dentiny

63 mods across 1 repository, 3 stars between them.

SubagentStop

25

dentiny/kon

Hook

Runs when a subagent finishes, executing on_subagent_stop.py via python3. From dentiny/kon.

3 1mo ago A tokens not measured original MIT

PreCompact

26

dentiny/kon

Hook

Runs before the context is compacted, executing on_pre_compact.py via python3. From dentiny/kon.

3 1mo ago A tokens not measured original MIT

kon

27

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…

3 1mo ago A 133 tokens original MIT

kon

28

dentiny/kon

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…

3 1mo ago A 166 tokens original MIT

kon

29

dentiny/kon

Cursor rule

Resolve once at the start of every kon command.

3 1mo ago A 23 tokens original MIT

Azusa-challenge

30

dentiny/kon

Agent

Challenge Mugi's plan during /kon:design — write gaps and risks to .kon/design-debate- .md only.

3 1mo ago A 34 tokens original MIT

Azusa

31

dentiny/kon

Agent

Explore the codebase before implementation. Find relevant files, conventions, and impact surface. No code changes.

3 1mo ago A 24 tokens original MIT

Jun

32

dentiny/kon

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.

3 1mo ago A 37 tokens original MIT

Mio

33

dentiny/kon

Agent

Strictly review Yui's implementation or an external PR. Default BLOCKED. Must be convinced by evidence. Follow skills/strict-review.

3 1mo ago A 32 tokens original MIT

Mugi

34

dentiny/kon

Agent

Turn requirements and exploration results into a structured, executable step-by-step plan. Write to the session-scoped plan file. No implementation code.

3 1mo ago A 31 tokens original MIT

Nodoka

35

dentiny/kon

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.

3 1mo ago A 34 tokens original MIT

Sawako

36

dentiny/kon

Agent

Garbage collect the codebase — remove dead code, simplify over-complex logic, trim redundant comments and docs. No behavior changes.

3 1mo ago A 30 tokens original MIT

Yui

37

dentiny/kon

Agent

Implement code changes per Mugi's plan. Follow existing conventions. No self-review.

3 1mo ago A 20 tokens original MIT

caveman

38

dentiny/kon

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.

3 1mo ago A 35 tokens original MIT

ask-dont-guess

39

dentiny/kon

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.

3 1mo ago A 45 tokens original MIT

bug-hunt

40

dentiny/kon

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.

3 1mo ago A 43 tokens original MIT

caveman

41

dentiny/kon

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…

3 1mo ago A 85 tokens original MIT

commit-message

42

dentiny/kon

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).

3 1mo ago A 50 tokens original MIT

core-principles

43

dentiny/kon

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.

3 1mo ago A 48 tokens original MIT

design-debate

44

dentiny/kon

Skill Claude CodeCodex

Multi-agent design argument — Azusa challenges Mugi's plan, Mugi revises. Used by /kon:design after exploration and initial plan draft.

3 1mo ago A 35 tokens original MIT

external-research

45

dentiny/kon

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.

3 1mo ago A 48 tokens original MIT

failure-handling

46

dentiny/kon

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.

3 1mo ago A 56 tokens original MIT

dentiny/kon

Skill Claude CodeCodex

Summarize a GitHub issue and all discussion comments. Used by /kon:describe-issue (Jun). Writes sessions/ /issue-summary.md.

3 1mo ago A 37 tokens original MIT

interactive-session

48

dentiny/kon

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.

3 1mo ago A 35 tokens original MIT