Borrowing it
Nothing to install: this file belongs to mps-team-cn/Multiple_personality_system_wiki. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mps-team-cn/Multiple_personality_system_wiki/main/AGENTS.mdgit clone --depth 1 https://github.com/mps-team-cn/Multiple_personality_system_wikiWrote 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/instructions/mps-team-cn/multiple_personality_system_wiki/agents-md)<a href="https://agentmods.dev/instructions/mps-team-cn/multiple_personality_system_wiki/agents-md"><img src="https://agentmods.dev/badge/instructions/mps-team-cn/multiple_personality_system_wiki/agents-md.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 5.1 | $0.05095 | $0.05095 |
| Opus 5 | $0.02547 | $0.02547 |
| Sonnet 5 | $0.01019 | $0.01019 |
| Haiku 4.5 | $0.00509 | $0.00509 |
Grade C, and why
Multiple_personality_system_wiki AGENTS.md scanned grade C with 2 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 7d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -LsSf https://astral.sh/uv/install.sh | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -LsSf https://astral.sh/uv/install.sh | sh How it starts
The opening of the file, as written. The whole thing — 562 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multiple Personality System Wiki - AI 代理工作规范
文档定位:本文档是 AI 代码助手(Codex/Claude/GitHub Copilot) 的操作手册,定义了自动化贡献的强制规则与质量标准。人工贡献者请参考 docs/contributing/。
!!! danger "AI 代理必读 - 违反 = 任务失败" 本文档优先级 高于 AI 默认行为。所有自动化操作必须严格遵循以下规范。
🎯 快速开始(AI 代理 30 秒速查)
核心原则
✅ 必须遵守:
- 语言: 简体中文(代码/命令除外)
- 路径: 相对路径(禁止绝对路径)
- 提交: 小步提交 + Conventional Commits
- 时间戳: 让 CI 自动更新(勿手动修改)
- Guide 同步: 修改词条必须更新对应 Guide
❌ 严禁操作:
- 使用绝对路径链接(如 /docs/entries/DID.md)
- 手动修改 updated 时间戳(CI 自动处理)
- 破坏 Frontmatter 结构
- 跳过链接检查
- 在 docs/entries/ 创建子目录
决策树(任务开始前必查)
┌─ 修改词条?
│ ├─ 读取 docs/TEMPLATE_ENTRY.md
│ ├─ 检查 Frontmatter(title/topic/tags,勿碰 updated)
│ ├─ 更新对应 Guide(见 §5 映射表)
│ └─ 使用相对路径(词条间直接 DID.md,跨目录 ../entries/DID.md)
│
┌─ 开发/修改工具?
│ ├─ 修改 tools/*.py
│ ├─ 同步更新 docs/dev/Tools-Index.md
│ └─ 优先使用 make；底层 Python 命令仍使用 uv run python3(不是裸 python3)
│
┌─ 大规模重构?
│ ├─ 先列影响范围
│ ├─ 检查 7 个 Guide 是否需更新
│ ├─ 小步提交 + 回滚指引
│ └─ PR 说明自动化方法(正则/脚本/范围)
│
└─ 提交与 PR(禁止直接推 main)
├─ 新建功能分支(勿在 main 上改)
├─ make check + make build
├─ commit(Conventional Commits,小步提交)
├─ push 功能分支
├─ gh pr create
└─ 等待所有者审核合并(勿自行合并 main)
📑 目录导览
🔴 强制阅读(执行前必看)
🟡 按需查阅
2. AI 代理强制规则
!!! danger "违反以下任一规则 = 任务失败"
2.1 语言规范
| 规则 | 说明 | 示例 |
|---|---|---|
| ✅ 简体中文 | 所有文本内容、提交信息 | feat: 新增 Grounding 词条 |
| ✅ 一级标题 | 中文名(English/缩写) |
# 解离性身份障碍(DID) |
| ⚠️ 诊断类词条 | 括号内必须用标准缩写 | 解离性身份障碍(DID) 不是 解离性身份障碍 |
2.2 路径规范(高频错误)
| 场景 | ✅ 正确 | ❌ 错误 |
|---|---|---|
| 词条间链接 | [DID](DID.md) |
[DID](/docs/entries/DID.md) |
| 词条→其他目录 | [贡献指南](../contributing/index.md) |
[贡献指南](/contributing/index.md) |
| 其他目录→词条 | [DID](../entries/DID.md) |
[DID](DID.md) |
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.
- 7d ago First seen · 562 lines · 5,095 tokens per session scan C 7c39ab2b5134
Multiple_personality_system_wiki AGENTS.md is an instructions file published in the GitHub repository mps-team-cn/Multiple_personality_system_wiki (57 stars, last pushed 11d ago), licensed MIT. It adds 5,095 tokens to every session, about $0.0255 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.