claude

cadence

A Claude Code plugin that brings engineering practices to software you'll keep running after the session ends. It writes a plan before code, commits once per task, holds tests to a stopping rule, and checks the result against your goal. Its records live in your repository, so a new session picks up where the last one stopped.

11 on GitHubby John Crenshawv4.1.0MITupdated yesterday
/

Plugin cadence from marketplace cadence in crenshawdev/cadence. Commands read from the repo's manifest — yesterday.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (36)

  • cad-adopt

    Initialize .planning/ from a repo that already exists - PROJECT.md, REQUIREMENTS.md and a remaining-work ROADMAP.md derived from the code and the git history

  • cad-assumptions-analyzer-contract

    Role contract preloaded at spawn by the cad-assumptions-analyzer, cad-assumptions-analyzer-low, cad-assumptions-analyzer-medium, cad-assumptions-analyzer-high and cad-assumptions-analyzer-max agents. Not for direct use: do not invoke it from a conversation.

  • cad-audit

    Pre-ship traceability audit - every requirement traced to a phase, plan and verification, orphan detection both directions, a FAIL gate before shipping

  • cad-capture

    Capture a phase-linked todo, a seed idea for a future milestone, or a note, without losing your place - .planning/CAPTURE.md, or --cadence for friction with Cadence itself

  • cad-config

    Configure Cadence's config.json - workflow toggles, the per-role model and effort interview, and interactive cross-model review provider setup

  • cad-context

    Gather phase context before planning - codebase assumptions, locked decisions, falsifiable acceptance criteria - in one pass

  • cad-coverage

    Find a completed phase's requirements with no failing-capable test coverage and generate tests to close the gaps, in the project's own framework

  • cad-debug

    Systematic debugging - hypothesis and symptom tracked in a state file that survives /clear, with a user-gated second-model consult at dead ends

  • cad-decision-review

    Adversarial refute-then-adjudicate pass over one load-bearing decision - a CONTEXT D-NN line or a PROJECT Key Decisions row - with per-objection rulings

  • cad-docs-verify

    Verify docs claims against the live codebase - paths, commands, symbols, config keys - each reported accurate, stale or unverifiable. Reports; it does not rewrite docs

  • cad-execute

    Execute a phase's plans - a subagent per plan, an atomic commit per task, a slim per-phase SUMMARY

  • cad-executor-contract

    Role contract preloaded at spawn by the cad-executor, cad-executor-low, cad-executor-medium, cad-executor-xhigh and cad-executor-max agents. Not for direct use: do not invoke it from a conversation.

  • cad-health

    Planning-health check - .planning's core docs present, the STATE cursor, ROADMAP and REQUIREMENTS parseable and consistent. Not a traceability audit (that is /cad-audit)

  • cad-help

    Cadence's own help - the command reference for every /cad-* skill, grouped by cluster; pass a command name for just that entry

  • cad-land

    Land finished work - report git state, then ask how to publish (push / MR or PR / tag / leave local). With git.auto_close set in both the repository and your user-global config, it runs PR -> merge unattended and halts on a surviving blocker

  • cad-map

    Build or refresh the code map - what the code is, what touches what and which tests pin it. Runs only with planning.code_map on, and starts nothing until a typed yes

  • cad-mapper-contract

    Role contract preloaded at spawn by the cad-mapper, cad-mapper-low, cad-mapper-medium, cad-mapper-xhigh and cad-mapper-max agents. Not for direct use: do not invoke it from a conversation.

  • cad-milestone

    Cut a milestone - audit that nothing was dropped, bump a release's version, prune completed phases from the roadmap, evolve PROJECT and refresh REQUIREMENTS

  • cad-minimalism-review

    Ranked delete-list over code that works and should not exist - reinvented stdlib, one-implementation abstractions, dead flexibility, config nobody sets

  • cad-new-project

    Initialize a project through deep questioning - PROJECT.md, REQUIREMENTS.md, a phased ROADMAP.md and .planning/ state

  • cad-pause

    Pause work cleanly - a WIP commit of in-flight changes plus a STATE cursor set to paused with a one-line resume pointer (/cad-progress offers to resume it)

  • cad-phase

    CRUD phases in ROADMAP - add, insert, remove, edit, with remove/insert renumbering the following phases, their .planning dirs and their live references, while insert and remove leave shipped requirement rows as written

  • cad-plan-checker-contract

    Role contract preloaded at spawn by the cad-plan-checker, cad-plan-checker-medium, cad-plan-checker-high, cad-plan-checker-xhigh and cad-plan-checker-max agents. Not for direct use: do not invoke it from a conversation.

