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/jimmypaolini/codebase/stay-awakenpx skills add JimmyPaolini/codebase --skill stay-awakegit clone --depth 1 https://github.com/JimmyPaolini/codebaseWrote 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/jimmypaolini/codebase/stay-awake)<a href="https://agentmods.dev/skills/jimmypaolini/codebase/stay-awake"><img src="https://agentmods.dev/badge/skills/jimmypaolini/codebase/stay-awake.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 | $0.00066 | $0.01306 |
| Opus 5 | $0.00033 | $0.00653 |
| Sonnet 5 | $0.00013 | $0.00261 |
| Haiku 4.5 | $0.00007 | $0.00131 |
Grade A, and why
stay-awake 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 4d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stay Awake
Overview
Keep macOS awake during agent work using caffeinate with a bounded lifecycle.
Prefer process-coupled assertions, then timeout-based assertions, and only use unbounded assertions with explicit cleanup.
GitHub Copilot CLI runs through shell-backed sessions and tool execution. In practice, the most reliable wake assertion target is the shell or concrete command process that will own the long-running work, not an abstract "agent" process. If the work is started from a shell, capture that shell's PID with $$; if it is started from a wrapper script or a specific child process, use that process ID instead.
When to Use
Use this skill when:
- The session may run long enough for idle sleep to interrupt work
- You are running long tests, builds, or debugging loops on macOS
- You need predictable wake-lock cleanup at session end
Do not use this skill on non-macOS systems.
Decision Order
- Attach to the agent process when possible (best)
- Use a timeout when process attachment is not possible
- Use bare
caffeinateonly as fallback, then always cancel at session end
Quick Reference
| Situation | Command | Cleanup behavior |
|---|---|---|
| Agent process ID is known | caffeinate -i -w <process_id> |
Stops automatically when process exits |
| Duration is known | caffeinate -i -t <seconds> |
Stops automatically at timeout |
| No PID and no duration | caffeinate -i |
Must be manually stopped |
| Long single command | caffeinate -i <command> [args...] |
Stops when wrapped command exits |
Workflow
1) Prefer a process-coupled wake lock
If the shell or long-running command process ID is available, tie the assertion to that process:
caffeinate -i -w <process_id>
If the work is started from a shell, the current shell's process ID can be read directly with $$ and used immediately:
agent_process_id=$$
caffeinate -i -w "$agent_process_id"
This is the safest default because wakefulness ends with the process that owns the long-running work. If the agent is not running inside a shell, if the chosen process exits immediately, or if the work is being driven by a wrapper process instead of a shell, prefer a timeout or a fallback caffeinate -i with cleanup instead.
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.
- 4d ago First seen · 131 lines · 66 tokens per session scan A b12bfa44f130
stay-awake is a skill published in the GitHub repository JimmyPaolini/codebase (0 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 1,306 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 2026-09-01.
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.