keep-alive

keep-alive is a skill for Claude Code from ttxttx1111/sts2-llm. It costs 26 tokens per session (595 once invoked), scanned A, original, MIT.

A utility for keeping a computer awake while an agent continues an assigned workflow. It also tracks progress and stops at commit checkpoints that need user approval.

In plain words
What is it for?
Continuing the current workflow or a specified task, preventing sleep on macOS, Windows, or Linux, tracking progress, and stopping safely before commits.
Why use it?
It prevents the computer from sleeping and interrupting long-running autonomous work when the user steps away.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the TodoWrite tool.

Good fit Continuing the current workflow or a specified task, preventing sleep on macOS…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ttxttx1111/sts2-llm/keep-alive
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 ttxttx1111/sts2-llm --skill keep-alive
Clone the repo
git clone --depth 1 https://github.com/ttxttx1111/sts2-llm

Made for: Claude Code.

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 keep-alive

README.md
[![agentmods](https://agentmods.dev/badge/skills/ttxttx1111/sts2-llm/keep-alive.svg)](https://agentmods.dev/skills/ttxttx1111/sts2-llm/keep-alive)
Your own site
<a href="https://agentmods.dev/skills/ttxttx1111/sts2-llm/keep-alive"><img src="https://agentmods.dev/badge/skills/ttxttx1111/sts2-llm/keep-alive.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 595 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.
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 $0.00026 $0.00595
Opus 5 $0.00013 $0.00298
Sonnet 5 $0.00005 $0.00119
Haiku 4.5 $0.00003 $0.00060

Measured 7d ago against content hash 2f94214fe0a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

keep-alive 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 7d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (prevent-sleep.ps1), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

deprecated/1/llm-slay-the-spire/.claude/skills/keep-alive/SKILL.md · 89 lines

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.

Keep-Alive Skill

Enable autonomous work mode while preventing computer from sleeping.

What This Does

  1. Prevents sleep: Starts a background process to keep the computer awake
  2. Autonomous work: Continues executing the specified task or current workflow
  3. Progress tracking: Updates todos and logs progress
  4. Safe stopping: Stops at commit checkpoints (requires user approval per safeguard)

Usage

/keep-alive continue          # Continue current workflow (e.g., next phase)
/keep-alive "implement X"     # Work on specific task

Process

1. Start Sleep Prevention

Windows:

# Start caffeine mode (prevents sleep until killed)
powershell -Command "& {[System.Windows.Forms.Application]::SetSuspendState('Suspend', $false, $false); while($true){[System.Windows.Forms.SendKeys]::SendWait('{F15}'); Start-Sleep -Seconds 60}}" &

Mac/Linux:

caffeinate -d -i -s &

2. Define Work Scope

If argument is "continue":

  • Check current phase status
  • Identify next incomplete phase
  • Queue: implementers → unified verifier → STOP (await user for commit)

If argument is a task description:

  • Create todo list for the task
  • Spawn appropriate agents
  • Track progress

3. Work Loop

while work_remaining:
    1. Spawn implementers for current phase (parallel)
    2. Wait for completion
    3. Spawn unified verifier
    4. If SHIP IT:
       - Log "Ready for commit - awaiting user approval"
       - STOP (do not commit without user)
    5. If FAIL:
       - Spawn fix agents
       - Loop back to verification

4. Stopping Points (MUST STOP)

  • Before any git commit (safeguard requires user approval)
  • On verification failure that needs human judgment
  • On ambiguous requirements
  • On errors that can't be auto-resolved

Important Constraints

  • NEVER commit without user approval - stop and wait
  • NEVER make architectural decisions - stop and ask
  • Log progress clearly so user can catch up when they return
  • Prefer stopping early over making wrong assumptions

Read the full file on GitHub · 89 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 89 lines · 26 tokens per session scan A 2f94214fe0a3

Subscribe to this mod's changes

keep-alive is a skill published in the GitHub repository ttxttx1111/sts2-llm (41 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 595 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.

Related

Other skills, from other repositories

self-awareness-review

Reviews a given week of your OWN Teams meetings, chats, and sent emails to surface moments where you may have misread social signals or come across as passive-aggressive, curt, sarcastic, or dismissive — returning the exact quote, how it likely landed, and a kinder rewrite. Private self-reflection coaching for the…

pnp/copilot-prompts · 202 tokens

weekly-pacing

Analyzes the user's upcoming or current work week using Work IQ signals (calendar, email volume, and semantic themes) and produces a visualized pacing report — classifying each day as Rest, Light, Focus, or Heavy based on meeting load, back-to-back density, communication volume, and available deep-work time. Designed…

pnp/copilot-prompts · 267 tokens

042-planning-openspec

Use when creating or updating OpenSpec artifacts from an issue, plan, approved design, ADRs, existing OpenSpec, or a valid combination. The workflow assesses reviewable scope, records source authority and derivation, handles conflicts, and prevents silent synchronization. Triggers include Create OpenSpec from an…

jabrena/plinth · 94 tokens

043-planning-github-issues

Use when you need GitHub CLI (gh) installation/authentication guidance and an operator-only GitHub issue inventory workflow. The agent does not ingest GitHub issue, milestone, body, comment, title, label, or summary text; requirements analysis must use repository-owned planning artifacts, with issue numbers only for…

jabrena/plinth · 113 tokens

044-planning-jira

Use when you need Jira CLI (jira) installation/authentication guidance and a maintainer-authored Jira issue inventory workflow. The agent does not ingest raw Jira issue or JQL output directly; it asks the Jira project maintainer/operator to author sanitized issue summaries before analysis or @014-agile-user-story…

jabrena/plinth · 100 tokens

microsoft-build

Your companion for Microsoft Build 2026. Helps you find sessions relevant to your project, discover what's new for your tech stack, scaffold projects from sessions, and plan your event schedule. Activate when users mention sessions, schedule, what's new, Build, Ignite, AI Tour, Microsoft event, conference, or…

microsoft/Build-CLI · 109 tokens