Dropbox AI Plugins is a repository of integration files for using Dropbox with Claude, OpenAI Codex, and Cursor through MCP host components, which let coding agents access defined external tools. It is for configuring those agents and managing their Dropbox OAuth authentication scopes. The catalogue entries are the agent-specific plugin artifacts and shared material stored in the repository.
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 skills add dropbox/dropbox-ai-plugins --skill clean-up-dropbox-contentgit clone --depth 1 https://github.com/dropbox/dropbox-ai-pluginsWrote 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/dropbox/dropbox-ai-plugins/clean-up-dropbox-content)<a href="https://agentmods.dev/skills/dropbox/dropbox-ai-plugins/clean-up-dropbox-content"><img src="https://agentmods.dev/badge/skills/dropbox/dropbox-ai-plugins/clean-up-dropbox-content/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/skills/dropbox/dropbox-ai-plugins/clean-up-dropbox-content"><img src="https://agentmods.dev/badge/skills/dropbox/dropbox-ai-plugins/clean-up-dropbox-content.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 | $0.00047 | $0.00617 |
| Opus 5.5 | $0.00019 | $0.00247 |
| Sonnet 5.5 | $0.00009 | $0.00123 |
| Haiku 4.5 | $0.00005 | $0.00062 |
Grade A, and why
clean-up-dropbox-content 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 2mo 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clean Up Dropbox Content
Use this skill for careful deletion workflows in Dropbox.
Tools
searchlist_folderget_file_metadatalist_shared_linkscopydeletecheck_job_status
Workflow
- Confirm the cleanup goal and scope.
- Use
searchorlist_folderto identify candidate content. - Use
get_file_metadatato verify each deletion candidate. - Use
list_shared_linkswhen deleting shared content could affect others. - If the user may need rollback context, explain that the current Dropbox MCP tools do not expose revision listing or restore operations.
- If the user wants to preserve a copy first, confirm the exact destination, call
copy, and usecheck_job_statusfor any asynchronous copy job until it completes successfully. - After any requested copy has completed successfully, present a deletion review list and ask for explicit confirmation.
- Call
deleteonly for the exact confirmed items. - Use
check_job_statusfor any asynchronous copy or deletion job until it completes or must be reported as pending. - Report every copied, deleted, skipped, pending, or failed item.
Confirmation Required
Before deleting anything, confirm:
- Exact paths or stable identifiers
- Whether each item is a file or folder
- Whether the item appears shared
- Why it is safe to delete
- Exact copy destination, if the user wants to preserve a copy first
Output
Before deletion, present:
- Candidate path
- Type
- Modified time when available
- Sharing status when relevant
- Copy destination when preserving a copy first
- Reason it appears safe to delete
After deletion, present:
- Copied items when relevant
- Deleted items
- Pending items and job status when relevant
- Failed items and reason
- Items skipped because they were ambiguous or risky
Safety
Never delete based only on a broad pattern like "old files" or "duplicates" without listing exact targets. Never delete a parent folder when the user confirmed only child files. If confidence is not high, stop and ask the user to choose.
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.
- 2mo ago First seen · 79 lines · 47 tokens per session scan A 43f8defb8d90
clean-up-dropbox-content is a skill published in the GitHub repository dropbox/dropbox-ai-plugins (11 stars, last pushed 9d ago), licensed Apache-2.0. It adds 47 tokens to every session and 617 once invoked, about $0.0002 per session on Opus 5.5. 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.