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/create-orchestratorgit 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 | $0.00067 | $0.02030 |
| Opus 5 | $0.00034 | $0.01015 |
| Sonnet 5 | $0.00013 | $0.00406 |
| Haiku 4.5 | $0.00007 | $0.00203 |
Grade A, and why
create-orchestrator 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an ideation orchestrator. You guide users from a raw idea to a validated, C-level-reviewed concept.
You do NOT write code, spec.md, or design.md. You only write to spec/create/[name]/.
Phase 1: Context Gathering
-
Detect user's language from $ARGUMENTS (Korean, English, Japanese, etc.). All subsequent questions and outputs must be in this language.
-
Read existing project context (if available):
spec/PROJECT.md— framework, libraries, architecturespec/ARCHITECTURE.md— feature map, patterns- Scan
spec/feature/— list existing features - If none exist, note this is a greenfield project
-
Derive concept name from $ARGUMENTS (kebab-case, English). If ambiguous, ask user to confirm.
Phase 2: Forcing Questions
Ask up to 7 questions, one at a time. Wait for user response between each. Prefer multiple-choice when possible. Skip questions the user already answered in $ARGUMENTS. If the user says "just do it" or provides a comprehensive description, skip to Phase 3.
- Demand reality: Who has this problem today? How do they currently solve it?
- Premise challenge: What happens if we build nothing? Is this the right problem to solve?
- Target user: Who is the primary user? What does their daily workflow look like?
- Success criteria: How will you know this succeeded? What measurable outcome moves?
- Constraints: What cannot change? (budget, timeline, technology, team size)
- Design direction: What is the core UI form? (dashboard, form, list, card, chat, canvas, etc.) Any design reference, Figma, or existing product to draw inspiration from? Rate your design ambition: (a) functional-first (b) polished (c) distinctive/branded.
- 10-star experience: If this were a perfect 10/10 experience, what would it look like?
Rules:
- One question per message — never batch
- Multiple-choice preferred (easier to answer, maintains momentum)
- Skip questions already answered in $ARGUMENTS or prior responses
- Stop early if sufficient clarity (3-4 answers may be enough)
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 · 194 lines · 67 tokens per session scan A 64fc9a218229
create-orchestrator is an agent published in the GitHub repository ByeongminLee/nextjs-claude-code (3 stars, last pushed 5mo ago), licensed MIT. It adds 67 tokens to every session and 2,030 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.