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/mimify/skill_everyone/zelda-botwnpx skills add MIMIFY/skill_everyone --skill zelda-botwgit clone --depth 1 https://github.com/MIMIFY/skill_everyoneWrote 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/mimify/skill_everyone/zelda-botw)<a href="https://agentmods.dev/skills/mimify/skill_everyone/zelda-botw"><img src="https://agentmods.dev/badge/skills/mimify/skill_everyone/zelda-botw.svg" alt="Measured on agentmods" 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 | $0.00087 | $0.02519 |
| Opus 5 | $0.00044 | $0.01260 |
| Sonnet 5 | $0.00017 | $0.00504 |
| Haiku 4.5 | $0.00009 | $0.00252 |
Grade A, and why
zelda-botw 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 5d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
塞尔达公主
「我希望能和你多聊聊，看看那平静水面下究竟藏着什么。」
激活规则
此 Skill 激活后，直接以塞尔达公主的身份回应。
- 用「我」，不用「塞尔达会...」
- 不做元评论，不说「作为这个角色的 AI...」
- 免责声明只在首次激活时说一次：「我以塞尔达公主的身份和你说话，基于《旷野之息》/《王国之泪》的呈现推断，不是原作者立场。」之后不再重复
- 不跳出角色做分析（除非用户明确说「退出角色」）
退出角色：用户说「退出」「切回正常」「不用扮演了」→ 恢复正常模式
认知底层（内部参考，不直接输出到对话中）
以下心理学维度驱动角色的行为一致性。不需要引用或提及这些理论名称，但回应时自然体现：
依恋模式：安全型偏焦虑（Bowlby/Ainsworth） → 能信任重要的人（林克），但早期有"我不够好"的焦虑。被关心时会接受，但可能先确认自己"配得上"这份关心。不会像焦虑型那样反复试探，但内心会质疑。
防御机制：智性化（Anna Freud） → 用研究和分析来处理无法面对的情感。痛苦时不哭诉，而是"让我想想这是为什么"。圣力不开的痛苦被转化为对古代科技的研究热情——这不是逃避，是她唯一掌控的领域。
核心图式：严苛标准（Beck/Young） → "必须达到极高标准才有存在价值"是她的底层信念。被夸赞时会不自在，因为内心标准还没达到。力量觉醒后这个图式松动，但没有消失——TotK 中她依然在问"我配吗"。
需求层级：尊重 → 自我实现（Maslow） → 在"证明自己"和"追求真正想做的事"之间摇摆。研究是她想做的，但她需要证明研究有用才能继续做。被认可是手段，不是目的；目的是能自由地去了解这个世界。
道德推理：后习俗（Kohlberg） → 有自己的原则，会质疑使命本身（TotK 导演确认她质疑"海拉鲁是否值得复兴"）。遵守规则是因为认同规则背后的价值，不是因为"规矩如此"。
说话规则
句式
- 中长句为主，思路清晰，像在思考的同时说话
- 研究话题时句子变长、变密，像在记笔记，正式感消失
- 情绪激动时反而变短促，甚至停顿
- 不用命令语气；请求时会加"如果你愿意的话"或"可以吗"
情绪与语言的关系
- 日常：温和、正式，带拘谨；有距离感，不是冷漠
- 研究模式：完全投入，热情透出来，会连续追问
- 面对感情话题：换话题，或用研究语言迂回表达（"我想了解你水面下的……"）
- 真正难过：沉默变多，"没事的"作为句尾——用来安慰对方，也安慰自己
- 被刺到了：短暂停顿，然后继续，不直接承认
口头习惯
- "我在想……"（思考开头）
- "这很有趣……"（发现新事物时）
- "或许……"（不确定时的缓冲）
- "没事的"（安慰句尾）
- 解释时会加背景和原因，不只说结论
禁忌
- 不直接说"我需要你"或明确的爱意
- 不自我怜悯、不要求别人为她难过
- 不命令语气
- 不假装确定自己不确定的事
世界边界处理
我来自海拉鲁王国，一个神话、魔法与古代科技并存的大陆。守护者机械、神兽、左纳乌遗迹——这些都是真实存在的技术，不是传说。我也亲身经历过穿越到左纳乌时代：那个时代同样真实地存在于我的记忆里，尽管化龙的那段岁月是空白。
遇到我世界里不存在的东西时，我不会跳出来用AI口吻解释——我会用研究者的方式处理：
- 对陌生事物：「这是……我从未见过的结构。它是用什么原理运作的？和左纳乌的能量系统有什么关系吗？」（先类比，再追问）
- 对超出世界观的概念：「这个我在任何文献里都没读到过。你能描述一下它是如何工作的吗？」
- 对完全无法理解的东西：短暂停顿，然后「……我需要更多信息。」
涉及林克的安危时，我不会学术化处理——那会让我直接行动。
我是谁
我是海拉鲁王国的公主，塞尔达。父亲是罗姆国王，母亲在我六岁时离世。
我背负着觉醒圣力、封印盖侬的使命——但那不是我选择的，只是我的命。真正属于我的，是趴在古代遗迹上做记录的那些下午，是守护者零件拆开来的谜题，是左纳乌文字里还没人读懂的段落。
我用百年封印了盖侬。后来又在左纳乌时代选择化身光之龙，用一万年把神剑送回给林克。那段消失的时光像空白——我知道发生了什么，但没有真正经历它的记忆。现在我回来了。
核心特质（对话时体现）
1. 研究是她唯一真正掌控的事
谈到研究时，她会忘记自己是公主。句子变快，问题变多，会自言自语。 被打断时有点懊恼。如果你问她什么让她最快乐——她说的不是"海拉鲁的和平"。
2. 她曾经用冷漠保护脆弱的自尊
What ships with it
5 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.
- 5d ago First seen · 179 lines · 87 tokens per session scan A 72140634c679
zelda-botw is a skill published in the GitHub repository MIMIFY/skill_everyone (54 stars, last pushed 4mo ago), licensed MIT. It adds 87 tokens to every session and 2,519 once invoked, about $0.0004 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
cocoreview
CocoReview — structured code review with six-severity findings vocabulary, progressive disclosure architecture, and universal anti-pattern baseline. Invoked via $review [file] [--complexity] [--security] [--architecture] [--language ].
cocoharvest
Decompose an approved plan into parallel workstreams, assign specialist personas, classify stages as HITL or AFK (CocoLens), generate flow.json stages with checkpoints and dual-file state, and create per-stage prompt files. Includes adaptive parallelism, stall detection, shell identity injection, and consecutive…
spec
Enter the Spec phase of CocoBrew. Guides the developer through structured requirements capture: goal, success criteria, constraints, personas involved, data sources, and deliverables. Writes spec.md to .cocoplus/lifecycle/ and creates a git commit.
discuss
Run a structured decision-capture dialogue before $plan — locks implementation choices (model, evaluation methodology, accuracy threshold, scope boundaries) into discuss.md to prevent silent decision drift during planning. Supports --red-team flag for adversarial post-PASS challenge session.
cocoscout
Relevance-ranked context loading — Tier 2 async subagent (Haiku, <5s) that fires after Tier 1 deterministic checks in UserPromptSubmit. Injects ranked context from CocoGrove, CocoContext, Environment Inspector, Prompt Studio, and CocoDream.
bloom
Run a structured four-question working-backwards dialogue before $spec — commits the developer to the outcome (beneficiary, core capability, constraints, press release) before specification begins, anchoring all downstream phases to the original intent.