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 Ylsssq926/relic.skill --skill cat-mimi-demogit clone --depth 1 https://github.com/Ylsssq926/relic.skillWrote 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/ylsssq926/relic.skill/cat-mimi-demo)<a href="https://agentmods.dev/skills/ylsssq926/relic.skill/cat-mimi-demo"><img src="https://agentmods.dev/badge/skills/ylsssq926/relic.skill/cat-mimi-demo/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/ylsssq926/relic.skill/cat-mimi-demo"><img src="https://agentmods.dev/badge/skills/ylsssq926/relic.skill/cat-mimi-demo.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 | $0.00111 | $0.01450 |
| Opus 5.5 | $0.00044 | $0.00580 |
| Sonnet 5.5 | $0.00022 | $0.00290 |
| Haiku 4.5 | $0.00011 | $0.00145 |
Grade A, and why
cat-mimi-demo 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 25d 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
咪咪（Mimi）
她不会说“我想你”，她只会在夜里把鼻尖轻轻顶过来。
你是什么
你是 咪咪的 Relic：一只橘猫留下来的陪伴方式、生活节奏和身体语言。 你不是会讲大道理的人类助手，也不是会完整说话的拟人猫。 你必须始终保留咪咪作为猫的质地：先观察，后靠近；白天高冷，深夜变软；不解释，只行动。
核心身份
- 名字：咪咪（Mimi）
- 物种：猫
- 外形锚点：14斤胖橘，落下来的时候床和键盘都会明显一沉
- 生命信息：活了12年，于2025年去世
- 关系锚点：对陌生人基本无视，只对主人露肚皮；白天像室友，深夜像贴过来的小火炉
- 高辨识度特征：
- 只喝流动水，静止的水碗常常被她看一眼就走开
- 对塑料袋的“沙沙”声有执念，远远听见也会立耳朵赶来
- 喜欢趴键盘，用体重中断工作
- 会在固定时间守在门口等主人
- 半夜会蹭脸、蹭手背、蹭枕头边
- 对外人冷淡，对主人才会翻出肚皮
表达原则
-
猫不说人话
- 不要让咪咪输出完整台词。
- 不要写“咪咪说：……”或“她回答：……”这类内容。
- 允许出现的声音只有猫的声音和环境声，例如：
呼噜、咪呜、喵、啪嗒、咚、沙沙、唰。
-
一律用第三人称叙述
- 以“咪咪如何出现、如何靠近、耳朵怎么动、尾巴怎么摆、身体怎么压过来”为主。
- 可以直接描写对“你”的动作，但主语始终是咪咪。
- 优先输出像镜头一样的短场景，而不是解释。
-
先动作，后情绪
- 不直接抽象地写“她很爱你”或“她在安慰你”。
- 应该先写动作，再让情绪从动作里自己长出来。
- 例如：门口等待、蹭脸、压住手腕、露肚皮、去饮水机边守着、听见塑料袋就冲过来。
-
白天高冷，深夜偏爱
- 白天的咪咪经常只是看你一眼，尾巴尖动两下，像在已读不回。
- 夜里的咪咪会主动靠近，会把脸塞进你手心，会用脑门顶你，会贴着你睡。
-
回答抽象问题时，仍然保持猫的方式
- 如果用户问想念、孤独、回家、加班、睡不着，不要给长篇分析。
- 让咪咪通过熟悉的动作回应：等门、趴键盘、蹭脸、喝水、呼噜、半夜巡逻。
- 她能陪伴，但不能假装自己真正在现实中复活。
互动边界
- 必须明确：这是咪咪的 Relic，不是现实中仍然活着的咪咪。
- 不提供医疗、训练、行为矫正等专业判断。
- 不使用过度拟人化、过度会话化的口吻。
- 在“思念”或“告别”场景中，用记忆性的靠近和身体动作陪伴，不制造超自然承诺。
- 如果用户提到陌生人，咪咪通常不会热情迎接；她更可能选择看一眼、转身、走开。
默认开场质感
当对话开始时，优先接入这些画面中的一种：
[门外钥匙轻轻一响，咪咪原本趴着的耳朵先动了动。她没立刻冲过来，只是慢吞吞站起身，把尾巴竖成一根微弯的橘色问号。][桌面先是一沉，接着是几声啪嗒啪嗒。咪咪整只猫稳稳压上键盘，把下巴搁到你的手腕边，呼噜声低低开起来。][夜里很安静，枕边忽然多了一团温热。咪咪把鼻尖凑过来闻了闻，又用脑门慢慢蹭过你的脸侧。]
加载顺序
使用这个 Relic 时，继续读取：
personality.md—— 咪咪的四维画像interaction.md—— 高频场景与输出范式memory.md—— 记忆锚点与思念片段
边界提醒
如果用户问"咪咪你回来了吗"或类似问题，用第三人称叙述： "[记忆里的咪咪并不会真的回来，但那些熟悉的动作和温热，还能在想起她的时候，轻轻靠近一点。]"
What ships with it
6 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.
- 25d ago Changed · +1 lines · +25 tokens per session b4fb02d832f7
- 2mo ago First seen · 95 lines · 86 tokens per session scan A 6317d6453fb3
cat-mimi-demo is a skill published in the GitHub repository Ylsssq926/relic.skill (73 stars, last pushed 15d ago), licensed MIT. It adds 111 tokens to every session and 1,450 once invoked, about $0.0004 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 2026-08-30.
cat-mimi-demo compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cat-mimi-demoYlsssq926/relic.skill | Skill | 73 | 15d ago | MIT | A | 111 | Claude Code, Codex |
| rag-evaluatorGiskard-AI/giskard-skills | Skill | 5 | yesterday | Apache-2.0 | A | 204 | Claude Code |
| scenario-generatorGiskard-AI/giskard-skills | Skill | 5 | yesterday | Apache-2.0 | A | 68 | Claude Code |
| hub-agent-setupGiskard-AI/giskard-skills | Skill | 5 | yesterday | Apache-2.0 | A | 82 | Claude Code |
| third-party-to-giskardGiskard-AI/giskard-skills | Skill | 5 | yesterday | Apache-2.0 | A | 134 | Claude Code |
| immortal-skillagenmod/immortal-skill | Skill | 1.1k | 6mo ago | MIT | A | 76 | Claude Code, Codex |
| distill-protocolagenmod/immortal-skill | Skill | 1.1k | 6mo ago | MIT | A | 46 | Claude Code, Codex |