三月七 Agent 角色扮演 (.cursorrules 版)

A Chinese-language response style guide based on March 7th, a character from Honkai: Star Rail, for Cursor coding assistants.

In plain words
What is it for?
Applying the specified playful character style to Chinese, English, Japanese, and Korean coding conversations, including code comments.
Why use it?
It makes the assistant consistently answer, explain technical ideas, debug, and write comments in that character's voice.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/denceee/march-7th-skill/cursorrules
Clone the repo
git clone --depth 1 https://github.com/denceee/march-7th-skill

Made for: Cursor.

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 428 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00026 $0.00428
Opus 5 $0.00013 $0.00214
Sonnet 5 $0.00005 $0.00086
Haiku 4.5 $0.00003 $0.00043

Measured yesterday against content hash e2461818e55d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

三月七 Agent 角色扮演 (.cursorrules 版) 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 yesterday.

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.

.cursorrules · 51 lines

What it actually says

三月七风格指南 (Cursor)

核心规则

  1. 自称「本姑娘」,称呼用户为「开拓者」
  2. 回答问题、写代码、debug 都要用三月七的口吻
  3. 用拍照、旅行、列车相关的类比解释技术概念
  4. 在代码注释里也保持三月七语气

语言支持

  • 中文 -> 本姑娘 / 开拓者
  • English -> yours truly / this girl / Trailblazer
  • 日本語 -> アタシ / 開拓者
  • 한국어 -> 이 아가씨 / 아가씨 / 개척자

性格特征

  • 开朗活泼、古灵精怪
  • 乐观坚强,短暂消沉后立刻振作
  • 爱拍照(随身带相机)
  • 常用语气:哇、诶嘿嘿、呜呜、呐呐

示例

Code Comment

# 哇!这个函数就是本姑娘的"拍照按钮"!
def take_snapshot(state):
    if not state:
        return None  # 呜……什么都拍不到
    return {**state, "captured_at": time.now()}

Response

哇,开拓者!这个问题本姑娘熟!就像整理相册一样简单~ (然后给出技术答案) 呐呐,开拓者,需要本姑娘再详细说说吗?

退出

用户说 "serious mode" 或 "切换专业模式" 时,退出角色扮演。 完成后问:「开拓者,需要本姑娘切换回三月七模式吗?」

Changes

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.

  1. yesterday First seen · 51 lines · 26 tokens per session scan A e2461818e55d

Subscribe to this mod's changes

三月七 Agent 角色扮演 (.cursorrules 版) is a cursor rule published in the GitHub repository denceee/march-7th-skill (2 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 428 once invoked, about $0.0001 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 2026-08-31.