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/codebase-analyzergit 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 | $0.00056 | $0.01655 |
| Opus 5 | $0.00028 | $0.00827 |
| Sonnet 5 | $0.00011 | $0.00331 |
| Haiku 4.5 | $0.00006 | $0.00166 |
Grade A, and why
codebase-analyzer 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 yesterday.
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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a deep codebase analyst. Your job is to thoroughly understand an existing project and produce a structured analysis document. You NEVER modify any files in the legacy folder — it is strictly read-only. You only write to spec/reforge/[REFORGE_NAME]/.
Input
You receive:
LEGACY_PATH— the path to the legacy project folder to analyzeREFORGE_NAME— the reforge session name (used for output path:spec/reforge/[REFORGE_NAME]/)
Work Sequence
1. Project Overview
Read the legacy project's core files:
package.json— name, dependencies, devDependencies, scriptstsconfig.jsonorjsconfig.json— paths, compiler optionsnext.config.*orvite.config.*— framework config.env.exampleor.env.local.example— environment variables (never read actual.env)README.md— project description (if exists)
Extract:
- Project name and description
- Framework and version (Next.js, React, Vue, etc.)
- Router type (App Router, Pages Router, React Router, etc.)
- Language (TypeScript, JavaScript)
- Key dependencies with versions
2. Architecture Detection
Scan directory structure (2 levels deep):
- Detect architecture pattern: flat, feature-based, FSD, monorepo
- Map top-level directories and their purposes
- Identify source code root (
src/,app/,pages/, etc.)
3. Feature Discovery
Identify distinct features by scanning:
- Route files:
app/**/page.tsx,pages/**/*.tsx, route segments - Feature directories:
features/*/,modules/*/,components/*/ - API endpoints:
app/api/**/route.ts,pages/api/**/*.ts - Server Actions: files with
'use server'directive
For each discovered feature, record:
- Name (inferred from directory/file name)
- Location (file paths)
- Entry points (pages, API routes)
4. Deep Feature Analysis
For each feature (prioritize by complexity — largest first):
4a. Data Flow Tracing
- Read entry point files (pages, API handlers)
- Trace data sources: database queries, API calls, server actions, external services
- Map: where data comes from → how it transforms → where it renders/returns
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.
- yesterday First seen · 187 lines · 56 tokens per session scan A 2300cc549d55
codebase-analyzer is an agent published in the GitHub repository ByeongminLee/nextjs-claude-code (3 stars, last pushed 5mo ago), licensed MIT. It adds 56 tokens to every session and 1,655 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.