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 skills add DemonDamon/AgenticX --skill agenticx-automation-crontaskgit clone --depth 1 https://github.com/DemonDamon/AgenticXWrote 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/demondamon/agenticx/agenticx-automation-crontask)<a href="https://agentmods.dev/skills/demondamon/agenticx/agenticx-automation-crontask"><img src="https://agentmods.dev/badge/skills/demondamon/agenticx/agenticx-automation-crontask.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00065 | $0.01051 |
| Opus 5 | $0.00032 | $0.00526 |
| Sonnet 5 | $0.00013 | $0.00210 |
| Haiku 4.5 | $0.00006 | $0.00105 |
Grade A, and why
agenticx-automation-crontask 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 8d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- agenticx-automation-crontask — 100% identical, 0 lines differ
What it actually says
AgenticX 定时任务(Crontask)
任务根目录(工程约定,与 Desktop / schedule_task 一致)
| 用户在自动化里是否填写「工作区」 | 任务根目录 |
|---|---|
| 填写了 | 用户给定目录(Desktop 会 mkdir) |
| 留空 | ~/.agenticx/crontask/<task_id>/(每个定时任务独占一个子目录,与 automation:<task_id> 对话一一对应) |
- Python venv:一律在任务根下
<任务根>/.venv,用<任务根>/.venv/bin/pip/python;不要把定时任务专属依赖装到仓库.venv或任意路径,除非该路径就是用户指定的任务根。 - 脚本、数据、日志、临时文件、辅助工具:全部放在任务根或其子目录内;不要在
~/.agenticx/scripts、仓库根等散落(除非用户显式把其中某路径设为任务根)。
Meta-Agent:调用 schedule_task 之前(运行环境)
定时任务以后在 automation 专属会话里执行,不会在当时的 Near 对话里自动装包。在调用 schedule_task 之前应代用户准备好任务根下的环境:
- 先拿到 任务根:用户指定的
workspace,或创建任务后默认的~/.agenticx/crontask/<task_id>/(schedule_task返回的task_id可用于路径)。 - 在任务根下
python3 -m venv .venv(若尚无),.venv/bin/pip install …。 bash_exec用<任务根>/.venv/bin/python试跑脚本,确认无 import 错误。instruction里的命令必须与 同一解释器路径 一致。
默认工作区(摘要)
- 未指定
workspace时,Desktop 与schedule_task均写入~/.agenticx/crontask/<task_id>并创建目录。 - 删除任务时,UI 会二次确认是否同时删除该目录下的本地文件(仅针对上述 crontask 子目录,不随意删除用户任意路径)。
用 schedule_task 创建任务(对话 / Meta-Agent)
在 instruction(提示词)里写清:
- 何时跑:已在工具参数里用
frequency_type/time/days表达;提示词内可再写一句业务语义(如「交易日 9:28」)便于人读。 - 怎么跑:必须要求 真实执行(如
bash_exec+python3),禁止「只给代码不运行」。 - 输出格式:给出严格版式(标题、字段、单位),并写明「最终回复只允许该版式,禁止工具 JSON」。
- 失败:简短错误(接口/库/网络),不超过若干行,不要教程、不要反问。
- 依赖:写明
pip install包名;执行环境以本机为准。
可选参数 workspace:仅当用户明确要求固定目录时填写;否则留空使用默认 crontask 目录。
任务执行时(automation 会话)
会话 avatar_id 为 automation:<task_id> 时,后端会注入执行器系统提示,强调:
- 先工具执行、再按用户版式输出;
- 不在最终回复粘贴
schedule_task等原始 JSON; - 失败简短说明。
编写或审阅提示词时,应与此行为一致。
验收清单
- 提示词是否要求实际跑命令并得到数据?
- 是否定义了唯一允许的输出模板?
- 是否说明非交易日 / 无数据时的单行或短输出?
- 是否需要默认 crontask 路径下的脚本文件(便于复跑与排障)?
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.
- 8d ago First seen · 63 lines · 65 tokens per session scan A 41a37f9d8175
agenticx-automation-crontask is a skill published in the GitHub repository DemonDamon/AgenticX (229 stars, last pushed yesterday), licensed Apache-2.0. It adds 65 tokens to every session and 1,051 once invoked, about $0.0003 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
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
cron
Schedule reminders and recurring tasks.
cron
Manage scheduled cron jobs via the adclaw CLI — create, list, pause, resume, and delete tasks.
Send emails directly from your agent. Supports HTML and plain text. Works with Unosend (5,000 free emails/month) or any SMTP provider.
cli
A command-line and desktop-control skill for opening and closing applications, listing running apps or desktop items, opening files and folders, and checking the recycle bin. The command line is a text interface for controlling a computer.
Gmail: read inbox, search emails, compose drafts, send messages.