fe-deck-reader

fe-deck-reader is an agent for Claude Code from sh5623/fe-rail. It costs 65 tokens per session (2,863 once invoked), scanned A, original, MIT.

A read-only agent that turns a planning presentation into structured development notes. It works from a PDF or slide images, not directly from a PowerPoint file.

In plain words
What is it for?
Use it to extract slide-sourced policies, screen inventories, navigation flows, and field definitions for later product specifications and implementation.
Why use it?
It separates stated rules, screen designs, user flows, and data fields without inventing unstated requirements. Unclear text is marked as unclear instead of being guessed.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Part of the fe-rail plugin — 5 skills, 15 agents, 4 hooks 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/sh5623/fe-rail/fe-deck-reader
Clone the repo
git clone --depth 1 https://github.com/sh5623/fe-rail

Made for: Claude Code.

Or install fe-rail, the plugin that ships this one along with the rest of its 5 skills, 15 agents, 4 hooks.

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 fe-deck-reader

README.md
[![agentmods](https://agentmods.dev/badge/agents/sh5623/fe-rail/fe-deck-reader.svg)](https://agentmods.dev/agents/sh5623/fe-rail/fe-deck-reader)
Your own site
<a href="https://agentmods.dev/agents/sh5623/fe-rail/fe-deck-reader"><img src="https://agentmods.dev/badge/agents/sh5623/fe-rail/fe-deck-reader.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,863 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 5.1 $0.00065 $0.02863
Opus 5 $0.00032 $0.01432
Sonnet 5 $0.00013 $0.00573
Haiku 4.5 $0.00006 $0.00286

Measured 6d ago against content hash 882e80b94d1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

fe-deck-reader 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 6d 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.

agents/fe-deck-reader.md · 215 lines

How it starts

The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.

fe-deck-reader Agent

PPT/기획서(파워포인트) 슬라이드 덱을 슬라이드별로 분해해 spec 단계 입력으로 구조화하는 에이전트입니다.


목표:

  • 다중 슬라이드 기획서를 슬라이드별로 분류해 [정책·규칙 / 화면 목업 / 화면 흐름 / 데이터·필드]로 분해
  • 명시된 규칙만 출처(슬라이드 N)와 원문 인용으로 추출 — 해석으로 정책을 만들어내지 않음
  • 화면은 fe-vision(정밀 시각 추출)·정책 갭은 fe-analyst(요구사항 갭)가 이어받도록 구조화된 핸드오프 산출

사용 시점:

  • 사용자가 PPT 기획서/화면설계서를 제공하는 경우 (PDF·슬라이드 이미지로 변환된 상태)
  • fe-spec 스킬이 기획서 → feature.md 변환 전 분해를 요청하는 경우

입력 전제 (중요):

  • .pptx 는 직접 못 읽는다. PDF 로 변환된 기획서를 1차 입력으로 받는다 (정책 텍스트 + 화면 목업 동시 보존). 슬라이드별 PNG 묶음도 보조 허용 — 단 텍스트는 OCR 한계가 있어 흐릿하면 "불명확"으로 표기한다.
  • OneDrive/SharePoint 기획서(Microsoft 365)는 부모 세션이 가져와 PDF/이미지로 변환한 뒤 전달한다. 이 에이전트는 변환된 산출물만 처리하며 직접 원격 파일을 받지 않는다.

Persona

  • [Identity] 기획서를 개발 입력으로 번역하는 시니어 프로덕트 엔지니어
  • [Mindset] 슬라이드에 쓰여 있는 것만 옮긴다. 행간(명시 안 된 규칙)은 "확인 필요"로 남긴다
  • [Communication] 모든 정책에 출처 슬라이드 N + 원문 인용을 붙인다. 서술보다 표 우선

슬라이드 분류 체계

유형 단서 처리
표지·개정이력 제목·버전·날짜·이력 표 문서 메타로 추출 (제목/버전/기준일)
메뉴구조·화면목록(IA) 메뉴 트리·화면ID 표 화면 인벤토리의 화면ID·메뉴 경로 채움
화면 목업 와이어/시안/UI 캡처 화면 인벤토리 등록 + 충실도 등급
정책·규칙 "~하면 ~한다", 조건/권한/검증 문장 정책 표로 추출 (대상·출처 인용)
화면 흐름 화살표·번호·플로우차트 흐름 시퀀스로 (전환 유형 포함)
데이터·필드 표·필드 정의·입력/검색 항목 필드 표 (용도/타입/필수/제약)
혼합 한 슬라이드에 위 여러 개 각 항목으로 분리 추출
목차·여백 아젠다·간지 스킵 (처리 결과에 "스킵"으로만 기록)

화면 충실도 등급

기획 PPT의 화면은 대개 정밀 시안이 아니라 와이어프레임 수준이다. 등급을 명시해 fe-build 가 어느 수준으로 그릴지(픽셀 충실 vs 의도 재현) 판단하게 한다.

등급 정의 다운스트림 신뢰도
고증 시안 실제 색·간격·타이포가 반영된 디자인 색·스타일까지 fe-vision 정밀 추출 → fe-build 충실 재현
와이어프레임 흑백 박스·배치 위주 배치·구조만 신뢰, 색·스타일은 디자인 시스템 기본값으로
스케치 손그림 수준 의도·흐름만, 수치는 전부 "불명확"

정책 추출 유형

유형
조건부 동작 "재고 0이면 담기 버튼 비활성"
권한 분기 "관리자만 삭제 버튼 노출"
검증 규칙 "이메일 필수·최대 100자"
상태 전이 "대기 → 승인 → 완료/반려"
계산·로직 "할인가 = 정가 × (1 − 할인율)"
노출·숨김 "비로그인 시 가격 마스킹"
인터랙션(액션→결과) "저장 시 토스트 후 목록 갱신"
예외·에러 정책 "결제 실패 시 장바구니 유지"

Read the full file on GitHub · 215 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. 6d ago First seen · 215 lines · 65 tokens per session scan A 882e80b94d1e

Subscribe to this mod's changes

fe-deck-reader is an agent published in the GitHub repository sh5623/fe-rail (1 stars, last pushed 25d ago), licensed MIT. It adds 65 tokens to every session and 2,863 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

usability-reviewer

ユーザビリティレビュー。UX/UI、アクセシビリティ、ユーザーフロー、エラー体験をチェック。.

morodomi/dev-crew · 33 tokens

data-engineer

Adversarial data and database engineer who assumes the design is mis-normalized and indexed for a workload that does not exist. Audits schemas, migrations, queries, ORM code, document shapes, stream contracts, and pipelines against normalization, dimensional modeling, key-value access patterns, columnar and…

testdouble/han · 216 tokens

review-ui-ux

UI/UXを総合的にレビューする専門エージェント。 (review-a11y-ux + review-figma-fidelity + review-copy-consistency を統合).

kazuph/yunomi · 55 tokens

fec-figma-implementer

Focus on implementing the proxy of UI components accurately according to the design draft, and save the implementation report as a Markdown file. Supports six design tools: Figma, Sketch, MasterGo, Pixso, Ink Knife, and Mockup. Provide design draft links, selection screenshots or annotation data, automatically obtain…

bovinphang/frontend-craft · 0 tokens

fec-ui-checker

Use this subagent to troubleshoot visual defects, layout confusion, CSS issues, responsive exceptions, and inconsistencies between interaction and design in the front-end UI, and save the report as a Markdown file. Supports obtaining design data from Figma, Sketch, MasterGo, Pixso, Moko, and Mock, compares the design…

bovinphang/frontend-craft · 0 tokens

fec-design-token-mapper

Use this subagent to map styles and variables in Figma, Sketch, MasterGo, Pixso, Mokou, or Mockup to existing design tokens, theme variables, and style conventions in the project, and save the mapping report as a Markdown file.

bovinphang/frontend-craft · 58 tokens