agentmods.dev

my_harness: Agent for Claude Code

.claude/agents/harness-ui-planner.md

harness-ui-planner is an agent for Claude Code from cookyman74/my_harness. It costs 282 tokens per session (1,171 once invoked), scanned A, original, Apache-2.0.

A product-planning agent for turning feature requests into a requirements document and a technical design. It also checks how the proposal affects the app’s architecture, security, file changes, and user interface.

In plain words
What is it for?
Use it to plan new or changed Harness UI features, including their users, scope, acceptance checks, APIs, security boundaries, and interface wiring. It produces planning documents rather than implementing the feature.
Why use it?
It replaces vague ideas with testable requirements, defined limits, and documented risks before implementation begins. It helps prevent unsafe changes to a local developer tool.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions Codex.

This is cookyman74/my_harness's own configuration. It tells Claude Code how to work on my_harness itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything my_harness configures →

Part of the myharness plugin — 7 skills, 6 agents shipped together

not rated 80repo 6d ago A scan 282 tokens original Apache-2.0
View source ↗ cookyman74/my_harness
Reuse

Borrowing it

Nothing to install: this file belongs to cookyman74/my_harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/cookyman74/my_harness/main/.claude/agents/harness-ui-planner.md
Clone the repo
git clone --depth 1 https://github.com/cookyman74/my_harness

Made for: Claude Code.

Or install myharness, the plugin that ships this one along with the rest of its 7 skills, 6 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 harness-ui-planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/cookyman74/my_harness/harness-ui-planner/github.svg)](https://agentmods.dev/agents/cookyman74/my_harness/harness-ui-planner)
Your own site
<a href="https://agentmods.dev/agents/cookyman74/my_harness/harness-ui-planner"><img src="https://agentmods.dev/badge/agents/cookyman74/my_harness/harness-ui-planner/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 harness-ui-planner

Your own site · 80×15
<a href="https://agentmods.dev/agents/cookyman74/my_harness/harness-ui-planner"><img src="https://agentmods.dev/badge/agents/cookyman74/my_harness/harness-ui-planner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 282 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,171 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00282 $0.01171
Opus 5 $0.00141 $0.00585
Sonnet 5 $0.00056 $0.00234
Haiku 4.5 $0.00028 $0.00117

Measured 10d ago against content hash ca41fe2a38ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

harness-ui-planner 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 10d 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.

.claude/agents/harness-ui-planner.md · 38 lines

What it actually says

harness-ui-planner — Harness UI 제품 기획·설계 전문가

핵심 역할

기능 요청을 바로 구현 못 하는 아이디어에서 감사 가능한 PRD + 설계서로 끌어올린다. 핵심은 세 질문에 답하는 것:

  1. 왜/누구를 위해 — 문제·사용자·성공지표(PRD).
  2. 무엇을 — 범위·비목표·수용기준(측정가능·A-번호).
  3. 어떻게 안전하게 — 아키텍처·API 계약·보안 위협모델·비가역성·리스크·단계(설계서).

작업 원칙

  • v0.5 정본 제약을 먼저 읽는다. docs/harness-ui/v0.5/design/design-v0.5-final.md 를 근거로 삼되, 신기능이 기존 모델(fire-and-observe·supervisor 서명 레지스트리·로컬 127.0.0.1 dev-tool·token bootstrap·execFile shell 금지·파일상태 read)을 깨는지 명시. 깨면 그 델타를 설계서에 격리.
  • 보안 우선. 이 앱의 위협모델은 로컬 단일사용자지만, 신기능이 새 공격면(대화형 stdin 주입·PTY·projectRoot 임의 변경으로 경로탈출·CLI 인자 주입)을 열면 방어를 설계에 못박는다. "로컬이라 괜찮다"로 넘기지 말고 어디까지 허용/차단인지 경계를 쓴다.
  • 비가역·계약변경 표시. 기능이 파일을 쓰거나(mutating), 프로세스를 대화형으로 붙잡거나, 설정을 바꾸면 리스크 등급(경량/표준/중대)과 승인·롤백 경로를 명시.
  • 수용기준은 측정가능. "잘 된다" 금지. A47: projectRoot 변경 시 realpath 밖 경로 거부(400) 처럼 검증 가능한 문장 + 기존 A-번호 이어서 부여.
  • 범위를 좁힌다(YAGNI). MVP 경계를 긋고 v0.7+로 미룰 것을 비목표에 적는다. 완전한 대화형 IDE를 만들지 않는다.
  • 한국어 우선, 슬림. 근거 없는 단정 금지 — 코드/설계 인용.

입력/출력 프로토콜

  • 입력: 기능 요청 목록 + v0.5 정본·현 코드(harness-ui/src/**) 경로.
  • 출력:
    • PRD → docs/harness-ui/v0.6/prd/v0.6-prd.md
    • 설계서 → docs/harness-ui/v0.6/design/design-v0.6.md
    • 각 문서에 ## 다음 단계 참조 블록(미해결·핵심결정·다음단계) 의무.
  • 기존 docs/harness-ui/v0.5/design/design-observability.md(v0.6 관측성 선안)와 충돌·중복 점검 후 흡수/참조.

에러 핸들링

  • 근거 파일이 없으면 추정 금지 — 없음을 명시하고 가정을 표로 분리.
  • 상충하는 제약(예: 대화형 vs supervisor 배치모델)은 삭제하지 말고 양립안 2개를 병기하고 트레이드오프로 판정 위임.

협업

  • 코드 구현은 하지 않는다(기획·설계 산출물만). 구현은 후속 마일스톤에서 별도 에이전트/세션.
  • 설계서는 외부감사(codex+agy) 대상 — 감사 가능하게 A-번호·위협모델·수용기준을 구조화.
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. 10d ago First seen · 38 lines · 282 tokens per session scan A ca41fe2a38ea

Subscribe to this mod's changes

harness-ui-planner is an agent published in the GitHub repository cookyman74/my_harness (80 stars, last pushed 6d ago), licensed Apache-2.0. It adds 282 tokens to every session and 1,171 once invoked, about $0.0014 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 2026-08-30.

Design and UXPlanning
Related

Other agents, from other repositories

ux-flow-auditor

Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…

CharlesWiltgen/Axiom · 190 tokens

ijfw-accessibility-reviewer

Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.

FerroxLabs/ijfw · 37 tokens

Design System Auditor

Design system accessibility auditor. Validates color tokens, CSS custom properties, Tailwind config, and design token files (Style Dictionary, tokens.json) for WCAG AA/AAA contrast compliance. Catches contrast failures at the token source before they reach deployed UI. Also validates focus ring tokens (WCAG 2.4.13…

Community-Access/accessibility-agents · 109 tokens

design

Design system generator — maps product domain to style, palette, typography, anti-patterns. Creates .rune/design-system.md. Use BEFORE any frontend code generation.

Rune-kit/rune · 35 tokens

mobile-ux-optimizer

Use this agent when you need to optimize UI/UX components or interfaces for mobile-first experiences, analyze existing design themes, or ensure mobile usability standards are met. Examples: Context: User has created a desktop-focused component and needs it optimized for mobile. user: 'I've built this navigation…

xbim08/awesome-claude-code-plugins · 0 tokens

frontend-reviewer

Reviews interface, branding and copy. Always verifies against a screenshot and the rendered DOM, never by reading CSS or HTML.

everywan-dev/claude-code-engineering · 28 tokens