automate

automate is a skill for Claude Code from griffinwork40/agent-afk. It costs 44 tokens per session (593 once invoked), scanned A, original, Apache-2.0.

A setup guide for running a task automatically on a recurring schedule and sending its summary to Telegram, a messaging service. It uses the afk daemon, a background program that runs scheduled jobs.

In plain words
What is it for?
It helps create recurring headless jobs, check for schedule conflicts, confirm the scheduler and Telegram setup, and prepare the instruction each run receives.
Why use it?
It removes the need to start the same task manually and provides a notification when the scheduled run produces a result.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions subagents.

Part of the awa-bundled plugin — 17 skills shipped together

Good fit It helps create recurring headless jobs, check for schedule conflicts, confirm the scheduler and Telegram setup, and prepare the instruction each run receives.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/griffinwork40/agent-afk/automate
Install

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.

Any agent
npx skills add griffinwork40/agent-afk --skill automate
Clone the repo
git clone --depth 1 https://github.com/griffinwork40/agent-afk

Made for: Claude Code.

Or install awa-bundled, the plugin that ships this one along with the rest of its 17 skills.

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.

agentmods badge for automate

README.md
[![agentmods](https://agentmods.dev/badge/skills/griffinwork40/agent-afk/automate.svg)](https://agentmods.dev/skills/griffinwork40/agent-afk/automate)
Your own site
<a href="https://agentmods.dev/skills/griffinwork40/agent-afk/automate"><img src="https://agentmods.dev/badge/skills/griffinwork40/agent-afk/automate.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 593 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Rogue Agent · line 8
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 8
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.00593
Opus 5 $0.00022 $0.00296
Sonnet 5 $0.00009 $0.00119
Haiku 4.5 $0.00004 $0.00059

Measured 8d ago against content hash 93380f58316e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

automate 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.

src/bundled-plugins/awa-bundled/skills/automate/SKILL.md · 20 lines

What it actually says

Set up a recurring headless task using afk's native scheduler. Do NOT hand-roll launchd plists or shell scripts — afk has first-class scheduling: the create_schedule tool writes ~/.afk/config/schedules.json entries that afk daemon runs on cron.

Dispatch two sub-agents in parallel:

  1. Scout — call list_schedules and inspect ~/.afk/config/schedules.json for existing or overlapping jobs, run afk service status to see whether the daemon is installed as a launchd service and running, confirm Telegram is configured (TELEGRAM_BOT_TOKEN + AFK_TELEGRAM_ALLOWED_CHAT_IDS), and scan the target project folder for conventions. Report conflicts, daemon/service state, and any missing prerequisite.
  2. Prompt designer — draft the recurring task's command string: a self-contained prompt (or /skill --flags invocation) sent verbatim into a freshly spawned session each run. The daemon session starts cold, so encode all input context explicitly, and require the run to END by calling the send_telegram tool with a concise, push-ready summary.

When both return:

  • If Telegram is unconfigured, stop and tell the user to run /telegram-setup first — send_telegram fails closed without TELEGRAM_BOT_TOKEN and AFK_TELEGRAM_ALLOWED_CHAT_IDS.
  • Create the job with the create_schedule tool: name, the designed command, the requested 5-field cron, trigger: "cron", and notifyOn: "failure" as a crash safety-net (the per-run summary comes from the agent's own send_telegram call, not from notifyOn).
  • Schedules only fire while the daemon is running, so make it survive reboot/crash: if afk service status shows the daemon isn't installed, run afk service install daemon (launchd RunAtLoad + KeepAlive on macOS).

Dispatch a verification sub-agent to confirm the job registered (list_schedules), the daemon is running (afk service status), and — by running the task's command once as a one-shot (afk chat "<command>") — that the Telegram summary actually arrives. On failure, diagnose (Telegram config, daemon not running, cron syntax, prompt shape) and fix before exiting. Report the schedule id, cron, notifyOn, daemon/service status, and the next scheduled run.

Changes

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.

  1. 8d ago First seen · 20 lines · 44 tokens per session scan A 93380f58316e

Subscribe to this mod's changes

automate is a skill published in the GitHub repository griffinwork40/agent-afk (53 stars, last pushed today), licensed Apache-2.0. It adds 44 tokens to every session and 593 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.

Related

Other skills, from other repositories