kon
01Plugin Claude Code
Bundles 1 skill, 18 commands, 6 hooks · 638 tokens together
K-On! multi-agent dev workflow — explore, plan, implement, cleanup, review.
not rated 3 3mo ago A
tokens not measured
original MIT
kon
02Skill Claude CodeCodex
Multi-agent software engineering workflow. Use this skill whenever the user types a /kon: command — including /kon:team, /kon:design, /kon:quick, /kon:debug, /kon:ask, /kon:review, /kon:review-pr, /kon:hunt, /kon:gc, /kon:research, /kon:describe-issue, /kon:begin, /kon:finish, /kon:summarize, /kon:retro…
not rated 3 3mo ago A 166 tokens
original MIT
kon
03Cursor rule Cursor
Resolve once at the start of every kon command.
not rated 3 3mo ago A 23 tokens
original MIT
Agent Claude Code
Challenge Mugi's plan during /kon:design — write gaps and risks to .kon/design-debate- .md only.
not rated 3 3mo ago A 34 tokens
original MIT
Azusa
05Agent Claude Code
Explore the codebase before implementation. Find relevant files, conventions, and impact surface. No code changes.
not rated 3 3mo ago A 24 tokens
original MIT
Jun
06Agent Claude Code
Look up external information — API docs, release notes, specs, best practices. Write findings to .kon/research.md or session issue summaries. No repo code changes.
not rated 3 3mo ago A 37 tokens
original MIT
Mio
07Agent Claude Code
Strictly review Yui's implementation or an external PR. Default BLOCKED. Must be convinced by evidence. Follow skills/strict-review.
not rated 3 3mo ago A 32 tokens
original MIT
Mugi
08Agent Claude Code
Turn requirements and exploration results into a structured, executable step-by-step plan. Write to the session-scoped plan file. No implementation code.
not rated 3 3mo ago A 31 tokens
original MIT
Nodoka
09Agent Claude Code
Write a clean, complete summary of what happened in the session. Called at the end of every run and on-demand via /kon:summarize.
not rated 3 3mo ago A 34 tokens
original MIT
Sawako
10Agent Claude Code
Garbage collect the codebase — remove dead code, simplify over-complex logic, trim redundant comments and docs. No behavior changes.
not rated 3 3mo ago A 30 tokens
original MIT
Yui
11Agent Claude Code
Implement code changes per Mugi's plan. Follow existing conventions. No self-review.
not rated 3 3mo ago A 20 tokens
original MIT
caveman
12Command Claude Code
Toggle caveman output compression for the current session. Applies to orchestrator chat and Ui narration only — artifact files (plan.md, review.md, etc.) are never compressed.
not rated 3 3mo ago A 35 tokens
original MIT
Skill Claude CodeCodex
When requirements, code behavior, root cause, or review scope is unclear — ask the user before proceeding. Never invent facts, assumptions, or fixes. Applies to every kon stage and every agent.
not rated 3 3mo ago A 45 tokens
original MIT
bug-hunt
14Skill Claude CodeCodex
This skill should be used for /kon:hunt — read-only bug analysis from source code with best-effort repro SQL and test suggestions. Azusa only; no fixes, no repo writes.
not rated 3 3mo ago A 43 tokens
original MIT
caveman
15Skill Claude CodeCodex
Compressed chat output mode. Strip filler prose from orchestrator and narrator responses while keeping full technical accuracy. Apply to conversational output only — narration beats, status lines, agent summaries in chat. Never apply to structured artifact files (plan.md, review.md, debug.md) or hook-validated…
not rated 3 3mo ago A 85 tokens
original MIT
Skill Claude CodeCodex
This skill should be used when drafting a git commit message from staged or proposed changes. Produces a user-impact subject and a concise body. Deliberately avoids motivation paragraphs (those belong in the PR description, not the commit log).
not rated 3 3mo ago A 50 tokens
original MIT
Skill Claude CodeCodex
Kon's two highest-priority principles for design, implementation, and review — first principles (don't hide the issue) and the simplest, most concise correct solution. Applies to every agent, skill, and workflow stage.
not rated 3 3mo ago A 48 tokens
original MIT
Skill Claude CodeCodex
Multi-agent design argument — Azusa challenges Mugi's plan, Mugi revises. Used by /kon:design after exploration and initial plan draft.
not rated 3 3mo ago A 35 tokens
original MIT
Skill Claude CodeCodex
When to spawn 📚 Jun for external lookup — WebSearch/docs/APIs — vs 🎸 Azusa for codebase exploration. Used by /kon:research, /kon:team, and /kon:design.
not rated 3 3mo ago A 48 tokens
original MIT
Skill Claude CodeCodex
This skill should be used when handling failures in pipeline command flows — Mio blocking with NEEDSCHANGES / BLOCKED, and infinite-loop protection for repeated same must-fix. Applies to /kon:quick, /kon:team, /kon:debug.
not rated 3 3mo ago A 56 tokens
original MIT
Skill Claude CodeCodex
Summarize a GitHub issue and all discussion comments. Used by /kon:describe-issue (Jun). Writes sessions/ /issue-summary.md.
not rated 3 3mo ago A 37 tokens
original MIT
Skill Claude CodeCodex
Route plain-text user messages while a /kon:begin session is open. Reuse the same session JSON — never init a second session for sub-turns.
not rated 3 3mo ago A 35 tokens
original MIT
Skill Claude CodeCodex
This skill should be used by all kon agents at startup, before beginning work, to load relevant memory from public and repo indexes with relevance-based ordering and a 10-entry cap. Consumers: Azusa, Mugi, Mio, Jun, and any future memory-reading agent.
not rated 3 3mo ago A 0 tokens
original MIT
Skill Claude CodeCodex
This skill should be used by the kon orchestrator when saving memory — from.
not rated 3 3mo ago A 20 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: