cadence
by John Crenshaw · ★ 6 · updated yesterday
A plan/execute/verify loop for a single developer in Claude Code, with adversarial review at every gate: plans and diffs get refuted by a fresh Claude subagent or a panel of outside models (OpenAI, Gemini, DeepSeek), not just approved. State lives in files, not the conversation, so you clear aggressively and keep both your context and your token bill lean.
Install
/plugin marketplace add crenshawdev/cadence/plugin install cadence@cadenceThen run /reload-plugins or start a new session. Requires Claude Code 2.1.287+.
What it hooks into
From an automated scan with claude plugin validate, not a security review. Mods run with your permissions; read the code before installing.
- Events
turn.stepclassic.SubagentStartclassic.SubagentStoptool.callagent.offerprompt.attachmentui.rendersession.startcommand.runui.close- API calls
$.agent.list$.command.register$.fs.exists$.fs.read$.process.run$.prompt.fill$.session.cwd$.session.id$.session.model$.ui.invalidate$.ui.open$.ui.panes$.ui.resolve- Draws
AbovePromptCommandOutputPane- Can see
classic hooksevery tool call- Reach
- level 2 of 3 runs processeswrites the prompt boxreads filesdraws
Origin
- How it got here
- Automated scan of public GitHub repos, via the CC0 dataset awesome-claude-code-mods (scan of ).
- Repository
- github.com/crenshawdev/cadence
- Path in repo
- repository root
- Source commit
7e4da20the exact code the scan read- Author
- John Crenshaw @crenshawdev
- License
- MIT
- First published
- Last pushed
- First listed here
Name and description come from the mod's own manifest. We link to the code; we don't host it, and it stays under its author's license.