Enforce mindful, checklist-driven AI coding discipline via /kasi-* commands and specialist agents for code reviews, security audits, backend fixes, DevOps runbooks, refactors, and knowledge management. Orchestrates multi-model tiers (Opus/Sonnet/Haiku), builds project indexes/graphs, syncs global patterns, and captures replayable session histories in Markdown.
npx claudepluginhub kasidit-wansudon/kasidit --plugin kasiditCapture the steps just performed (deploy/migration/hotfix/etc.) as a replayable runbook. Writes to .kasidit/knowledge/runbooks/.
Backend mission — multi-mode (fix/audit/scaffold/design/perf) for API/controller/service/route/DB work
Tier cascade orchestration — Opus plans, Sonnet works, Haiku greps
DevOps mission — deploy flow, infra, CI/CD, env vars, data structure connections, runbooks
Fetch and cache version-matched official documentation
Bug fix mission with conservative discipline
Function call graph — build/show/extract subgraph for scoped audit
Initialize Kasidit on first install — 1-question prompt, scaffold, wire hooks, seed Gravity hub. One-shot.
Browse stored runbooks and knowledge entries — pick one by number to print "how to do it again".
Fan-out mode — dispatch N specialist agents in parallel for the current mission. `/kasi-multi` default N=6; `sudo` shorthand uses min 2 for speed. Max per tier cap.
Promote fact / pattern / knowledge from project .kasidit/ (dcenterlite) into global Centerlite hub
Pull item from Centerlite hub into local project .kasidit/ (dcenterlite)
Launch code review mission with Kasidit discipline
Build .kasidit/ knowledge structure for current project
Semantic search over .kasidit/knowledge/ using local embeddings
Security audit mission with checklist-driven scanning
Show current mission state, counter, and context usage
Project structure index — file paths, module relations, function call graph, auto-bridged so AI doesn't rescan every time
Audit diffs between project .kasidit/ (dcenterlite) and global Centerlite hub
UI/CSS fix mission with Override Mode
Sync docs/wiki/ content to github wiki repo (github.com/kasidit-wansudon/kasidit.wiki.git)
Toggle Kasidit intensity — off / router / lite / full / ultra. Session-level by default; use `save` to persist.
Plan BEFORE code for new features, significant refactors, or changes touching more than 2 files. Returns step-by-step plan, file list, data flow, trade-offs. Does NOT write code.
Multi-focus audit agent — review code quality, security, or performance depending on --focus flag. Replaces and supersedes separate code-reviewer, security-auditor, perf-profiler agents (v0.10). Use --focus=quality|security|perf|all.
Hunt down root cause of a reported bug. Use when test breaks, endpoint returns wrong data, stack trace appears, or user says "why does X fail". Returns minimal-change fix with reproduction.
Deprecated stub (v0.10). Delegated to audit-specialist --focus=quality. Kept for name resolution only; removed in v0.11.
Deep investigation across docs, source, web for library/API/framework questions. Use when task needs version-matched docs, competitor analysis, or codebase survey before deciding. Returns findings + sources, never writes final code.
Navigate and modify legacy codebases (ZF1, old Rails, Vue 2, etc.) without breaking them
Handle schema changes, framework upgrades, and data backfills safely. Specialist on backward-compat + zero-downtime patterns. High-risk work — deserves dedicated context.
Deprecated stub (v0.10). Delegated to audit-specialist --focus=perf. Kept for name resolution only; removed in v0.11.
Apply a specific, scoped refactor — extract function, rename, dedupe, split file, inline. Use when user names the refactor explicitly. Does NOT decide whether to refactor, only how. Preserves behavior exactly.
Deprecated stub (v0.10). Delegated to audit-specialist --focus=security. Kept for name resolution only; removed in v0.11.
Write unit or integration tests for a specific function, class, or endpoint. Use when user asks for tests, after a bug fix (regression test), or to backfill coverage. Produces runnable test file + gap notes.
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Multi-AI orchestration pipeline with Task-based enforcement and Codex final gate
AI-powered development workflow automation - Phase-based planning, implementation orchestration, preflight code quality checks with security scanning, ship-it workflow, and development principles generator for CLAUDE.md
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code.
Turn on Godmode for Claude Code. 126 skills. 7 subagents. Zero configuration.
Use this agent when designing APIs, building server-side logic, implementing databases, or architecting scalable backend systems. This agent specializes in creating robust, secure, and performant backend services. Examples:\n\n<example>\nContext: Designing a new API\nuser: "We need an API for our social sharing feature"\nassistant: "I'll design a RESTful API with proper authentication and rate limiting. Let me use the backend-architect agent to create a scalable backend architecture."\n<commentary>\nAPI design requires careful consideration of security, scalability, and maintainability.\n</commentary>\n</example>\n\n<example>\nContext: Database design and optimization\nuser: "Our queries are getting slow as we scale"\nassistant: "Database performance is critical at scale. I'll use the backend-architect agent to optimize queries and implement proper indexing strategies."\n<commentary>\nDatabase optimization requires deep understanding of query patterns and indexing strategies.\n</commentary>\n</example>\n\n<example>\nContext: Implementing authentication system\nuser: "Add OAuth2 login with Google and GitHub"\nassistant: "I'll implement secure OAuth2 authentication. Let me use the backend-architect agent to ensure proper token handling and security measures."\n<commentary>\nAuthentication systems require careful security considerations and proper implementation.\n</commentary>\n</example>
Production-ready Claude Code configuration with role-based workflows (PM→Lead→Designer→Dev→QA), safety hooks, 44 commands, 19 skills, 8 agents, 43 rules, 30 hook scripts across 19 events, auto-learning pipeline, hook profiles, and multi-language coding standards