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 agentmods add skills/yc-software/qm/dropboxnpx skills add yc-software/qm --skill dropboxgit clone --depth 1 https://github.com/yc-software/qmWhat 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 | $0.00027 | $0.01924 |
| Opus 5 | $0.00014 | $0.00962 |
| Sonnet 5 | $0.00005 | $0.00385 |
| Haiku 4.5 | $0.00003 | $0.00192 |
Grade A, and why
dropbox scanned grade A with 1 finding 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sS -X POST 'https://api.dropboxapi.com/2/users/get_current_account' \ How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dropbox
Use this skill when the user asks about their Dropbox files or folders — listing, searching, reading/downloading, uploading, or sharing.
This is an OAuth connector. The resolved user's Dropbox token already lives on your computer as an environment variable, one per Dropbox API host (the way a logged-in CLI's cached credential would):
$VAULT_TOKEN_API_DROPBOXAPI_COM— forapi.dropboxapi.com(RPC: list, search, share, move, delete)$VAULT_TOKEN_CONTENT_DROPBOXAPI_COM— forcontent.dropboxapi.com(download, upload)
Both carry the same Dropbox token (one OAuth grant spans every host), so if a
host-specific var is empty, $VAULT_TOKEN_API_DROPBOXAPI_COM works as the bearer for any
Dropbox host. Pass it as -H "Authorization: Bearer $VAULT_TOKEN_...". Never ask the user
for a token, log it, or use another principal's credential or a service fallback.
If $VAULT_TOKEN_API_DROPBOXAPI_COM is empty: per-user connector tokens are injected
only in a direct DM with the user (their personal scope) — in a channel or group
they're absent by design, even for a fully-connected user. So don't tell a channel user to
reconnect; ask them to DM you to run this. Only if it's empty inside a DM does it mean they
haven't connected Dropbox — then point them to the Connectors page.
On 401: the token is expired/invalid → have them reconnect — unless the error body's
.tag is missing_scope, in which case the app lacks a permission; name the required_scope
it returns (the connected app grants account_info.read, files.metadata.read,
files.content.read/write, sharing.read/write).
First: pick the right namespace (team vs personal)
This is the step that makes team and shared folders visible. By default the Dropbox
API only lists the user's personal (home) namespace — for a Business member that root
is often nearly empty. The team folders they see in the Dropbox web UI live in the
team namespace, and the API only shows them when you set the Dropbox-API-Path-Root
header.
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.
- 2d ago First seen · 167 lines · 27 tokens per session scan A 2ccf657a630f
dropbox is a skill published in the GitHub repository yc-software/qm (14,428 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 1,924 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
building-pydantic-ai-agents
Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydanticai, or asks to build an AI agent, add tools/capabilities, defer capability loading, stream output, define agents…
complete-partial-pr
Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical maintainer decisions.
harness-creator
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…
address-feedback
Find and address unresolved PR review comments for the current branch, then continue the canonical push, reply, reaction, and resolution workflow.
agent-initialization
Initialize an Agent's settings from a user requirement by writing AGENTS.md, setting identity metadata, and installing only needed Skills.
agent-mode
Unified tool for managing agent LLM modes (add, remove, update, list, switch).