Borrowing it
Nothing to install: this file belongs to luyangkk/trae-superpowers. 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/luyangkk/trae-superpowers/main/AGENTS.mdgit clone --depth 1 https://github.com/luyangkk/trae-superpowersWrote 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/luyangkk/trae-superpowers/agents-md)<a href="https://agentmods.dev/instructions/luyangkk/trae-superpowers/agents-md"><img src="https://agentmods.dev/badge/instructions/luyangkk/trae-superpowers/agents-md/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/instructions/luyangkk/trae-superpowers/agents-md"><img src="https://agentmods.dev/badge/instructions/luyangkk/trae-superpowers/agents-md.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 | $0.01757 | $0.01757 |
| Opus 5.5 | $0.00703 | $0.00703 |
| Sonnet 5.5 | $0.00351 | $0.00351 |
| Haiku 4.5 | $0.00176 | $0.00176 |
Grade C, and why
trae-superpowers 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 1mo 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.
- **脚本自包含**:脚本要能被 `curl -fsSL ... | bash` 直接执行,禁止 `source` 外部文件。 Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **脚本自包含**:脚本要能被 `curl -fsSL ... | bash` 直接执行,禁止 `source` 外部文件。 How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
本文件为在此仓库工作的 AI 编码代理提供指引。
项目概述
trae-superpowers 把上游 obra/superpowers 的 skills
装入 Trae IDE 的全局 skills 目录;若共享的 ~/.agents/skills 已有完整 Superpowers,
则直接复用且不接管。项目用 Trae 的 User Rules 替代上游原生的 SessionStart Hook,
使 skills 从第一条消息起即生效。
产物是三个自包含的 bash 脚本(install.sh / update.sh / uninstall.sh)加双语文档,没有构建产物、
没有运行时依赖。
常用命令
# 运行全部行为测试(离线、隔离 HOME,不触碰真实环境)
bash tests/run_all.sh
# 单独运行某个测试
bash tests/test_install.sh
bash tests/test_update.sh
bash tests/test_uninstall.sh
# 本地离线跑安装脚本(用假 skills 源和显式目标,避免 git clone 与写入真实目录)
HOME=/tmp/fakehome SUPERPOWERS_TARGET=trae-cn \
SUPERPOWERS_SKILLS_SRC=/path/to/fake bash install.sh
关键环境变量:
SUPERPOWERS_SKILLS_SRC:注入本地 skills 源(其下需有skills/子目录),跳过git clone, 测试与本地验证均依赖它。SUPERPOWERS_UPSTREAM_URL:覆盖上游仓库地址,默认https://github.com/obra/superpowers.git。SUPERPOWERS_TARGET:非交互环境下指定唯一目标,取值为trae-cn或trae。SUPERPOWERS_TTY:测试专用的终端设备覆盖项,默认/dev/tty;生产使用无需设置。
架构与关键文件
- install.sh:通过方向键菜单或
SUPERPOWERS_TARGET单选 Trae 目标 → 优先复用 完整的.agents/skills,否则获取上游 skills 源 →cp -R写入所选 skills 目录并写 manifest。核心函数select_target/target_skills_dir/agents_superpowers_state/resolve_src/copy_skills/write_manifest。 - update.sh:普通模式下唯一 manifest 自动定位,两处都有或都没有时单选;完整
.agents存在时改由唯一托管 Rule 自动定位,歧义时单选。选定目标后清理孤儿并逐 skill 清替(先删后拷),最后覆盖写 manifest。 - uninstall.sh:完整
.agents存在时无需选择,保留外部安装并清理两个 Trae 目录中 manifest 管理的副本及托管 Rule;普通模式下唯一 manifest 自动定位,歧义时单选, 再优先按 manifest 逐名删除(离线可用),无 manifest 时回退到上游 skills 清单。 - tests/test_helpers.bash:断言与隔离环境辅助(
make_temp_home、make_fake_src、assert_*、finish_tests)。兼容 bash 3.2,不用关联数组。 - README.md / README.zh-CN.md:英文默认 + 中文,结构须保持一致。
支持的 Trae 变体目录
两个候选根目录($HOME 下):.trae-cn(CN)、.trae(intl)。每次安装只选择一个目标,
目录不存在时自动创建;再次选择另一目标不会迁移或清理旧目标。._agent-cn / ._agent
不再探测、迁移或清理。
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.
- 1mo ago First seen · 95 lines · 1,757 tokens per session scan C 54ef3e40652c
trae-superpowers AGENTS.md is an instructions file published in the GitHub repository luyangkk/trae-superpowers (10 stars, last pushed 1mo ago), licensed MIT. It adds 1,757 tokens to every session, about $0.0070 per session on Opus 5.5. 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 2026-09-23.
trae-superpowers AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| trae-superpowers AGENTS.mdluyangkk/trae-superpowers | Instructions file | 10 | 1mo ago | MIT | C | 1,757 | Claude Code, Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |