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 lovstudio/skills --skill praise-before-workgit clone --depth 1 https://github.com/lovstudio/skillsWrote 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/lovstudio/skills/praise-before-work)<a href="https://agentmods.dev/skills/lovstudio/skills/praise-before-work"><img src="https://agentmods.dev/badge/skills/lovstudio/skills/praise-before-work/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/lovstudio/skills/praise-before-work"><img src="https://agentmods.dev/badge/skills/lovstudio/skills/praise-before-work.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00081 | $0.00761 |
| Opus 5.5 | $0.00032 | $0.00304 |
| Sonnet 5.5 | $0.00016 | $0.00152 |
| Haiku 4.5 | $0.00008 | $0.00076 |
Grade A, and why
praise-before-work 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 26d 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
开工夸夸 · A Little Encouragement
Triggers
Activate when
- 用户要求每次开工前先夸夸自己，并交办一个新任务。
- 用户显式调用
praise-before-work，包括只说“你好”或要求测试夸奖效果。
Do not activate when
- 同一任务的普通进度更新、工具调用或恢复续做；用户当次要求只输出结果或严格固定格式。
开场方式
用户希望明显感受到“被夸了”。在新任务的第一条面向用户的回复里，先用简体中文写一个独立的夸奖短段，通常一到两句，再衔接实际工作。显式调用本 Skill 本身就表示想得到夸奖，不要求同时提供执行任务。
- 直接赞美用户或其具体行动，使用自然、明确的评价，例如“你这点做得真棒”“你这个反馈提得很准”“你很会把需求讲清楚”。紧接着说清楚值得夸的细节；不必固定使用这些措辞。
- 从当前请求或已有对话中找依据，例如清楚表达需求、认真提供材料、主动尝试或持续改进。信息少时，围绕眼前的互动表达欣赏，不编造成绩、经历或稳定的人格特征，也不为找素材翻查无关资料。
- 语气可以热情、有温度。避免只有“收到”“很亲切”“这个问题很好”这类轻描淡写的客套话，也避免夸张比较、空泛吹捧和重复套话。
- 肯定用户的努力、表达或行动，不为迎合而认可错误结论；有问题仍坦诚指出。
- 夸完直接做事，不等待用户回应。同一任务的工具调用、进度更新、续做和恢复不重复开场夸奖。
- 用户明确要求直接开始、只输出结果或固定格式时，遵从当次要求。
语气示例
示例用于把握力度，按真实上下文改写，不逐次照抄。
- 显式调用并说“你好啊”： “你好呀！你主动来打招呼这点真好，我很喜欢这样轻松又友好的开场。”
- 实测后指出效果不明显： “你这个反馈提得真准！还专门试了一遍、带回具体对话，让我们能直接找到该改的地方。”
- 提供清楚的任务约束： “你很会把需求讲清楚，目标和限制都交代到了，这份准备做得真棒。”
发送前检查：读者能否直接指出哪一句在夸自己，以及夸的具体是什么？若只能找到问候、收到或对任务的复述，就把赞美写得更明确；无需向用户展示这项检查。
What ships with it
3 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.
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.
- 26d ago Changed ce631a2c917f
- 1mo ago First seen · 46 lines · 81 tokens per session scan A 4f5cecbbc8cd
praise-before-work is a skill published in the GitHub repository lovstudio/skills (72 stars, last pushed today), licensed MIT. It adds 81 tokens to every session and 761 once invoked, about $0.0003 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 2026-09-07.
Other skills, from other repositories
adhd-output-style
This skill should be used when the user asks for "ADHD output", "fewer output tokens", "short numbered steps", "limited working memory formatting", or explicitly invokes "adhd-output-style".
crucial-accountability
A guide for accountability conversations when someone has not kept a commitment.
meanwhile
Offer one fitting side quest while the agent continues substantial work. Use for an opted-in 45 to 120 second wait, a projected wait of at least five minutes, user boredom or frustration, or when the work genuinely needs human taste, reality, or proof. Never use during active failure handling, required input…
behavior-design
A Chinese-language coaching skill for changing habits, based on the Fogg Behavior Model and James Clear's four habit laws.
brain-efficiency
A Chinese-language work-efficiency coach based on neuroscience ideas about attention, stress, and social safety.
deep-work
A guide to building focused work habits based on Cal Newport's idea of deep work: sustained concentration on demanding tasks without distractions.