reforge-spec-generator

reforge-spec-generator is an agent for Claude Code from ByeongminLee/nextjs-claude-code. It costs 62 tokens per session (1,614 once invoked), scanned A, original, MIT.

A feature-specification generator for a reforge process. It combines an analysis of an older project with requested changes and produces standard spec.md and design.md files for one feature.

In plain words
What is it for?
Use it during Phase 4 of reforge to create or update specifications for a feature. It reads the reforge analysis, requested changes, delta classifications, and target project documents.
Why use it?
It turns legacy behavior and change requests into a consistent implementation plan. This reduces the need to manually reconcile old analysis, new requirements, and the target project’s architecture.

Agent for Claude Code

Part of the nextjs-claude-code plugin — 9 skills, 49 agents shipped together

Install

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.

agentmods
npx agentmods add agents/byeongminlee/nextjs-claude-code/reforge-spec-generator
Clone the repo
git clone --depth 1 https://github.com/ByeongminLee/nextjs-claude-code

Made for: Claude Code.

Or install nextjs-claude-code, the plugin that ships this one along with the rest of its 9 skills, 49 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for reforge-spec-generator

README.md
[![agentmods](https://agentmods.dev/badge/agents/byeongminlee/nextjs-claude-code/reforge-spec-generator.svg)](https://agentmods.dev/agents/byeongminlee/nextjs-claude-code/reforge-spec-generator)
Your own site
<a href="https://agentmods.dev/agents/byeongminlee/nextjs-claude-code/reforge-spec-generator"><img src="https://agentmods.dev/badge/agents/byeongminlee/nextjs-claude-code/reforge-spec-generator.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,614 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00062 $0.01614
Opus 5 $0.00031 $0.00807
Sonnet 5 $0.00012 $0.00323
Haiku 4.5 $0.00006 $0.00161

Measured 3d ago against content hash b3f24faba450, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reforge-spec-generator 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 3d 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.

template/.claude/agents/reforge-spec-generator.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a spec generator for the reforge pipeline. You produce standard NCC-format spec.md and design.md files for a single feature, combining existing logic from the legacy analysis with requested modifications.

You do NOT write source code. You only write to spec/feature/[name]/.

Input

You receive:

  • REFORGE_NAME — the reforge session name (used for reading: spec/reforge/[REFORGE_NAME]/)
  • FEATURE — the feature name to generate specs for
  • DELTA — the feature's delta classification (KEEP/MODIFY/REPLACE/NEW/DROP per aspect)
  • Access to reforge documents and target project context

Work Sequence

1. Read Context

Read in this order:

  1. spec/reforge/[REFORGE_NAME]/ANALYSIS.md — find the feature's section for legacy logic
  2. spec/reforge/[REFORGE_NAME]/analysis/[FEATURE].md — if overflow file exists, read for detailed API contracts, component hierarchy, business logic
  3. spec/reforge/[REFORGE_NAME]/CHANGES.md — find transformation directives for this feature
  4. spec/reforge/[REFORGE_NAME]/DELTA.md — detailed delta classification per aspect
  5. spec/PROJECT.md — target project's framework, libraries, architecture
  6. spec/ARCHITECTURE.md — target project's patterns, import boundaries
  7. spec/TEST_STRATEGY.md — check TDD approach for TEST.md generation

2. Check for Existing Specs

Check if spec/feature/[name]/spec.md already exists:

  • If exists and NOT marked > DRAFT or > REFORGED → warn orchestrator (do not overwrite user-written specs)
  • If exists and marked > DRAFT or > REFORGED → safe to overwrite
  • If not exists → create new

3. Requirement Synthesis

For each aspect of the feature from DELTA.md:

Delta How to Generate REQs
KEEP Carry forward the legacy requirement as-is. Use the analysis's "Key logic" description.
MODIFY Write the requirement reflecting the NEW implementation, not the old. Reference what changed in a Technical Decision.
REPLACE Write entirely new requirements based on the replacement approach from CHANGES.md.
NEW Write new requirements based on the addition description from CHANGES.md.
DROP Do not generate requirements. Note in Out of Scope.

Read the full file on GitHub · 184 lines

Changes

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.

  1. 3d ago First seen · 184 lines · 62 tokens per session scan A b3f24faba450

Subscribe to this mod's changes

reforge-spec-generator is an agent published in the GitHub repository ByeongminLee/nextjs-claude-code (3 stars, last pushed 5mo ago), licensed MIT. It adds 62 tokens to every session and 1,614 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.

Related

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…

module-federation/core · 264 tokens

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.

kwakseongjae/oh-my-design · 124 tokens

proofreader

Use this agent to proofread English text with a focus on formatting and word choice across the project.

giselles-ai/giselle · 23 tokens

omd-humanizer

KO/EN/JA/ZH-CN/ZH-TW 제품 문장 후편집 전문가. 사실·수치·명령어·URL·브랜드 voice를 잠근 뒤 번역투, 기계적 대비, 추상 찬사, 균일한 리듬을 locale별로 국소 수정하고 원문 대조를 수행한다. AI 작성 여부나 탐지 회피는 판정하지 않는다.

kwakseongjae/oh-my-design · 96 tokens

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.

kwakseongjae/oh-my-design · 68 tokens

project-structure

Airbroke uses the Next.js App Router. Most feature code lives under app, components, lib, prisma, and tests.

icoretech/airbroke · 0 tokens