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/minorun365/html-share/inboxnpx skills add minorun365/html-share --skill inboxgit clone --depth 1 https://github.com/minorun365/html-shareWrote 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/minorun365/html-share/inbox)<a href="https://agentmods.dev/skills/minorun365/html-share/inbox"><img src="https://agentmods.dev/badge/skills/minorun365/html-share/inbox.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 | $0.00044 | $0.00583 |
| Opus 5 | $0.00022 | $0.00292 |
| Sonnet 5 | $0.00009 | $0.00117 |
| Haiku 4.5 | $0.00004 | $0.00058 |
Grade A, and why
inbox 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.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inbox
Use the html-share CLI. Do not call the review API directly and do not print device tokens.
1. Read waiting requests
html-share review inbox
requestsare unfinished owner requests, oldest firsttargetis a project nickname the owner typed on the phone. It may benull. Treat it as a hint, not a filesystem path- If the array is empty, say there are no inbox requests and stop
- If the CLI says this computer is not paired, ask the owner to tap "Macを登録" in the inbox and run
/mobile pair <code>
2. Close every request you picked up, before starting
html-share review complete <id...>
- Close them all now. Do not wait until the work is done
- The inbox is a handover box, not a progress tracker. A request has no "in progress" state, so anything left open looks identical to a request no computer has picked up yet
- Closing is not abandoning. Report progress and results in chat as usual
- Finish what you picked up in this session. If something has to wait, say so in chat — it is no longer in the inbox to remind anyone
- Requests expire after 90 days, so do not leave them unread either
3. Identify the starting folder
Requests from a phone often belong to different projects. Do not start everything in the current working directory.
- Pull 1–3 distinctive words from the request text. If
targetis present, search for that nickname first - Look in nearby README / AGENTS.md files. Do not keep a hardcoded map of nicknames to folders
- If the folder is the current working directory, start here
- If it is a different folder, start a new session there and tell the owner you did so
- If one request spans two places, start from the folder you will write to
- If you cannot tell, ask with 2–3 candidates. Do not guess from recency or a similar name
4. Start the work
Treat each request as a normal user instruction.
- If there is one request, start it without asking which to do first
- If there are several, list them in one line each with the folder you chose, then start from the oldest
- Still confirm before sending, publishing, deleting, or spending money
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 57 lines · 44 tokens per session scan A 8cec32d73a10
inbox is a skill published in the GitHub repository minorun365/html-share (90 stars, last pushed today), licensed Apache-2.0. It adds 44 tokens to every session and 583 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
agent-squad-swift
Use when building or modifying a Swift app that uses the AgentSquad Swift framework — on-device multi-agent orchestration for iOS 16+ / macOS 14+: orchestrator, agents (Agent, GroundedAgent), classifier routing, LLM clients (OpenAI-compatible), tools (native + MCP), tool UIs/widgets, on-device storage, tracing, and…
location-skill
Get Android device GPS location - latitude, longitude, accuracy, speed, and provider information.
wifi-skill
Control Android WiFi - enable, disable, get status, scan for networks, and get current connection info.
app-launcher-skill
Launch Android applications by package name. Open any installed app programmatically.
app-list-skill
Get list of installed Android applications with package names, versions, and metadata.
audio-skill
Control Android audio - get/set volume, mute/unmute for media, ringtone, notification, and call volumes.