Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/daodao166888/fanbox-windows/fanbox-agent)<a href="https://agentmods.dev/skills/daodao166888/fanbox-windows/fanbox-agent"><img src="https://agentmods.dev/badge/skills/daodao166888/fanbox-windows/fanbox-agent/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/daodao166888/fanbox-windows/fanbox-agent"><img src="https://agentmods.dev/badge/skills/daodao166888/fanbox-windows/fanbox-agent.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 | $0.00101 | $0.02021 |
| Opus 5 | $0.00051 | $0.01010 |
| Sonnet 5 | $0.00020 | $0.00404 |
| Haiku 4.5 | $0.00010 | $0.00202 |
Grade B, and why
fanbox-agent scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl "${CT[@]}" -X POST -H 'Content-Type: application/json' -d '{"id":"t5"}' "$FANBOX_CTL/kill" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl "${CT[@]}" "$FANBOX_CTL/terminals" This is a copy
100% identical to fanbox-agent — 1 line differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FanBox 终端控制
只在 FanBox 桌面 app 的终端里可用。先确认门票在手:
[ -n "$FANBOX_CTL" ] && echo "在 FanBox 里,我是 $FANBOX_TERM_ID 号窗口" || echo "不在 FanBox 终端里,本 skill 不可用"
三个环境变量由 FanBox 注入:FANBOX_CTL(接口地址)、FANBOX_CTL_TOKEN(门票,每次启动随机、只存在于 FanBox 终端的环境里,绝不外传、不写进文件)、FANBOX_TERM_ID(自己的窗口 id)。
别给自己($FANBOX_TERM_ID)发指令——那会把你自己的输入流打乱甚至死循环。
接口速查
所有请求带 x-fanbox-token 头。以下用 CT 缩写公共参数:
CT=(-s -H "x-fanbox-token: $FANBOX_CTL_TOKEN")
列出所有终端窗口(id / 目录 / 前台进程 / 忙闲 / 最近输出尾巴):
curl "${CT[@]}" "$FANBOX_CTL/terminals"
读某窗口最近输出(去 ANSI 纯文本,默认 200 行,最多 2000):
curl "${CT[@]}" "$FANBOX_CTL/read?id=t2&lines=100"
给窗口发指令(默认自动补回车提交;"submit": false 只输入不提交;多行文本发给 claude 等 TUI 加 "paste": true 走 bracketed paste 整块粘贴):
curl "${CT[@]}" -X POST -H 'Content-Type: application/json' \
-d '{"id":"t2","text":"npm test"}' "$FANBOX_CTL/send"
控制键直接发字符本身,如 Ctrl-C:{"id":"t2","text":"","submit":false}。
新开终端窗口(可选 autorun 开窗即执行,会等 shell 就绪再敲):
curl "${CT[@]}" -X POST -H 'Content-Type: application/json' \
-d '{"cwd":"/path/to/project","autorun":"claude \"跑通所有测试\""}' "$FANBOX_CTL/create"
# → {"ok":true,"id":"t5","autorun":true}
等窗口告一段落(HTTP 长轮询,timeoutMs 最长 240000):
curl "${CT[@]}" -X POST -H 'Content-Type: application/json' \
-d '{"id":"t5","timeoutMs":120000}' "$FANBOX_CTL/wait"
三种等法:
- 默认:前台回到裸 shell 且输出静默 ≥
idleMs(默认 2000)——适合等普通命令跑完 "idle":"quiet":只看输出静默——适合等 claude 等常驻 TUI 回答完,建议配"idleMs":3000"until":"正则":新输出匹配到正则就立刻返回——注意只匹配 wait 开始之后的新输出,所以要在结果出现前就发起 wait。命令回显也算输出:你敲的命令本身会先出现在流里,正则要用^锚定行首(如"^DONE$")才不会匹配到自己发的命令
返回 {ok, idle|matched|exited|timeout, elapsed, output},output 是等待期间的输出(最后 8KB),通常不用再 read。
关闭窗口:
curl "${CT[@]}" -X POST -H 'Content-Type: application/json' -d '{"id":"t5"}' "$FANBOX_CTL/kill"
定时任务:用户白话 → 你换算成 schedule
用户说「每天早上 9 点整理灵感箱」「周五下班前汇总本周改动」「两小时后跑一遍测试」时,把意图换算成 schedule 对象调接口。到点 FanBox 会自动开一个终端窗口执行(FanBox 没开着则记「错过」不补跑)。
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.
- 11d ago First seen · 134 lines · 101 tokens per session scan B 631a6c299240
fanbox-agent is a skill published in the GitHub repository daodao166888/fanbox-windows (25 stars, last pushed 1mo ago), licensed MIT. It adds 101 tokens to every session and 2,021 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). It is 100% identical to fanbox-agent, differing in 1 line, and is treated as a copy.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.