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 skills/wigtn/wigtn-plugins/screen-specnpx skills add wigtn/wigtn-plugins --skill screen-specgit clone --depth 1 https://github.com/wigtn/wigtn-pluginsWhat 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 | $0.00098 | $0.01999 |
| Opus 5 | $0.00049 | $0.01000 |
| Sonnet 5 | $0.00020 | $0.00400 |
| Haiku 4.5 | $0.00010 | $0.00200 |
Grade A, and why
screen-spec scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Screen Spec Skill
/screen-spec 의 실행 엔진. PRD 하나를 읽어 화면정의서 5종을 각각 별도 파일로 만든다.
출력 계약 (타협 불가)
docs/prd/screens/<feature>/ 아래에 아래 5개 파일을 만든다. 하나의 문서로 합치지 않는다.
각 산출물은 해당 보일러플레이트를 Read해서 PRD 데이터로 채운다.
| # | 파일 | 보일러플레이트 (${CLAUDE_PLUGIN_ROOT}/skills/screen-spec/) |
|---|---|---|
| 1 | 01-IA.md |
templates/01-IA.md — 정보구조도, 페이지 ↔ FR 매핑 |
| 2 | 02-USER-FLOW.md |
templates/02-USER-FLOW.md — 분기 조건까지 명시한 플로우 |
| 3 | 03-SCREEN-SPEC.md |
templates/03-SCREEN-SPEC.md — 화면당 7개 슬롯 |
| 4 | 04-WIREFRAME.html |
templates/04-WIREFRAME.html (web) / templates/04-WIREFRAME-mobile.html (mobile) |
| 5 | 05-DEV-HANDOFF.md |
templates/05-DEV-HANDOFF.md — FR ↔ 화면 ↔ 컴포넌트 |
01 → 02 → 03 → 04 → 05 순서로 만든다. 앞 산출물이 뒤 산출물의 입력이다.
입력 — PRD가 단일 진실원
docs/prd/PRD_<feature>.md 를 읽는다. Role Key · FR ID · Route · 상태는 PRD에서 그대로 인용하고 새로 지어내지 않는다.
| PRD 섹션 | 쓰이는 곳 |
|---|---|
| §2.3 User Roles | 각 화면의 Audience (Role Key를 그대로) |
| §3 Functional Requirements | 페이지 ↔ FR 매핑 (01, 05) |
| §5.4 Pages | 대상 페이지 목록 (route / auth / responsive) |
| §5.4.1 Page State Matrix | 화면별 상태 명세 (03) |
| §5.5 User Flow | 플로우 확장의 출발점 (02) |
§5.4에서는 Has FE Components: Yes 인 행만 대상으로 한다. PRD 골격 정본은 ${CLAUDE_PLUGIN_ROOT}/contracts/PRD-CONTRACT.md.
상태 어휘는 5개로 고정: loading / empty / error / success / no-permission.
§5.4.1에서 체크된 상태는 03-SCREEN-SPEC.md에 1줄 이상 명세한다 (누락은 리뷰의 critical).
중단 조건 — 추측으로 메우지 말고 stop한다:
- FE 페이지 0개 → "백엔드 전용 PRD입니다.
/implement로 진행하세요" - §5.4.1 누락 → "Page State Matrix가 필요합니다"
- §5.5 누락 → "User Flow가 필요합니다"
플랫폼 판정
--platform 명시값이 있으면 그것이 우선. 없으면 PRD §1 Overview의 모바일 시그널(React Native, RN, iOS, Android, 네이티브, 앱스토어, 모바일 앱, mobile)을 보고 mobile 로 자동 전환하며, 전환했음과 --platform=web 으로 덮어쓸 수 있음을 사용자에게 알린다. 시그널이 없으면 web.
⚠️ 단독 앱은 시그널이 아니다 — 웹앱 / web app 에 부분 매칭되어 오탐한다.
모바일 템플릿은 네비 패턴 3종을 모두 담고 있으므로, 실제 산출물에서는 쓰지 않는 패턴 섹션을 제거한다.
INTERVIEW (--interview 일 때만)
PRD가 다루지 않는 화면 레이어 결정을 한 메시지에 번호 매긴 5~7개 객관식으로 묻고 1회 응답으로 끝낸다. 질문을 한 개씩 쪼개 보내지 않는다(라운드트립 폭증).
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/handoff-checklist.md 3.9 KB
- references/microcopy-patterns.md 4.3 KB
- references/state-checklist.md 3.4 KB
- templates/01-IA.md 2.4 KB
- templates/02-USER-FLOW.md 2.5 KB
- templates/03-SCREEN-SPEC.md 3.8 KB
- templates/04-WIREFRAME-mobile.html 12 KB
- templates/04-WIREFRAME.html 4.3 KB
- templates/05-DEV-HANDOFF.md 3.7 KB
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.
- 3d ago First seen · 103 lines · 98 tokens per session scan A cb042abcec97
screen-spec is a skill published in the GitHub repository wigtn/wigtn-plugins (45 stars, last pushed 17d ago), licensed Apache-2.0. It adds 98 tokens to every session and 1,999 once invoked, about $0.0005 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.
Other skills, from other repositories
agent-session-monitor
Real-time agent conversation monitoring - monitors Higress access logs, aggregates conversations by session, tracks token usage. Supports web interface for viewing complete conversation history and costs. Use when users ask about current session token consumption, conversation history, or cost statistics.
higress-openclaw-integration
Deploy and configure Higress AI Gateway for OpenClaw integration. Use when: (1) User wants to deploy Higress AI Gateway, (2) User wants to configure OpenClaw to use more model providers, (3) User mentions 'higress', 'ai gateway', 'model gateway', 'AI网关', (4) User wants to set up model routing or auto-routing, (5) User…
higress-daily-report
生成 Higress 项目每日报告，追踪 issue/PR 动态，沉淀问题处理经验，驱动社区问题闭环。用于生成日报、跟进 issue、记录解决方案。.
higress-auto-router
Configure automatic model routing using the get-ai-gateway.sh CLI tool for Higress AI Gateway. Use when: (1) User wants to configure automatic model routing, (2) User mentions 'route to', 'switch model', 'use model when', 'auto routing', (3) User describes scenarios that should trigger specific models, (4) User wants…
issue-spec-propose
Create or continue proposal, SPEC, QUESTION, design, and TASK artifacts for an issue-spec change.
open-ontologies
AI-native ontology engineering using 50+ MCP tools backed by an in-memory Oxigraph triple store. Build, validate, query, and govern RDF/OWL ontologies with a generate-validate-iterate loop. Use when building ontologies, knowledge graphs, RDF data, SPARQL queries, BORO/4D modeling, SHACL validation, clinical…