claude

kaizen

The engine around Addy Osmani's agent-skills, embedded: one plugin with its whole workflow under /kaizen: (spec, plan, build, test, review, ship, ideate, debug…), plus what it does not do — a quality gate that keeps a turn open while checks are red, agent-skills' review recorded by itself and required before any push, no secret committed, learnings brought back when a spec, a plan or a file they cover is touched, the PR followed to looks-ready (/kaizen:watch), approximated DORA metrics, friction and cost per feature (/kaizen:metrics). Stops at the merge-ready PR: no deployment

5 on GitHubby Angelo LIMAv1.1.0MITupdated todaydevelopment
/

Plugin kaizen from marketplace dojo in Lingelo/dojo. Commands read from the repo's manifest — today.

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 (4)

  • learn

    Keeps the project's memory — captures one solved problem as a durable learning in docs/learnings/ (validated frontmatter, corpus vocabulary, updated rather than duplicated), harvests every lesson of a finished piece of work one at a time, or prunes the learnings that went stale or duplicate. Kaizen'

  • metrics

    Reads the delivery numbers honestly — DORA metrics approximated from git and GitHub (frequency, lead time, rework rate, change failure rate), batch size, whether learnings are read back and applied, how often the gates stopped the work, and what each feature or fix cost in tokens (kaizen cost) — the

  • setup

    Sets Kaizen (with the agent-skills workflow it embeds) up in a repository, and says where the repository stands — initializes .kaizen/config.json and docs/learnings/, validates the verification commands the quality gate will run, declares kaizen@dojo for every clone, runs kaizen doctor, then names t

  • watch

    Follows an open GitHub pull request until it honestly looks ready to merge — each cycle handles review feedback first (a verdict per comment, the fix pushed before the reply, the thread resolved, human decisions left open), then the head commit's red CI (one rerun for infrastructure, a real fix othe

Slash commands (15)

  • /kaizen:adr

    Record an architecture decision — context, options, decision, consequences

  • /kaizen:build

    Implement tasks incrementally — build, test, verify, commit. Add "auto" to run the whole plan in one approved pass.

  • /kaizen:code-simplify

    Simplify code for clarity and maintainability — reduce complexity without changing behavior

  • /kaizen:constraints

    Define and enforce this project's quality bar — interview, sane defaults, CONSTRAINTS.md

  • /kaizen:debug

    Find the root cause of a failure — reproduce, isolate, fix, guard against its return

  • /kaizen:doubt

    Cross-examine a plan, a decision or a claim before it stands — fresh-context adversarial review

  • /kaizen:ideate

    Brainstorm an idea before the spec — clarify the intent, diverge, stress-test, converge

  • /kaizen:migrate

    Plan a deprecation or a migration — old system, API, feature or schema out, safely

  • /kaizen:plan

    Break work into small verifiable tasks with acceptance criteria and dependency ordering

  • /kaizen:review

    Conduct a five-axis code review — correctness, readability, architecture, security, performance

  • /kaizen:security

    Security audit of the changes or of a given area — untrusted input, auth, secrets, data

  • /kaizen:ship

    Run the pre-launch checklist via parallel fan-out to specialist personas, then synthesize a go/no-go decision

  • /kaizen:spec

    Start spec-driven development — write a structured specification before writing code

  • /kaizen:test

    Run TDD workflow — write failing tests, implement, verify. For bugs, use the Prove-It pattern.

  • /kaizen:webperf

    Run a web performance audit via the web-performance-auditor persona

Subagents (4)

  • code-reviewer

    Senior code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, and performance. Use for thorough code review before merge.

  • security-auditor

    Security engineer focused on vulnerability detection, threat modeling, and secure coding practices. Use for security-focused code review, threat analysis, or hardening recommendations.

  • test-engineer

    QA engineer specialized in test strategy, test writing, and coverage analysis. Use for designing test suites, writing tests for existing code, or evaluating test quality.

  • web-performance-auditor

    Web performance engineer focused on Core Web Vitals, loading, rendering, and network optimization. Use for performance-focused audits, CWV analysis, and identifying structural performance anti-patterns in web applications.

Hooks (8)

  • SessionStart

    node "${CLAUDE_PLUGIN_ROOT}/scripts/review-hooks.mjs" --heartbeat

  • PreToolUse

    node "${CLAUDE_PLUGIN_ROOT}/scripts/secret-gate.mjs"

  • PreToolUse

    node "${CLAUDE_PLUGIN_ROOT}/scripts/review-gate.mjs"

  • PostToolUse

    node "${CLAUDE_PLUGIN_ROOT}/scripts/post-edit.mjs"

  • PostToolUse

    node "${CLAUDE_PLUGIN_ROOT}/scripts/review-hooks.mjs" --evidence

  • Stop

    node "${CLAUDE_PLUGIN_ROOT}/scripts/quality-gate.mjs"

  • Stop

    node "${CLAUDE_PLUGIN_ROOT}/scripts/review-hooks.mjs" --stop

  • Stop

    node "${CLAUDE_PLUGIN_ROOT}/scripts/ledger-hook.mjs"

View source on GitHub

More from Lingelo/dojo

All 4 plugins →

agent-skills

claudecodex

Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.

25 skills · 4 agents

5

Motion design as code: HTML/CSS/SVG/Canvas animations rendered frame by frame to MP4/WebM/GIF via Playwright + ffmpeg, with synced sound, voice-over and subtitles

1 skill

5

Presentation decks as one HTML file: themed template with 19 layouts (ink, paper, kaizen), browser presenter with notes and steps, slide-by-slide layout check, PDF/PNG export

1 skill

5

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

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

15 skills · hooks

obra/superpowers 316,836

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

Maintain kaizen?

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 plugins4 plugins