Kimi Challenge — Design agent for Claude Code
Use this agent when Claude wants Kimi to run an adversarial review that challenges the implementation approach, design choices, tradeoffs, and assumptions rather than just flagging defects.
How to install Kimi Challenge
Installs to ~/.claude/agents/linxule-kimi-plugin-cc-kimi-challenge.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/linxule/kimi-plugin-cc/HEAD/agents/kimi-challenge.md -o ~/.claude/agents/linxule-kimi-plugin-cc-kimi-challenge.md Restart Claude Code, or start a new session, for it to be picked up.
What Kimi Challenge does
name: kimi-challenge description: Use this agent when Claude wants Kimi to run an adversarial review that challenges the implementation approach, design choices, tradeoffs, and assumptions rather than just flagging defects. Choose this agent when the user wants pushback on whether the chosen approach is the right one, not a tighter pass over implementation defects (see kimi-review for that). model: sonnet tools: Bash color: yellow
kimi:challenge
Forward an adversarial challenge-revie
Alternatives in Design
- Apex Architect — Use this agent when the user needs strategic architecture analysis, design tradeoffs, or read-only debugging 523 ★
- Template Cloner — Use this agent whenever Pulkit gives a UI template/website URL in the fable repo and wants it reproduced same 509 ★
- Omd Persona Tester — Adversarial synthetic user that walks through generated UI under a strict persona prompt with hard turn budget 465 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Kimi Review
Use this agent when Claude wants an independent second-pair-of-eyes review from Kimi over a working-tree diff
Scope Reviewer
Strategic scope review — challenge assumptions about WHAT to build before design work begins. Four modes: EXPA
Decision Challenger
Devil's advocate for ADRs, SDRs, and tech radar entries. Challenges assumptions, surfaces second-order effects
Angela
Adversarially review a plan's architecture, or review a finished diff for architectural soundness and regressi
Orchestrator Implementer
Opus implementation specialist for the orchestrator skill. Use only for a JUDGEMENT task the lead chose to del
Fable Architect
Plan-only Fable 5.1 pass from an Opus or Sonnet main. Use for architecture, ambiguous root cause, or a design
Related Skills
Codex Plan Review
Adversarial Codex review of a PLAN or design (not code) via the local Codex CLI. Read-only second-model challe
Envoy Adversarial Review
Run a Codex review that challenges the implementation approach and design choices
Legal Pt Ul
Maintain the ubiquitous language glossary for Brazilian legal domain. Use when user wants to add terms, flag a