Borrowing it
Nothing to install: this file belongs to mrzeszowski/claude-code-keep-alive. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mrzeszowski/claude-code-keep-alive/main/CLAUDE.mdgit clone --depth 1 https://github.com/mrzeszowski/claude-code-keep-aliveWrote 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/instructions/mrzeszowski/claude-code-keep-alive/claude-md)<a href="https://agentmods.dev/instructions/mrzeszowski/claude-code-keep-alive/claude-md"><img src="https://agentmods.dev/badge/instructions/mrzeszowski/claude-code-keep-alive/claude-md/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/instructions/mrzeszowski/claude-code-keep-alive/claude-md"><img src="https://agentmods.dev/badge/instructions/mrzeszowski/claude-code-keep-alive/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01307 | $0.01307 |
| Opus 5.5 | $0.00523 | $0.00523 |
| Sonnet 5.5 | $0.00261 | $0.00261 |
| Haiku 4.5 | $0.00131 | $0.00131 |
Grade A, and why
claude-code-keep-alive CLAUDE.md 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 1mo 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Repository status: v0.1.0 ready
Everything from §5 of the design spec is built and CI is green. Working branch is feat/v0.1.0 (merges to main for release). Design spec: docs/superpowers/specs/2026-05-17-claude-code-keep-alive-design.md.
Lint and test commands:
- Lint:
shellcheck -s sh bin/keep-alive(must be clean) - Tests:
bats tests/— 28 tests, pass on macOS and Ubuntu
What the plugin does
A Claude Code plugin that prevents the user's machine from sleeping during a session. It ports the user-facing surface of GitHub Copilot CLI's /keep-alive (subcommands on, off, busy, duration), namespaced as /keep-alive:on, /keep-alive:off, /keep-alive:busy, /keep-alive:status. Spec §1–3.
Architecture (the non-obvious parts)
Three pieces, and the interactions between them matter:
- Slash command files are intentionally minimal — frontmatter + one line telling Claude to run
keep-alive <verb> $ARGUMENTSvia the Bash tool and print stdout/stderr verbatim.allowed-toolsis locked to["Bash"]to prevent the LLM from interpreting the command. Don't add logic here. bin/keep-aliveis a POSIX-sh script (target ~150 lines). All real work — argument parsing, platform detection, state, inhibitor lifecycle — lives here. Added to the Bash tool'sPATHwhile the plugin is enabled.hooks/hooks.jsonregistersUserPromptSubmitandStophooks that invokekeep-alive --busy-event=start|stopin the background. They fire in every Claude Code session whenever the plugin is enabled, not only when the user invoked/keep-alive. They are no-ops unless the state file saysmode=busy. This is what makesbusymode work without polling.
Concretely, "no-op unless mode=busy" is a load-bearing invariant: if you ever change the hooks to do work unconditionally, you'll add a flock + JSON write to every prompt across every session for every user.
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.
- 1mo ago First seen · 60 lines · 1,307 tokens per session scan A 0c1f4a8b7a42
claude-code-keep-alive CLAUDE.md is an instructions file published in the GitHub repository mrzeszowski/claude-code-keep-alive (2 stars, last pushed 4mo ago), licensed MIT. It adds 1,307 tokens to every session, about $0.0052 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.