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 borealstack/proton-drive-cli-mcp --skill proton-drive-cligit clone --depth 1 https://github.com/borealstack/proton-drive-cli-mcpWrote 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/borealstack/proton-drive-cli-mcp/proton-drive-cli)<a href="https://agentmods.dev/skills/borealstack/proton-drive-cli-mcp/proton-drive-cli"><img src="https://agentmods.dev/badge/skills/borealstack/proton-drive-cli-mcp/proton-drive-cli/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/borealstack/proton-drive-cli-mcp/proton-drive-cli"><img src="https://agentmods.dev/badge/skills/borealstack/proton-drive-cli-mcp/proton-drive-cli.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 | $0.00038 | $0.00580 |
| Opus 5.5 | $0.00015 | $0.00232 |
| Sonnet 5.5 | $0.00008 | $0.00116 |
| Haiku 4.5 | $0.00004 | $0.00058 |
Grade A, and why
proton-drive-cli 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Proton Drive
Use the proton-drive-cli MCP server tools for Proton Drive work. The server wraps the official Proton Drive CLI and uses the current OS user's CLI session.
Workflow
- Start with
proton_drive_diagnosewhen setup or auth state is unknown. - Use
proton_drive_setupwhen the CLI may be missing; it can install the latest official Proton Drive CLI for the current OS/CPU and verifies Proton's SHA-512 checksum before use. - If unauthenticated, call
proton_drive_auth_login, surface any returned URL, and ask the user to finish browser sign-in. This tool starts login in the background and returns quickly. - If the user asks what happened to login, call
proton_drive_auth_login_status. - Use
/my-filesas the default root for user-owned files. - Use POSIX-style remote paths even on Windows, for example
/my-files/Reports/file.pdf. - Prefer JSON-returning tools over raw CLI output.
Safety
- Do not call
proton_drive_auth_logoutunless the user explicitly asks to log out. - Do not permanently delete, empty trash, remove sharing access, or accept/reject invitations unless the user explicitly confirms the action.
- Do not write text files unless the user explicitly confirms the destination path and content.
- Do not ask for or pass custom public-link passwords through this MCP server; the current official CLI accepts them only as command-line arguments.
- For upload/download, ask for a concrete local path when it is not clear from context.
- Do not request or handle Proton passwords; login is browser-based through the official CLI.
Useful Tools
proton_drive_diagnoseandproton_drive_setupfor first-run checks.proton_drive_listfor browsing folders; uselimitandoffsetto keep output small.proton_drive_cli_installfor explicit install or update to the official latest CLI.proton_drive_infofor metadata.proton_drive_create_folderbefore uploads into a new location.proton_drive_uploadandproton_drive_downloadfor transfers.proton_drive_upload_async,proton_drive_download_async, andproton_drive_job_statusfor large or slow transfers.proton_drive_read_textandproton_drive_write_textfor small UTF-8 files.proton_drive_sharing_statusbefore changing access.proton_drive_cli_helpwhen a Proton CLI behavior or flag is unclear.
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 · 41 lines · 38 tokens per session scan A 272209c6dfd8
proton-drive-cli is a skill published in the GitHub repository borealstack/proton-drive-cli-mcp (0 stars, last pushed 4mo ago), licensed MIT. It adds 38 tokens to every session and 580 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 2026-08-31.
Other skills, from other repositories
adhoc-flow
Workflow for the rest of tasks: lightweight documentation, build, track, synchronize, etc.
google-meet
Google Meet via gws: create spaces, fetch join links, list recordings.
phone-call
Place outbound AI phone calls via Bland AI: book reservations, make appointments, ask businesses questions, then report back the transcript and summary.
cortex-profile
View and manage your cognitive profile — how you think, work patterns, blind spots, and cross-domain connections. Use when the user says 'show my profile', 'how do I work', 'what are my patterns', 'cognitive style', 'blind spots', 'methodology', or at the start of a session to load context. Also use 'rebuild profile'…
people-crm
Turn LinkedIn connections (or any contact export) into a queryable personal CRM using the agent database.
x-use-inbox
Read X direct messages, triage inbox and request folders, send contextual reviewed messages, and inspect notifications with x-use. Use for unread chats, conversation search or replies, individual DMs, and All or Mentions notifications; use x-use-engage for public-post engagement and profile outreach research.