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 withoneai/one-agent-plugin --skill dropboxgit clone --depth 1 https://github.com/withoneai/one-agent-pluginWrote 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/withoneai/one-agent-plugin/dropbox)<a href="https://agentmods.dev/skills/withoneai/one-agent-plugin/dropbox"><img src="https://agentmods.dev/badge/skills/withoneai/one-agent-plugin/dropbox/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/withoneai/one-agent-plugin/dropbox"><img src="https://agentmods.dev/badge/skills/withoneai/one-agent-plugin/dropbox.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 | $0.00094 | $0.05953 |
| Opus 5 | $0.00047 | $0.02976 |
| Sonnet 5 | $0.00019 | $0.01191 |
| Haiku 4.5 | $0.00009 | $0.00595 |
Grade A, and why
dropbox 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 5d 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.
This is a copy
86% identical to 2-chat — 258 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dropbox through One
Dropbox is a cloud storage platform that enables users to store, share, and collaborate on files and documents securely across devices and teams.
One exposes Dropbox through four MCP tools. The table below carries real action ids from One's knowledge base, so for a common operation you can skip search and go straight to reading the action's parameters.
How to run an action
- Find the action in the table below, or call
search_one_platform_actionswith platformdropboxif it is not listed. - Call
get_one_action_knowledgewith the action id. Do this every time, including for actions in this table. The table gives you the id, not the parameters. - Call
execute_one_actionwith parameters copied from that knowledge.
Never guess a parameter name, a body field, or an enum value. The knowledge has the real schema, and a guessed field is either a 400 or a silent write of the wrong thing.
Before you start
Call list_one_integrations once and confirm Dropbox is connected. If it is missing, the user has not connected it: say so and point them at https://app.withone.ai rather than reaching for raw HTTP.
Each connection carries an access field. If it reports {"policy": "methods", "methods": ["GET"]} the agent is read-only here, so plan a read-only answer instead of attempting a write that will be refused.
Before a write
Creates, updates, deletes and sends land on a real Dropbox account and cannot be recalled. State the action and the specific target in one line before the first write in a task, and let the user stop you. Reads need no confirmation.
Actions
Files
| Action | Method | Path | Action id |
|---|---|---|---|
| Check a Batch Delete Job Status | POST | /2/files/delete_batch/check |
conn_mod_def::GJ2YeS_a5Ak::ln1Bg0g8Qiqrjo8RnC6C3A |
| Check a Create Folder Batch Job Status | POST | /files/create_folder_batch/check |
conn_mod_def::GJ2Yd2MAUnA::Sjrvu6a7QvuQUvxLZj0mXA |
| Check Status of a Move Batch v2 Job | POST | /files/move_batch/check_v2 |
conn_mod_def::GJ2Ygtd6zGw::pMJU5wB1TvGCUA5TekZDGA |
| Continue Listing a Folder | POST | /files/list_folder/continue |
conn_mod_def::GJ2Yfz0tWEc::FiSFqMwYRwWkwIOpR-Bj5g |
| Copy a File or Folder | POST | /2/files/copy_v2 |
conn_mod_def::GJ2YXnRvxVc::xocmINTQRVCsJWOhLBDVXQ |
| Copy Multiple Files or Folders (Batch, v2) | POST | /2/files/copy_batch_v2 |
conn_mod_def::GJ2YXy5oHIo::ertEyamBQ_e2om-8yPVKVg |
| Delete a File or Folder | POST | /2/files/delete_v2 |
conn_mod_def::GJ2Yd-EbMzc::5qFJ0RLjTH-ST3MbuIFcug |
| Delete Multiple Files/Folders (Batch) | POST | /2/files/delete_batch |
conn_mod_def::GJ2YeHC2rUY::fVjyPaMzQxS9d9cWFyfibA |
| Download a File | POST | /files/download |
conn_mod_def::GJ2YebAmTy0::ufbX-_tvSOePcDqblDuPLg |
| Download a Folder as a ZIP File | POST | /files/download_zip |
conn_mod_def::GJ2Yek4tqrs::xVZNqdrqRUmkVUbEZtOGSg |
| Export a File | POST | /files/export |
conn_mod_def::GJ2YesPdC2I::Ztd7vzMQRZei_WNw-N3ukQ |
| Finish a File Upload Session (Commit Uploaded Data) | POST | /2/files/upload_session/finish |
conn_mod_def::GJ2YoaCU9q4::rOQW3wkXR3aedsPj9Zuj5g |
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.
- 5d ago First seen · 291 lines · 0 tokens per session scan A 7eb9095c907c
dropbox is a skill published in the GitHub repository withoneai/one-agent-plugin (1 stars, last pushed 19d ago), licensed MIT. It adds 94 tokens to every session and 5,953 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to 2-chat, differing in 258 lines, and is treated as a copy.
Other skills, from other repositories
box
Box manages cloud files, sharing, search, and metadata.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
recipe-save-email-attachments
Find Gmail messages with attachments and save them to a Google Drive folder.
material-organizer
Organize only the materials the user has already provided or explicitly pointed to. The job is to make messy inputs easier to scan, reuse, archive, or continue from later while preserving source traceability.
minutes-note
Add a note to the current recording or annotate a past meeting. Use whenever the user says "note that", "remember this", "mark this as important", "add a note about", "annotate the meeting", or wants to capture a thought during or after a recording. Plain text input — no markdown needed.
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.