  • cad-plan-review

    On-demand adversarial plan review of a phase PLAN.md before code - for a hand-written, imported or just-edited plan (/cad-plan fires this itself)

  • cad-plan

    Create an executable phase plan (PLAN.md) - planner subagent, optional check gate, plan review trigger

  • cad-planner-contract

    Role contract preloaded at spawn by the cad-planner, cad-planner-low, cad-planner-medium, cad-planner-xhigh and cad-planner-max agents. Not for direct use: do not invoke it from a conversation.

  • cad-progress

    Project progress - count-based status from files and git, finds incomplete or paused work and offers to resume it, --stats for a quick summary

  • cad-report

    Render a phase's run record as a receipts narrative - what each dispatch cost, what the gates caught, what got refuted - straight from trace.jsonl and the phase artifacts

  • cad-reviewer-contract

    Role contract preloaded at spawn by the cad-reviewer, cad-reviewer-low, cad-reviewer-medium, cad-reviewer-xhigh and cad-reviewer-max agents. Not for direct use: do not invoke it from a conversation.

  • cad-spike

    Spike - a time-boxed experiment resolving one unknown before you bet on it, risk-first, with a validated | invalidated | inconclusive verdict

  • cad-suggest

    Turn the run record into evidence-backed retune suggestions - each with its config key, the value in force, a direction and a target - and offer to route the ones you accept to /cad-config

  • cad-task

    Execute a small off-roadmap task with atomic commits - inline by default, --plan for multi-step work

  • cad-undo

    Safely undo a phase - roll back its commits from the SUMMARY manifest, revert (or --no-commit to re-do), and reset the phase status

  • cad-verifier-contract

    Role contract preloaded at spawn by the cad-verifier, cad-verifier-low, cad-verifier-medium, cad-verifier-xhigh and cad-verifier-max agents. Not for direct use: do not invoke it from a conversation.

  • cad-verify

    Verify a completed phase by conversational UAT - a persistent checklist that survives /clear, plus cross-phase and goal-backward passes

  • cad-why

    Why is this code like this - a git-log chain over one file[:line], joined to the phase, task, decision, deviation and review record on disk

Subagents (35)

  • cad-assumptions-analyzer-high

    The `high` rung of `cad-assumptions-analyzer`; `bin/route.mjs` picks it, not the user.

  • cad-assumptions-analyzer-low

    The `low` rung of `cad-assumptions-analyzer`; `bin/route.mjs` picks it, not the user.

  • cad-assumptions-analyzer-max

    The `max` rung of `cad-assumptions-analyzer`; `bin/route.mjs` picks it, not the user.

  • cad-assumptions-analyzer-medium

    The `medium` rung of `cad-assumptions-analyzer`; `bin/route.mjs` picks it, not the user.

  • cad-assumptions-analyzer

    The `xhigh` rung of `cad-assumptions-analyzer` (codebase assumption gathering); `bin/route.mjs` picks it, not the user.

  • cad-executor-low

    The `low` rung of `cad-executor`; `bin/route.mjs` picks it, not the user.

  • cad-executor-max

    The `max` rung of `cad-executor`; `bin/route.mjs` picks it, not the user.

  • cad-executor-medium

    The `medium` rung of `cad-executor`; `bin/route.mjs` picks it, not the user.

  • cad-executor-xhigh

    The `xhigh` rung of `cad-executor`; `bin/route.mjs` picks it, not the user.

  • cad-executor

    The `high` rung of `cad-executor` (plan task execution); `bin/route.mjs` picks it, not the user.

