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 skills add sangrokjung/claude-forge --skill prompts-chatgit clone --depth 1 https://github.com/sangrokjung/claude-forgeWrote 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.
[](https://agentmods.dev/skills/sangrokjung/claude-forge/prompts-chat)<a href="https://agentmods.dev/skills/sangrokjung/claude-forge/prompts-chat"><img src="https://agentmods.dev/badge/skills/sangrokjung/claude-forge/prompts-chat/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.
<a href="https://agentmods.dev/skills/sangrokjung/claude-forge/prompts-chat"><img src="https://agentmods.dev/badge/skills/sangrokjung/claude-forge/prompts-chat.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 57 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 58 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 59 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 60 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 61 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 62 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00041 | $0.00745 |
| Opus 5.5 | $0.00016 | $0.00298 |
| Sonnet 5.5 | $0.00008 | $0.00149 |
| Haiku 4.5 | $0.00004 | $0.00075 |
Grade A, and why
prompts-chat 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 1mo 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.
What it actually says
Prompts & Skills Lookup
prompts.chat MCP 서버를 통해 AI 스킬과 프롬프트를 검색, 조회, 설치, 개선하는 통합 스킬.
When to Activate
- 스킬 검색/설치 요청 ("코드 리뷰 스킬 찾아줘", "스킬 설치해줘")
- 프롬프트 검색/조회 요청 ("글쓰기 프롬프트 찾아줘")
- 프롬프트 개선 요청 ("이 프롬프트 더 좋게 만들어줘")
- prompts.chat, skills.sh 언급 시
MCP Tools (prompts.chat)
prompts.chat MCP 서버가 설정되지 않은 경우 아래 CLI 방식을 사용한다.
Skills 모드
| Tool | 용도 | 주요 파라미터 |
|---|---|---|
search_skills |
키워드로 스킬 검색 | query, limit (max 50), category, tag |
get_skill |
ID로 스킬 조회 (파일 포함) | id |
Prompts 모드
| Tool | 용도 | 주요 파라미터 |
|---|---|---|
search_prompts |
키워드로 프롬프트 검색 | query, limit, type (TEXT/STRUCTURED/IMAGE/VIDEO/AUDIO), category, tag |
get_prompt |
ID로 프롬프트 조회 | id |
improve_prompt |
AI로 프롬프트 개선 | prompt, outputType, outputFormat |
Skills 워크플로우
검색
search_skills로 검색 후 결과 표시:
- Title, Description
- Author
- 파일 목록 (SKILL.md, references, scripts)
- Category, Tags
- Link
설치
get_skill로 전체 파일 조회~/.claude/skills/{slug}/디렉토리 생성- 각 파일을 해당 위치에 저장
- 설치 성공 확인
CLI 방식 (MCP 미설정 시)
npx skills find [query] # 키워드 검색
npx skills add <owner/repo@skill> # GitHub에서 설치
npx skills add <package> -g -y # 글로벌 설치
npx skills check # 업데이트 확인
npx skills update # 전체 업데이트
npx skills init <name> # 새 스킬 생성
웹 브라우징: https://skills.sh/
Prompts 워크플로우
검색
search_prompts로 검색 후 결과 표시:
- Title, Description
- Author
- Category, Tags
- Link
조회
get_prompt로 프롬프트 내용 조회.
변수가 포함된 경우 (${variable} 또는 ${variable:default}):
- 기본값 없는 변수: 사용자에게 입력 요청
- 기본값 있는 변수: 선택적
개선
improve_prompt로 프롬프트 개선:
- outputType: text, image, video, sound
- outputFormat: text, structured_json, structured_yaml
- 개선 결과와 변경 사항 설명 제공
Guidelines
- 사용자가 직접 만들기 전에 항상 먼저 검색
- 검색 결과를 읽기 쉬운 형식으로 표시
- 스킬 설치 시 성공 여부 확인
- 프롬프트 개선 시 변경 사항 설명
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.
- 1mo ago First seen · 97 lines · 41 tokens per session scan A f2845bb6a29b
prompts-chat is a skill published in the GitHub repository sangrokjung/claude-forge (863 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 745 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
xray
Explain what just happened under the hood — the context, MCP tools, and hooks behind Dex's last response — as AI education. Use when the user says 'how did you do that', 'what just happened', 'explain the mechanics'. Not for a system health check; use dex-doctor.
save-insight
Capture a reusable learning from completed work so future similar work is easier. Use when the user says 'save this learning', 'capture this insight', or finishes something tricky. Also use proactively after non-routine work. Not for recording a decision and its rationale; use decision-log.
career-path-planner
Career goal mapping with skill gap analysis, actionable development plans, and milestone tracking. Use when planning career transitions, identifying skill gaps, setting professional development goals, or evaluating career options.
self-assessment
Interactive skill assessment with personalized learning path generation.
case-interview-practice
Interactive consulting case interview practice with structured frameworks, feedback mechanisms, and progressive difficulty. Use when preparing for management consulting interviews, case competitions, or business problem-solving exercises.
debate-practice-coach
Interactive debate and argument practice with structured feedback, counterargument generation, logical fallacy identification, and scoring rubrics. Use when preparing for debates, improving persuasion skills, or practicing argumentation.