DonnyClaude

DonnyClaude

The verified workflow engine for Claude Code.

Claude Code is excellent at generating code. It is weaker at long projects: context gets messy, /clear loses decisions, and the model can call a task "done" before tests, requirements, or security checks actually pass.

DonnyClaude wraps Claude Code in a durable planning layer and a deterministic verification loop:

• writes project state to .planning/ so work survives /clear and new sessions
• breaks large work into explicit phases with requirement and dependency gates
• routes work to scoped subagents: planners, implementers, reviewers, verifiers
• refuses to mark work complete until engine-backed checks pass

npx donnyclaude

One command installs the Donny engine, the skills and agents, coding rules for 13 languages, project hooks, and a curated MCP setup - then Claude itself walks you through your first project.

Why this exists

LLM coding tools are good at producing work. They are much worse at knowing when work is actually finished. The recurring failure modes:

• the model forgets project decisions after /clear
• long tasks turn into messy chat history instead of durable state
• one overloaded prompt tries to plan, code, review, and verify itself
• "looks good" replaces tests, security checks, and requirement coverage
• unfinished work gets marked complete because the model graded its own output

Most Claude Code setups are prompt packs: they change what the model is told, then still trust it to declare success. DonnyClaude is built around one idea: the model generates the work, but completion is decided by durable state, skeptical review, and deterministic gates.

What this changes on your machine

Everything installs under ~/.claude/ (user scope); nothing touches a project until you start one there.

• ~/.claude/skills/, agents/, commands/, hooks/, rules/ - the toolkit
• ~/.claude/donny/ - the workflow engine
• ~/.claude/bin/, cco-memory/, scrapers/, docs/, statusline.py, and a skill-index registry (.donnyclaude-skill-index.json) - support tools
• ~/.claude/CLAUDE.md - a fresh machine gets the full operating guide; an existing file gets only a clearly marked, idempotent standards block appended
• ~/.claude/settings.json - merged, with your original backed up to settings.json.bak first
• MCP registrations for Context7 (live docs) and Playwright (browser), at user scope

Existing settings are preserved, not clobbered. And you can inspect or reverse all of it:

npx donnyclaude --dry-run       # preview what install would change - no writes
npx donnyclaude doctor          # check installation health
npx donnyclaude diff            # drift between installed files and this version (exit 1 = drift)
npx donnyclaude uninstall       # remove every DonnyClaude-owned file; yours stay

uninstall accepts --dry-run, --yes, and --no-mcp. It removes only files this package ships, strips just the managed block from CLAUDE.md, leaves settings.json in place, and never touches anything you created yourself.

Quickstart

npx donnyclaude                 # install, then the setup wizard

# then, in Claude Code:
/donny-init                     # research -> requirements -> roadmap
/donny-plan-phase 1             # plan a phase (dependency + requirement gates)
/donny-execute-phase 1          # build it (parallel subagents, atomic commits)
/donny-verify-work 1            # conversational UAT
/donny-ship                     # open a PR once verification passes

Use /donny-progress any time to see where you are, /donny-autonomous to advance the whole roadmap hands-off, and /donny-help for every command.

Install as a plugin (experimental)

/plugin marketplace add d0nmega/donnyclaude
/plugin install donnyclaude@donnyclaude