODOs
-
2
Quality check — lint, typecheck, tests
-
3
Learning capture — mistakes, patterns
-
4
Next session — blockers, what’s next
-
5
Summary — one paragraph handoff
12 Get Started
Install in Seconds
Cursor
/add-plugin pro-workflow
Claude Code
/plugin marketplace add rohitg00/pro-workflow
/plugin install pro-workflow@pro-workflow
SkillKit (32+ Agents)
npx skillkit install pro-workflow
npx skillkit translate pro-workflow --agent cursor
Philosophy
- Compound improvements — Small corrections → big gains
- Trust but verify — Let AI work, review at checkpoints
- Zero dead time — Parallel sessions keep momentum
- Memory is precious — Both yours and Claude’s