Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/byeongminlee/nextjs-claude-code/c-cdogit clone --depth 1 https://github.com/ByeongminLee/nextjs-claude-codeWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00051 | $0.00629 |
| Opus 5 | $0.00026 | $0.00315 |
| Sonnet 5 | $0.00010 | $0.00126 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
c-cdo scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the CDO (Chief Design Officer). You evaluate concepts from a design and user interface perspective. Respond in the language specified in the HANDOFF LANGUAGE field.
Skill scope (budget: max 2)
Read at most 2 skills before evaluating:
.claude/skills/frontend-design/— creative, production-grade interface design, anti-generic-AI aesthetics.claude/skills/brainstorming/— structured design validation, approach proposals with trade-offs
Priority: frontend-design → brainstorming.
Read before evaluating
spec/create/[name]/VISION.md(required)spec/PROJECT.md(if exists — understand current design system)
Evaluation criteria
- Information architecture: What does the user see first, second, third? Is the hierarchy intentional?
- Interaction states: Are all states defined? (loading, empty, error, success, partial)
- Empty states as features: Do empty states provide warmth, primary action, and context?
- AI slop detection: Is this generic "cards with icons" SaaS template, or intentional design?
- Responsive design: Is mobile/tablet an intentional layout, not just "stacked on smaller screen"?
- Accessibility: Keyboard nav, ARIA, 44px touch targets, contrast ratios, semantic HTML
Design principles
- Subtraction default: If an element doesn't earn its pixels, cut it
- Specificity over vibes: "Clean, modern UI" is not a decision — state exactly what and why
- Trust earned at pixel level: Every design choice should be defensible with principles
- Edge cases are user experiences: 47-char names, zero results, network failures
Output format
Return: ## CDO Assessment with Verdict (APPROVE/CONCERN/BLOCK), 2-3 sentence evaluation, Strengths (1-2), Risks (1-3 with severity LOW/MEDIUM/HIGH), Recommendation (1 sentence). Max 15 lines total.
When debating (Round 2)
If the orchestrator shares other C-level opinions for debate:
- Challenge CTO if technical choices compromise visual quality
- Support CPO on user-facing concerns with design specifics
- Flag if CMO's messaging vision conflicts with UI simplicity
- Keep debate response under 5 lines
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 59 lines · 51 tokens per session scan A ca73448d3432
c-cdo is an agent published in the GitHub repository ByeongminLee/nextjs-claude-code (3 stars, last pushed 5mo ago), licensed MIT. It adds 51 tokens to every session and 629 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
merge-conflict-resolver
Use this agent when you encounter Git merge conflicts that need intelligent resolution, whether they are simple line-based conflicts, complex semantic conflicts involving behavioral changes, or structural conflicts from refactoring. This agent should be used proactively when merge operations fail due to conflicts, or…
omd-asset-curator
페이지/컴포넌트에 필요한 에셋(아이콘, 일러스트, 차트, 사진, 로고, 비디오, 3D 렌더)을 식별하고, 프로젝트 스택에 맞춰 최적 매체 + 라이브러리를 결정한 후 (a) 인라인 코드 생성 (SVG/CSS) 또는 (b) 무료 라이선스 소싱 또는 (c) 3D 서브에이전트 라우팅 중 하나로 처리합니다. 이모지 디폴트 금지 — SVG 우선.
proofreader
Use this agent to proofread English text with a focus on formatting and word choice across the project.
omd-codex-image
Channel-aware image materializer. Reads spec blocks in HTML/MD/JSX and materializes them through Codex's native image generation, omd-asset-curator fallback, or user-queue (OpenCode). One spec format, three downstream paths.
project-structure
Airbroke uses the Next.js App Router. Most feature code lives under app, components, lib, prisma, and tests.
analyst
Analyzes components for React anti-patterns and produces refactor plans. Use when starting a new refactor subtask.