Skill Claude CodeCodex
Task subagents must use the orchestrator's model — Cursor defaults to Composer if model is omitted. Applies whenever spawning Task subagents in kon.
not rated 3 3mo ago A 33 tokens
original MIT
narration
26Skill Claude CodeCodex
This skill should be used by the kon orchestrator on every /kon command, to frame the run with Ui narration at the opening, the closing, and stuck-point beats, and to enforce the emoji prefix on every mention of a kon agent or narrator.
not rated 3 3mo ago A 55 tokens
original MIT
Skill Claude CodeCodex
Keep orchestrator chat lean — artifacts hold full agent output; orchestrator routes by file pointer only. Applies to all /kon: commands that spawn Task subagents.
not rated 3 3mo ago A 38 tokens
original MIT
Skill Claude CodeCodex
This skill should be used by the kon orchestrator on every /kon command, alongside narration, to govern the conversational conduct of the main dialogue — AskUserQuestion widget discipline and word-choice norms.
not rated 3 3mo ago A 45 tokens
original MIT
Skill Claude CodeCodex
Mandatory understanding check after exploration and before any Mugi planning step. Orchestrator asks high-level and implementation questions; do not spawn Mugi until answers resolve material gaps. Applies to /kon:team, /kon:design, /kon:debug.
not rated 3 3mo ago A 56 tokens
original MIT
repo-skill
30Skill Claude CodeCodex
Convention for per-repo skill directories at /.kon/projects/ /skills/ /SKILL.md. Each named subdirectory is one skill. Agents load all SKILL.md files as the first step before memory entries.
not rated 3 3mo ago A 50 tokens
original MIT
review-pr
31Skill Claude CodeCodex
Holistic GitHub PR review — code diff, PR description, existing review comments, and linked issues. Used by /kon:review-pr (Mio). Read-only; no gh pr merge or code edits.
not rated 3 3mo ago A 46 tokens
original MIT
Skill Claude CodeCodex
This skill should be used by the orchestrator at the end of pipeline commands (team, quick, design, debug, gc, address-comments) after /kon:summarize, to propose session learnings for public or repo memory with human confirmation before write.
not rated 3 3mo ago A 56 tokens
original MIT
Skill Claude CodeCodex
This skill should be used when performing code review on a diff (whether implemented by another agent or an external PR), enforcing a strict reviewer stance, applying a mandatory 7-item golden checklist, demanding evidence, and giving specific改法 instead of vague critique.
not rated 3 3mo ago A 54 tokens
original MIT
Skill Claude CodeCodex
This skill should be used when orchestrating the full kon teammate flow — Azusa explores, Mugi plans, Yui implements, Sawako cleans, Mio reviews. Applies to /kon:team.
not rated 3 3mo ago A 45 tokens
original MIT
Skill Claude CodeCodex
Map a codebase for learning — glossary, architecture, flashcards, and quiz. Produces interactive HTML (clickable terms/diagrams + side panel) and an optional PDF.
not rated 3 3mo ago A 42 tokens
original MIT
yolo-mode
36Skill Claude CodeCodex
This skill should be used when the user passes --yolo to any kon command. The orchestrator proceeds autonomously through all confirmation checkpoints, accepting defaults and auto-retrying failures. Stops only when genuine human judgment is required.
not rated 3 3mo ago A 49 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: