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 sonature-lab/timsquad --skill tsq-promptgit clone --depth 1 https://github.com/sonature-lab/timsquadWrote 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/sonature-lab/timsquad/tsq-prompt)<a href="https://agentmods.dev/skills/sonature-lab/timsquad/tsq-prompt"><img src="https://agentmods.dev/badge/skills/sonature-lab/timsquad/tsq-prompt/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/sonature-lab/timsquad/tsq-prompt"><img src="https://agentmods.dev/badge/skills/sonature-lab/timsquad/tsq-prompt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00099 | $0.00698 |
| Opus 5 | $0.00049 | $0.00349 |
| Sonnet 5 | $0.00020 | $0.00140 |
| Haiku 4.5 | $0.00010 | $0.00070 |
Grade A, and why
tsq-prompt 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.
What it actually says
Prompt Engineering
에이전트와 스킬 프롬프트의 품질을 체계적으로 개선하기 위한 가이드라인.
최적화 원칙
구조화
역할 → 페르소나 → 작업 전 필수 → 핵심 원칙 → 작업 프로세스 → 출력 형식 → 금지 사항 → 예시
명확성
| Bad | Good |
|---|---|
| "잘 작성해" | "3문장 이내로 요약해" |
| "좋은 코드" | "테스트 커버리지 80%" |
| 나열만 | "필수/권장/선택" 분류 |
모호한 표현은 측정 가능한 기준으로 바꾼다. 모델은 명확한 기준이 있을 때 더 일관된 결과를 낸다.
컨텍스트
프로젝트 정보, 참조 문서 경로, 제약 사항을 명시적으로 주입한다. 모델이 추측해야 하는 정보가 줄어들수록 정확도가 올라간다.
예시 포함
Good/Bad 예시를 함께 제공하여 기대 품질 수준을 명확화한다.
개선 매핑 프로세스
패턴에서 프롬프트 개선으로 이어지는 흐름:
- 실패/성공 패턴 식별 (회고 스킬에서)
- 대상 에이전트/스킬 .md 파일 특정
- 변경 전/후 diff 작성
- 기대 효과 및 검증 방법 명시
- 사용자 승인 후 적용
품질 체크리스트
| 항목 | 검증 내용 |
|---|---|
| 명확성 | 모호한 표현이 없는가? |
| 완전성 | 필요한 정보가 모두 있는가? |
| 구조화 | 논리적 순서로 구성되었는가? |
| 예시 | Good/Bad 예시가 있는가? |
| 제약 | 금지 사항이 명시되었는가? |
| 출력 | 기대 출력 형식이 정의되었는가? |
템플릿 형식 (예시)
아래는 프롬프트 템플릿의 구조 예시입니다:
---
name: {skill-name}
version: 1.0.0
agent: {target-agent}
task_type: {implementation|review|analysis}
---
# {Title}
## 컨텍스트 주입
{{CONTEXT}}
## 작업 정의
{{TASK_DESCRIPTION}}
## SSOT 참조
{{SSOT_REFERENCES}}
## 출력 요구사항
{{OUTPUT_REQUIREMENTS}}
## 검증 기준
{{VALIDATION_CRITERIA}}
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.
- 10d ago First seen · 87 lines · 99 tokens per session scan A 0a39fe938586
tsq-prompt is a skill published in the GitHub repository sonature-lab/timsquad (11 stars, last pushed 10d ago), licensed MIT. It adds 99 tokens to every session and 698 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
prompt-optimization
Use this skill when the user wants to optimize, modify, or improve the system prompt of an AI agent. This includes requests like 'optimize the prompt', 'make the AI more focused on X', 'change the system prompt', 'improve the agent behavior', or 'modify how the AI responds'.
prompt-optimizer
Analyze and improve LLM prompts for clarity, precision, and output quality. Use when a prompt produces inconsistent results, the model ignores instructions, outputs are too long/short, or quality is below expectations.
seedance-2.0-prompter
Expert prompt engineering for Seedance 2.0. Use when the user wants to generate a video with multimodal assets (images, videos, audio) and needs the best possible prompt.
seedance-prompt-zh
Chinese-language guidance for writing prompts for Seedance 2.0, an AI video generator that can use text, images, video, and audio.
seedance-prompt-en
Write effective prompts for Jimeng Seedance 2.0 multimodal AI video generation. Use when users want to create video prompts using text, images, videos, and audio inputs with the @ reference system. Covers camera movements, effects replication, video extension, editing, music beat-matching, e-commerce ads, short…
prompt-engineering
Use when advanced prompt engineering — chain-of-thought, few-shot, tree-of-thought, self-consistency, meta-prompting, system design, debugging, and optimization for production AI systems. Use when working with prompt engineering.