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 commands/managed-digital-llc/justdrop-mcp/justdropgit clone --depth 1 https://github.com/Managed-Digital-LLC/justdrop-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/commands/managed-digital-llc/justdrop-mcp/justdrop)<a href="https://agentmods.dev/commands/managed-digital-llc/justdrop-mcp/justdrop"><img src="https://agentmods.dev/badge/commands/managed-digital-llc/justdrop-mcp/justdrop.svg" alt="Measured on agentmods" 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 | $0.00017 | $0.00422 |
| Opus 5 | $0.00009 | $0.00211 |
| Sonnet 5 | $0.00003 | $0.00084 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
justdrop 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.
What it actually says
The user invoked /justdrop. Use the JustDrop MCP tools (drop, receive, status, cancel) to fulfil this request:
$ARGUMENTS
How to interpret the request:
- send / drop / share <paths...> → call the
droptool with those paths. Show the returned room code, link, and QR code to the user VERBATIM (keep the QR inside its code fence) so they can scan it with their phone. If they mention a time limit ("for 10 minutes"), passexpiry_minutes. - get / receive / grab [from] [into ] → call the
receivetool with thatroom_code. Defaultsave_dirto "./incoming" unless they name a directory. Remind them: they create the room at https://justdrop.ai on the sending device and read you the code. - get / receive with NO room code → ask for the room code from the sending device (justdrop.ai → send → code). Only create the room agent-side (receive without room_code) if the other side is another JustDrop MCP/CLI client.
- status [room-code] → call the
statustool (no room code = list all transfers this session). - cancel → call the
canceltool. - empty arguments → briefly show these subcommands and ask what they'd like to transfer.
Notes:
- Files can only be read from / saved inside the configured root directory. If a path is refused, say why and suggest copying the file into the workspace first.
- Never work around a refused path (dotfiles, credentials) — the refusal is the security model working.
- If a tool reports the room expired or wasn't found, ask the user to generate a fresh code.
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 · 23 lines · 17 tokens per session scan A 74d7aac89eb4
justdrop is a command published in the GitHub repository Managed-Digital-LLC/justdrop-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 422 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.