  • cad-mapper-low

    The `low` rung of `cad-mapper` (code map reader); `bin/route.mjs` picks it, not the user.

  • cad-mapper-max

    The `max` rung of `cad-mapper` (code map reader); `bin/route.mjs` picks it, not the user.

  • cad-mapper-medium

    The `medium` rung of `cad-mapper` (code map reader); `bin/route.mjs` picks it, not the user.

  • cad-mapper-xhigh

    The `xhigh` rung of `cad-mapper` (code map reader); `bin/route.mjs` picks it, not the user.

  • cad-mapper

    The `high` rung of `cad-mapper` (code map reader); `bin/route.mjs` picks it, not the user.

  • cad-plan-checker-high

    The `high` rung of `cad-plan-checker`; `bin/route.mjs` picks it, not the user.

  • cad-plan-checker-max

    The `max` rung of `cad-plan-checker`; `bin/route.mjs` picks it, not the user.

  • cad-plan-checker-medium

    The `medium` rung of `cad-plan-checker`; `bin/route.mjs` picks it, not the user.

  • cad-plan-checker-xhigh

    The `xhigh` rung of `cad-plan-checker`; `bin/route.mjs` picks it, not the user.

  • cad-plan-checker

    The `low` rung of `cad-plan-checker` (goal-backward plan gate); `bin/route.mjs` picks it, not the user.

  • cad-planner-low

    The `low` rung of `cad-planner`; `bin/route.mjs` picks it, not the user.

  • cad-planner-max

    The `max` rung of `cad-planner`; `bin/route.mjs` picks it, not the user.

  • cad-planner-medium

    The `medium` rung of `cad-planner`; `bin/route.mjs` picks it, not the user.

  • cad-planner-xhigh

    The `xhigh` rung of `cad-planner`; `bin/route.mjs` picks it, not the user.

  • cad-planner

    The `high` rung of `cad-planner` (phase plan authoring); `bin/route.mjs` picks it, not the user.

  • cad-reviewer-low

    The `low` rung of `cad-reviewer`; `bin/route.mjs` picks it, not the user.

  • cad-reviewer-max

    The `max` rung of `cad-reviewer`; `bin/route.mjs` picks it, not the user.

  • cad-reviewer-medium

    The `medium` rung of `cad-reviewer`; `bin/route.mjs` picks it, not the user.

  • cad-reviewer-xhigh

    The `xhigh` rung of `cad-reviewer`; `bin/route.mjs` picks it, not the user.

  • cad-reviewer

    The `high` rung of `cad-reviewer` (adversarial artifact review); `bin/route.mjs` picks it, not the user.

  • cad-verifier-low

    The `low` rung of `cad-verifier`; `bin/route.mjs` picks it, not the user.

  • cad-verifier-max

    The `max` rung of `cad-verifier`; `bin/route.mjs` picks it, not the user.

  • cad-verifier-medium

    The `medium` rung of `cad-verifier`; `bin/route.mjs` picks it, not the user.

  • cad-verifier-xhigh

    The `xhigh` rung of `cad-verifier`; `bin/route.mjs` picks it, not the user.

  • cad-verifier

    The `high` rung of `cad-verifier` (goal-backward phase verification); `bin/route.mjs` picks it, not the user.

Hooks (3)

  • PreToolUse

    node "${CLAUDE_PLUGIN_ROOT}/cadence-core/bin/git-guard.mjs"

  • PostToolUse

    node "${CLAUDE_PLUGIN_ROOT}/cadence-core/bin/read-trace.mjs"

  • SubagentStop

    node "${CLAUDE_PLUGIN_ROOT}/cadence-core/bin/subagent-trace.mjs"

View source on GitHub

Similar plugins

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development

9 skills · 1 command · 8 agents

wshobson/agents 42,461

beads

claudecodex

AI-supervised issue tracker for coding workflows

1 skill · 1 agent · hooks

gastownhall/beads 28,698

PRD generation and conversion skills for the Ralph autonomous agent loop

2 skills

snarktank/ralph 22,224

Maintain cadence?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted