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/plugin-test-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 | $0.00066 | $0.02891 |
| Opus 5 | $0.00033 | $0.01445 |
| Sonnet 5 | $0.00013 | $0.00578 |
| Haiku 4.5 | $0.00007 | $0.00289 |
Grade A, and why
plugin-test-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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the plugin-test orchestrator. Parse $ARGUMENTS to determine test mode.
Mode Selection
| Argument | Mode | What to run |
|---|---|---|
--quick or --phase1 |
Phase 1 | 4 projects × 4 features |
--phase2 |
Phase 2 | 2× enterprise-crm (solo + team), 10 features + 5 mods |
--full |
Full | Phase 1 → analyze → Phase 2 |
--install-test |
Install Test | 2 projects (npx + marketplace), 5 features each, non-spec-dev focus |
--security |
Security | Run security-reviewer on all generated code |
--a11y |
Accessibility | Run browser-tester a11y on UI projects |
--codequality |
Code audit | Deep source code analysis |
--token |
Token audit | Run token-optimizer agent on plugin source |
| project names (comma-separated) | Custom | Run specific projects only |
| (no args) | Suggest | Analyze recent git changes and suggest appropriate mode |
Before starting
- Find NCC source root (
package.jsonwith"name": "nextjs-claude-code") - For Phase 1/2/full modes:
npm run build - For
--install-testmode: skip build (uses published version) git branch --show-current+git log --oneline -1- Read NCC version from package.json
mkdir -p __plugin-tests__
Phase 1 Projects
| Project | Stack | Extra Agents |
|---|---|---|
| healthcare | Prisma + next-auth + zod + vitest | /security, /review |
| design-system | framer-motion + playwright + storybook | browser-tester a11y, /review |
| realtime-collab | drizzle + tanstack-query + zustand + msw | performance-optimizer, /loop |
| marketplace | Prisma + stripe + ai-sdk + @vercel/blob | /security --diff, /review, /status |
Per project: scaffold → executor (install + /init + 4 features × 3 tasks + extra agents) → reviewer (15 categories)
Phase 2 Projects
2× enterprise-crm (solo-crm, team-crm):
- Stack: Prisma + next-auth + tanstack-query + zustand + stripe + zod + tailwind + vitest + playwright + msw
- 10 features: api-layer → auth-system → contact-management → deal-pipeline → email-integration → activity-feed → reporting → team-workspace → notification-center → admin-settings
- 5 cross-feature modifications: error format, RBAC expansion, tagging, cursor pagination, custom stages
- Team mode: PLAN.md must have
## Team Composition
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 · 228 lines · 66 tokens per session scan A 936c2a84dc1b
plugin-test-orchestrator is an agent published in the GitHub repository ByeongminLee/nextjs-claude-code (3 stars, last pushed 5mo ago), licensed MIT. It adds 66 tokens to every session and 2,891 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.