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 griffinwork40/agent-afk --skill automategit clone --depth 1 https://github.com/griffinwork40/agent-afkWrote 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/griffinwork40/agent-afk/automate)<a href="https://agentmods.dev/skills/griffinwork40/agent-afk/automate"><img src="https://agentmods.dev/badge/skills/griffinwork40/agent-afk/automate/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/griffinwork40/agent-afk/automate"><img src="https://agentmods.dev/badge/skills/griffinwork40/agent-afk/automate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
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.
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 | $0.00044 | $0.01438 |
| Opus 5.5 | $0.00018 | $0.00575 |
| Sonnet 5.5 | $0.00009 | $0.00288 |
| Haiku 4.5 | $0.00004 | $0.00144 |
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 16d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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.
Input routing
The argument is one of three forms:
- Task description / directory path — proceed directly to the Scout + Prompt designer wave below.
- Session ID — run the fit-assessment flow first (Waves 0–1 + authorization gate) to determine whether the session is automatable before building a schedule.
Session ID path: fit-assessment
Wave 0 — Signal extraction (orchestrator, synchronous)
Read the session facet with get_facet (pass fields: ["duration_minutes", "user_message_count"] so the goal and first prompt never enter the extraction) and the session's tool calls with read_witness (kinds: ["tool_call"]), then extract four flat signals:
duration— the facet'sduration_minutesuser_messages— the facet'suser_message_count. Do not count witness events for this: the trace records no user turns, and itsqueued_user_messageevents cover only messages typed mid-turn, so they undercount.llm_branch_steps— count of tool calls whose branch condition is model output rather than exit code (i.e., tool calls following a reasoning step that is not mechanically determined)command_sequence— ordered list of distinct bash/shell commands issued, with item count
Emit Artifact 1: duration=Xm, user_messages=N, llm_branch_steps=M, command_sequence=[cmd1, cmd2, …] (K distinct commands). This is the only input forwarded to Wave 1 — the session ID, original user message, and any rationale are withheld.
Wave 1 — Automation-fit probe (isolated sub-agent)
Receives Artifact 1 only. Denied: session ID, original user message, any framing about why the task was run manually. Denied write tools.
Applies the five-point rubric:
| Criterion | Points |
|---|---|
duration ≤ 10m |
+1 |
user_messages ≤ 2 |
+1 |
llm_branch_steps == 0 |
+1 |
| Command sequence is idempotent with no destructive commands lacking a guard | +1 |
| No step requires live user judgment | +1 |
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.
- 16d ago Changed · +69 lines 95645aa07d28
- 1mo ago First seen · 20 lines · 44 tokens per session scan A 93380f58316e
automate is a skill published in the GitHub repository griffinwork40/agent-afk (61 stars, last pushed today), licensed Apache-2.0. It adds 44 tokens to every session and 1,438 once invoked, about $0.0002 per session on Opus 5.5. 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
hunk-launch-video
Produces Hunk videos by driving the real TUI headlessly in a PTY, compositing captioned 1080p frames in Chromium, and encoding with ffmpeg. Use for feature demos, workflow explainers, announcements, launch videos, and full-release roundups.
gog-workspace
Use the gog CLI for Google Workspace tasks across Gmail, Calendar, Drive, Docs, Sheets, Contacts, and related services. Use when the user asks to check email, search Gmail, inspect calendar events, find Drive files, read Docs or Sheets, or manage Google Workspace data through gog.
apple-calendar
Read macOS Calendar events via the icalBuddy CLI and create events via AppleScript (osascript). Use to check the user's calendar, agenda, upcoming events, or add an event on macOS.
apple-reminders
Manage Apple Reminders via the remindctl CLI on macOS — list, add, complete, delete, manage lists.
apple-notes
Manage Apple Notes via the memo CLI on macOS — create, view, search, edit, export.
amq-spec
Use two agents to research a design independently and converge on one specification through AMQ. Trigger for collaborative design or messages labeled workflow:spec; use amq-cli for ordinary coordination.