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/peiiii/nextclaw/automation-setupnpx skills add Peiiii/nextclaw --skill automation-setupgit clone --depth 1 https://github.com/Peiiii/nextclawWrote 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/peiiii/nextclaw/automation-setup)<a href="https://agentmods.dev/skills/peiiii/nextclaw/automation-setup"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/automation-setup.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 5.1 | $0.00026 | $0.00602 |
| Opus 5 | $0.00013 | $0.00301 |
| Sonnet 5 | $0.00005 | $0.00120 |
| Haiku 4.5 | $0.00003 | $0.00060 |
Grade A, and why
automation-setup 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Automation Setup
Use this skill when the user wants the assistant to:
- remind them later
- check something periodically
- continue an existing investigation on a schedule
- create a recurring follow-up tied to an existing session
- turn a repeated manual workflow into an automation
This skill is a thin planner on top of the cron tool. Do not implement a second scheduler. Do not refer to Heartbeat or HEARTBEAT.md.
Decision Rules
- If the task should continue an existing conversation or investigation, pass the target
sessionId. - If the task should use a dedicated background thread, omit
sessionIdand let cron use its owncron:<jobId>session. - If the schedule is one-time, use
at. - If the schedule is a true fixed interval, use
every. - If the schedule is a calendar pattern, use
cron.
Message Rules
Write the message as an executable instruction for the agent at run time.
- Good:
Check the release board, summarize blockers, and report only changes since the previous run. - Good:
Continue the existing debugging session, inspect the latest logs, and append the next concrete step. - Bad:
debug logs
If the user wants a periodic check of a file, include that file path directly in the message.
- Example:
Read docs/TODO.md, identify items due this week, and summarize anything blocked.
Session-Bound Follow-Up
When the user wants “continue this later” or “keep following up on this thread”, prefer:
cron(action="add", name="<short-name>", message="<runtime instruction>", every=<seconds>, sessionId="<existing-session-id>")
Examples
Recurring follow-up on the current investigation:
cron(action="add", name="investigation-follow-up", message="Continue the existing investigation, check for new evidence, and report only meaningful changes.", every=1800, sessionId="<session-id>")
Periodic file-based review without a special session:
cron(action="add", name="todo-review", message="Read docs/TODO.md, identify items that need attention, and summarize the highest-priority updates.", cron="0 9 * * *")
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 · 66 lines · 26 tokens per session scan A 0fa065768e9b
automation-setup is a skill published in the GitHub repository Peiiii/nextclaw (254 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 602 once invoked, about $0.0001 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
meeting-notes
Use when the user asks to capture, structure, or summarize meeting notes / call notes / 1:1 discussion / standup notes. Produces a standard template with attendees, agenda, decisions, action items (owner + deadline), and open questions.
ha-settings
Manage Hope Agent application settings through conversation. Use when the user wants to view or change any app configuration: theme, language, enhanced focus indicators, proxy, temperature, notifications, tool timeout, context compaction, automatic session titles, web search, GitHub issue reporting, memory, embedding…
setup
First-time setup for the Chief of Staff system. Conversational, skippable, produces a working vault in about ten minutes.
chief-of-staff
Personal Chief of Staff system for ADHD-ish operators. Vault-based, loop-driven, nervous-system-aware. Built and lived-in across daily sessions on real consulting, content, and long-running personal work.
start
Morning briefing. Reads vault state, delivers Must/Should/Could briefing, flags overdue waiting-for items.
sync
Mid-session checkpoint. Saves to memory, flags Command Center or To-Do drift, rotates session context.