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
3Stars on the repository
63Mods indexed here, across every type
3mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Azusa
02Agent 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
03Agent 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
04Agent 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
05Agent 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
06Agent 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
07Agent 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
08Agent 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
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: