From devloop
Learn how to use devloop - interactive guide to commands, workflow, and best practices
npx claudepluginhub zate/cc-plugins --plugin devloopThis skill is limited to using the following tools:
Interactive guide to devloop.
Enforces structured agentic workflows for coding agents including RED-GREEN-REFACTOR TDD, design-first planning, systematic debugging, subagent-driven development, and git worktrees management. Auto-triggers on planning or implementation tasks.
Answers questions about Claude Code features like setup, best practices, automation, models, plugins, MCP, and configuration by reading reference docs.
Share bugs, ideas, or general feedback.
Interactive guide to devloop.
If $ARGUMENTS specifies a topic, skip to that section. Otherwise:
AskUserQuestion:
questions:
- question: "What would you like to learn about?"
header: "Topic"
multiSelect: false
options:
- label: "Getting Started"
description: "New to devloop? Start here"
- label: "Commands"
description: "What each command does"
- label: "The Loop"
description: "The plan -> run -> fresh cycle"
- label: "Skills & Agents"
description: "On-demand knowledge and parallel work"
- label: "Superpowers"
description: "How devloop works with superpowers plugin"
Development workflow where Claude does the work directly. No routine agents. Just you, Claude, and the code.
/devloop:plan "How should we implement feature X?" # Plan (or --deep for exploration)
/devloop:run # Execute tasks
/devloop:fresh && /clear # Save state, clear context (every fresh_threshold tasks (default 10, configurable in .devloop/local.md))
/devloop:run # Continue execution
/devloop:plan [task] (or --deep for detailed exploration)/devloop:run to implement/devloop:fresh then /clear then /devloop:run/devloop:shipStarting new work?
|-- Unclear requirements -> /devloop:plan --deep
|-- Small, clear task -> /devloop:plan --quick
|-- Normal feature -> /devloop:plan
|-- Have a plan -> /devloop:run
Mid-workflow?
|-- Context heavy -> /devloop:fresh -> /clear -> /devloop:run
|-- Ready to commit -> /devloop:ship
|-- Want review -> /devloop:review
Returning?
|-- /devloop:run
| Command | Purpose |
|---|---|
/devloop | Start new workflow (smart entry point) |
/devloop:plan | Autonomous planning (default mode) |
/devloop:plan --deep | Comprehensive exploration with spike report |
/devloop:plan --quick | Fast path for small, clear tasks |
/devloop:plan --from-issue N | Start from GitHub issue #N |
/devloop:run | Autonomous execution |
/devloop:run --interactive | With checkpoints |
/devloop:run --next-issue | Full issue-to-ship pipeline |
/devloop:run-swarm | Swarm for 10+ tasks |
/devloop:fresh | Save state for clear |
/devloop:review | Code review |
/devloop:ship | Commit & PR |
/devloop:archive | Archive completed plan |
/devloop:new | Create GitHub issue |
/devloop:issues | List GitHub issues |
/devloop:statusline | Configure statusline |
/devloop:help | This guide |
| Old Command | New Command |
|---|---|
/devloop:spike | /devloop:plan --deep |
/devloop:quick | /devloop:plan --quick |
/devloop:from-issue N | /devloop:plan --from-issue N |
/devloop:continue | /devloop:run --interactive |
/devloop:ralph | /devloop:run |
/devloop:plan [topic] -> Creates plan
|
/devloop:run -> Implements tasks
|
After fresh_threshold tasks (default 10, configurable in .devloop/local.md)?
|-- Yes -> /devloop:fresh -> /clear -> /devloop:run
|-- No -> Continue
| File | Purpose |
|---|---|
.devloop/plan.md | Current plan (persists) |
.devloop/next-action.json | Fresh state (consumed) |
.devloop/worklog.md | Work history |
Load when needed: Skill: skill-name
| Skill | Purpose |
|---|---|
plan-management | Working with plan.md |
go-patterns | Go idioms, testing |
python-patterns | Python best practices |
react-patterns | React/TypeScript |
java-patterns | Java/Spring |
git-workflows | Git operations |
atomic-commits | Commit practices |
testing-strategies | Test design |
api-design | REST/GraphQL |
database-patterns | SQL, schema |
architecture-patterns | System design |
security-checklist | Security review |
Don't preload. Claude loads automatically when needed.
Use for: parallel implementations, security scans, large exploration (50+ files) Don't use for: writing code, tests, git ops, single files, docs
| Agent | Purpose |
|---|---|
devloop:engineer | Exploration, architecture, code review |
devloop:qa-engineer | Test generation |
devloop:security-scanner | OWASP, secrets |
devloop:doc-generator | READMEs, API docs |
devloop:swarm-worker | Parallel task execution |
Plan corrupted: rm .devloop/plan.md && /devloop
Session ended: /devloop:run
Abandon plan: /devloop:archive && /devloop
Context heavy: /devloop:fresh && /clear && /devloop:run
Skill not loading: Check exact name in skills/INDEX.md
Progress not saving: Use [x] not [X]
Statusline missing: /devloop:statusline, restart Claude Code
rm -rf .devloop/ && /devloop
/devloop:run # Up to 50 iterations
/devloop:run --max-iterations 100 # Custom limit
/devloop:run --interactive # With checkpoints
/devloop:run creates ralph-loop state[x]<promise>ALL PLAN TASKS COMPLETE</promise>Auto-exits at 70% context usage. Configure in .devloop/local.md:
context_threshold: 80
/cancel-ralphDevloop and superpowers are complementary plugins with distinct lanes:
Devloop works fully standalone. Superpowers is optional.
| Task | Use |
|---|---|
| Plan and implement a feature | /devloop:plan -> /devloop:run |
| Write tests first, then code | superpowers:test-driven-development |
| Debug a failing test | superpowers:systematic-debugging |
| Quick review of changes | /devloop:review |
| Thorough code review | superpowers:requesting-code-review |
| Commit and PR | /devloop:ship |
/devloop:plan creates workflow plans (task breakdown, phased execution)superpowers:writing-plans creates implementation plans (architecture, design decisions)Both can coexist. Use devloop for the workflow, superpowers for quality gates within tasks.
AskUserQuestion:
questions:
- question: "Learn about another topic?"
header: "More"
multiSelect: false
options:
- label: "Yes, show topics"
description: "Return to topic menu"
- label: "No, I'm good"
description: "Exit help"
If yes, return to Step 1. If no:
Ready to start? Try
/devloop:plan [task]or/devloop:runif you have a plan.