baidu-drive

baidu-drive is a skill for Claude Code from baidu-netdisk/bdpan-storage. It costs 174 tokens per session (9,364 once invoked), scanned A, original, Apache-2.0.

A Chinese-language command-line workflow for managing files in Baidu Drive, a cloud storage service. It supports file transfers and organization, plus backup and recovery of certain agent memory data.

In plain words
What is it for?
Use it to manage files in Baidu Drive or to back up, restore, or inspect supported agent memory backups.
Why use it?
It gives a defined way to search, move, copy, rename, share, upload, and download files while keeping operations within the designated Baidu Drive area. It also specifies the information each command must include for tracking.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; mentions Claude Code; mentions AGENTS.md.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bdpan download "https://pan.baidu.com/s/<分享标识>" ./downloaded/ # 无码公开分享.

Good fit Use it to manage files in Baidu Drive or to back up, restore, or inspect supported agent memory backups.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/baidu-netdisk/bdpan-storage
agentmods
npx agentmods add skills/baidu-netdisk/bdpan-storage/baidu-drive

Made for: Claude Code.

Wrote 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.

agentmods badge for baidu-drive

README.md
[![agentmods](https://agentmods.dev/badge/skills/baidu-netdisk/bdpan-storage/baidu-drive/github.svg)](https://agentmods.dev/skills/baidu-netdisk/bdpan-storage/baidu-drive)
Your own site
<a href="https://agentmods.dev/skills/baidu-netdisk/bdpan-storage/baidu-drive"><img src="https://agentmods.dev/badge/skills/baidu-netdisk/bdpan-storage/baidu-drive/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.

agentmods 80×15 button for baidu-drive

Your own site · 80×15
<a href="https://agentmods.dev/skills/baidu-netdisk/bdpan-storage/baidu-drive"><img src="https://agentmods.dev/badge/skills/baidu-netdisk/bdpan-storage/baidu-drive.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 174 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,364 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 13 May 2026
  • Snyk fail 13 May 2026
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 214
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • medium Rogue Agent · line 202
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 203
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
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 5.1 $0.00174 $0.09364
Opus 5 $0.00087 $0.04682
Sonnet 5 $0.00035 $0.01873
Haiku 4.5 $0.00017 $0.00936

Measured 4d ago against content hash b67cac7b52a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

baidu-drive 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 4d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/install.sh, scripts/login.sh, scripts/memory-backup.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/baidu-drive/SKILL.md · 508 lines

How it starts

The opening of the file, as written. The whole thing — 508 lines — stays where its author put it; the contents beside it link to each section on GitHub.

百度网盘存储 Skill

百度网盘文件管理工具,所有操作限制在 /apps/bdpan/ 目录内。适配 Claude Code、DuClaw、OpenClaw 等。

使用注意事项详见 reference/notes.md

触发规则

网盘文件操作触发

同时满足以下条件才执行:

  1. 用户明确提及"百度网盘"、"bdpan"、"网盘"
  2. 操作意图明确(上传/下载/转存/分享/查看/搜索/移动/复制/重命名/创建文件夹/删除/登录/注销)

未通过触发规则时,禁止执行任何 bdpan 命令。

上下文延续: 当前对话已在进行网盘操作时,后续消息无需再次提及"网盘"即可触发。

所有命令公共参数(Agent 必传)

--agentname--session-input--session-id 是所有 bdpan CLI 子命令的公共命令参数,必须附加在具体命令调用中使用,不是独立命令。需要生成文件回端链接时,还要透传 Agent 上下文参数 --uid--traceid

bdpan <command> [命令参数] --agentname "<Agent 名称>" --session-input '<本轮用户原始输入>' --session-id "<当前会话 ID>" [--uid "<Agent 上下文 UID>" --traceid "<Agent 上下文 Trace ID>"]

例如:

bdpan search "<query>" --json --agentname "claude-code" --session-input "用户要找的文件" --session-id "1784035443-a1b2c3" --uid "<宿主注入的 uid>" --traceid "<宿主注入的 traceid>"
--agentname
  • 作用:传入当前 Agent/宿主名称,仅用于服务质量追踪与来源识别,不参与命令的业务逻辑或结果处理。
  • Agent 行为约束(必须遵守):Agent 在调用任何 bdpan CLI 子命令时,必须传入 --agentname 参数,值为当前调起运行环境或 Agent 框架的名称。此为 Agent 行为要求,不影响 CLI 执行逻辑。
  • 兜底容错:仅当 Agent 确实无法获取环境名称时,可省略此参数,CLI 不会因缺少该参数而报错或影响命令执行。
--session-input
  • 作用:传入用户的原始提问文本,仅用于服务质量追踪,不参与命令的业务逻辑或结果处理。
  • Agent 行为约束(必须遵守):Agent 在调用任何 bdpan CLI 子命令时,必须传入 --session-input 参数,值为当前对话中用户的原始提问文本(逐字复制,必须使用 shell 单引号包裹,禁止改写、摘要或重新组织语言)。此为 Agent 行为要求,不影响 CLI 执行逻辑。
  • 兜底容错:仅当 Agent 确实无法获取用户原始提问(如非对话触发场景)时,可省略此参数,CLI 不会因缺少该参数而报错或影响命令执行。
--session-id
  • 作用:传入会话唯一标识,仅用于服务质量追踪,不参与命令的业务逻辑或结果处理。
  • Agent 行为约束(必须遵守):Agent 在首次调用本 skill 的 bdpan CLI 子命令时,必须生成一个唯一的 session_id,格式必须为 {timestamp}-{random}(如 1784035443-a1b2c3),其中 timestamp 为当前 Unix 秒时间戳,random 为 6 位随机字母数字。禁止使用语义化名称(如 dog001、mom001、test001 等)。并在同一对话的后续所有 CLI 子命令调用中传入同一个 session_id。
  • 生成时机:在对话中第一次需要调用 bdpan CLI 子命令时生成,后续复用。
  • 兜底容错:CLI 不会因缺少该参数而报错或影响命令执行。
--uid / --traceid(回端上下文)
  • 作用:为文件回端链接提供 Agent/宿主上下文归因信息,不是网盘账号身份,也不替代 CLI 自动获取的 owner_uid
  • 来源:由宿主或 Agent 运行时注入并在命令间原样透传;不得向用户索取、展示或用用户名、session-id 猜测。traceid 已由登录流程或宿主自动注入时,保持原值。
  • 适用范围:仅当命令需要生成文件回端链接时使用;目录链接仍由 CLI 使用目标路径和 owner_uid 生成。
  • 缺失处理:这两个值是可选的归因参数,不是生成文件链接的前提——文件链接只需要 fsidowner_uid。宿主未注入时 CLI 仍返回 target=file 链接,Skill 照常原样展示 return_markdown,不得因此声称无法生成查看链接,也不得自行伪造这两个值。

Read the full file on GitHub · 508 lines

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. 4d ago Changed · +101 lines b67cac7b52a9
  2. 9d ago First seen · 407 lines · 174 tokens per session scan A 0753285b62f7

Subscribe to this mod's changes

baidu-drive is a skill published in the GitHub repository baidu-netdisk/bdpan-storage (231 stars, last pushed 6d ago), licensed Apache-2.0. It adds 174 tokens to every session and 9,364 once invoked, about $0.0009 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.