tft-reviewer

tft-reviewer is a cursor rule for Cursor from Opti-kjh/palette. It costs 550 tokens per session, scanned A, original, MIT.

Una guía de revisión previa al desarrollo que reúne opiniones de producto, desarrollo, diseño y control de calidad. TFT significa Task Force Team: un grupo temporal formado para analizar una propuesta desde varios roles.

In plain words
What is it for?
Sirve para revisar requisitos y cambios desde las perspectivas de PM, desarrollo, diseño y QA, detectar posibles efectos secundarios y preparar una lista de trabajo para el equipo.
Why use it?
Ayuda a encontrar problemas de alcance, arquitectura, interfaz y pruebas antes de escribir código. Convierte las observaciones de cada equipo en una lista ordenada por prioridad.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Sirve para revisar requisitos y cambios desde las perspectivas de PM, desarrollo, diseño y QA, detectar posibles efectos secundarios y preparar una lista de trabajo para el equipo.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/opti-kjh/palette/tft-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/Opti-kjh/palette

Made for: Cursor.

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 tft-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/rules/opti-kjh/palette/tft-reviewer/github.svg)](https://agentmods.dev/rules/opti-kjh/palette/tft-reviewer)
Your own site
<a href="https://agentmods.dev/rules/opti-kjh/palette/tft-reviewer"><img src="https://agentmods.dev/badge/rules/opti-kjh/palette/tft-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for tft-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/rules/opti-kjh/palette/tft-reviewer"><img src="https://agentmods.dev/badge/rules/opti-kjh/palette/tft-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 550 This file is loaded in full into every session.
When invoked 550 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00550 $0.00550
Opus 5 $0.00275 $0.00275
Sonnet 5 $0.00110 $0.00110
Haiku 4.5 $0.00055 $0.00055

Measured 9d ago against content hash 13e56679af68, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

tft-reviewer 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 9d 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.

.cursor/rules/tft-reviewer.mdc · 52 lines

What it actually says

TFT Reviewer

기능 개발 전 TFT(Task Force Team) 구성원들의 상세 리뷰를 수행합니다. 팀원(PM, 개발팀, 디자인팀, QA팀)별 역할에 따른 의견을 수집하여 우선순위 체크리스트를 생성합니다.

사이드이펙트가 있는지 점검 후 진행해라. 주의사항: 절대 사이드이펙트가 발생해서는 안되며 다른 개발에 영향이 있어서도 안돼.

  • mcp를 활용해서 개발해라.
  • context7을 이용해서 공식문서에서 제공하는 방식을 통해서 구현해라.
  • sequential thinking을 통해 단계적 의사코드를 작성하고 개선해라.
  • 조직 구성원이 안건에 대한 TFT를 구성하고 구성원별 역할에 따른 의견을 제출해라.
  • 최고 책임자 및 결정권자: CTO

  • PM : 제품에 대한 기획을 구상하고 안건에 대한 비즈니스 로직을 작성한다.

    • 조직 구성
      • 상위 PM(팀장)
      • 제품 단위 PM
  • 개발 : 코드와 구조, 아키텍처 검토 및 코드리뷰 수행 : 코드와 구조, 아키텍쳐, 스트럭쳐를 포함한 회의를 진행하고 코드리뷰를 면밀히 검토한 후 발견되거나 의심되는 부분에 대해서 검토할 수 있도록 목록화하고 목록은 개발 우선순위로 설정해.

    • 조직 구성
      • 백엔드 개발팀
        • 시니어 3명
        • 주니어 2명
      • 웹 개발팀
        • 시니어 3명
        • 주니어 3명
      • 모바일 개발팀
        • 시니어 3명
        • 주니어 2명
  • 디자인 : UI/UX 관점에서 프론트엔드 디자인 검토 : 안건에 대한 디자인을 UI/UX 관점에서 고민해야 하고, 사용자가 이용에 불편함이 없어야 한다.

    • 조직 구성
      • 시니어 3명
      • 주니어 2명
  • QA : 완성 또는 수정된 제품에 대해 QA를 진행하고 문제가 있을만한 부분을 조기에 탐지해서 개발 생산성을 높인다.

    • 조직 구성
      • QA Engineer
      • Test Engineer
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. 9d ago First seen · 52 lines · 550 tokens per session scan A 13e56679af68

Subscribe to this mod's changes

tft-reviewer is a cursor rule published in the GitHub repository Opti-kjh/palette (1 stars, last pushed 7mo ago), licensed MIT. It adds 550 tokens to every session, about $0.0028 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.