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 instructions/sanzharal/filedropbot/agents-mdgit clone --depth 1 https://github.com/sanzharal/filedropbotWrote 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/instructions/sanzharal/filedropbot/agents-md)<a href="https://agentmods.dev/instructions/sanzharal/filedropbot/agents-md"><img src="https://agentmods.dev/badge/instructions/sanzharal/filedropbot/agents-md.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 | $0.00572 | $0.00572 |
| Opus 5 | $0.00286 | $0.00286 |
| Sonnet 5 | $0.00114 | $0.00114 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
filedropbot AGENTS.md 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 4d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent instructions — filedropbot
This file documents the one convention an AI coding agent (Claude Code, Codex, Cursor, Aider, Gemini CLI, …) needs to know to use filedropbot. The mechanism is just the filesystem, so it works for any agent that can run shell commands — no API, SDK, or plugin required.
Receiving files from my phone
Files I send to the bot land under /root/filedropbot/data/drops/<date>/. The
bot replies to me with the host path; I paste it to you. Nothing for you to do.
Sending a file to my phone
To deliver a file to me on Telegram — a screenshot, a generated chart, a log, a build artifact — copy it into the outbox:
cp /path/to/file.png /root/filedropbot/data/outbox/
Within a few seconds the bot DMs it to my phone and moves it to
data/sent/<date>/. Do this whenever I ask you to "send me", "DM me", or "show
me on my phone" a file.
Notes:
-
Limit: 50 MB per file (Telegram bot upload cap). Larger files are skipped.
-
Atomic writes: if you generate the file slowly, write it under a
*.tmpname andmvit into the outbox when finished — the bot ignores.tmp,.part, and dotfiles until they're renamed, and otherwise waits ~2s of inactivity before sending so it never ships a half-written file. -
Filenames are preserved exactly and sent as documents (no recompression).
-
Message caption: by default the caption equals the filename. To keep a clean filename and add context, drop a sidecar
<filename>.caption.txtnext to the file — its text (≤1024 chars) becomes the caption, and the sidecar is removed after sending. Example:cp widget.zip /root/filedropbot/data/outbox/ printf 'ProverkaCheka widget v3.0.0' > /root/filedropbot/data/outbox/widget.zip.caption.txt
Wiring this into your agent's global config
So an agent knows this in every project (not just this repo), add the "Sending a file to my phone" instruction to its global standing-instructions file:
- Claude Code:
~/.claude/CLAUDE.md - Codex:
~/.codex/AGENTS.md(or repo-rootAGENTS.md) - Cursor:
.cursor/rules/filedrop.mdc - Gemini CLI:
~/.gemini/GEMINI.md
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.
- 4d ago First seen · 53 lines · 572 tokens per session scan A 861828c45684
filedropbot AGENTS.md is an instructions file published in the GitHub repository sanzharal/filedropbot (2 stars, last pushed 29d ago), licensed MIT. It adds 572 tokens to every session, about $0.0029 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 instructions, from other repositories
cml-mcp AGENTS.md
AGENTS.md instructions for xorrkaz/cml-mcp, covering agents.md — cml mcp server, project overview, compatibility goal, repository layout and tool modules (src/cmlmcp/tools/).
brilliant_sdk AGENTS.md
Instructions for brilliantlabsAR/brilliant_sdk, covering brilliant sdk — agent guide, how an app works (the pattern behind everything), minimal reading paths, verify without hardware and testing.
NeoMind CLAUDE.md
Claude Code instructions for camthink-ai/NeoMind, covering neomind — edge ai platform for iot, development commands, ecosystem repositories, extension package contract (.nep) and device type template contract (json).
cad-cae-copilot copilot-instructions.md
Copilot instructions for armpro24-blip/cad-cae-copilot, covering github copilot — aieng workspace and essentials.
phone-mcp CLAUDE.md
Claude Code instructions for premex-ab/phone-mcp, covering claude.md, project overview, build commands, architecture and module layout.
zmk-config AGENTS.md
AGENTS.md instructions for urob/zmk-config, covering customization guide, ground rules, how the multi-board layout works, adding a new board and where to change what.