SubagentStop
25Hook
Runs when a subagent finishes, executing on_subagent_stop.py via python3. From dentiny/kon.
Hook
Runs when a subagent finishes, executing on_subagent_stop.py via python3. From dentiny/kon.
Hook
Runs before the context is compacted, executing on_pre_compact.py via python3. From dentiny/kon.
Skill Claude CodeCodex
Multi-agent software engineering workflow. Use when the user mentions /kon: commands in plain text — 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…
Skill 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…
Cursor rule
Resolve once at the start of every kon command.
Agent
Challenge Mugi's plan during /kon:design — write gaps and risks to .kon/design-debate- .md only.
Agent
Explore the codebase before implementation. Find relevant files, conventions, and impact surface. No code changes.
Agent
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.
Agent
Strictly review Yui's implementation or an external PR. Default BLOCKED. Must be convinced by evidence. Follow skills/strict-review.
Agent
Turn requirements and exploration results into a structured, executable step-by-step plan. Write to the session-scoped plan file. No implementation code.
Agent
Write a clean, complete summary of what happened in the session. Called at the end of every run and on-demand via /kon:summarize.
Agent
Garbage collect the codebase — remove dead code, simplify over-complex logic, trim redundant comments and docs. No behavior changes.
Agent
Implement code changes per Mugi's plan. Follow existing conventions. No self-review.
Command
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.
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.
Skill 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.
Skill 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…
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).
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.
Skill Claude CodeCodex
Multi-agent design argument — Azusa challenges Mugi's plan, Mugi revises. Used by /kon:design after exploration and initial plan draft.
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.
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.
Skill Claude CodeCodex
Summarize a GitHub issue and all discussion comments. Used by /kon:describe-issue (Jun). Writes sessions/ /issue-summary.md.
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.