unsnoozeSAFE
Automatically resume Claude Code, Codex CLI, Grok, Qwen Code, Kimi CLI, OpenCode, and Antigravity sessions when 5-hour or weekly usage limits reset—across tmux, Zellij, VS Code, and desktop apps.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://github.com/saaranshM/unsnooze/actions/workflows/ci.yml) [](https://www.npmjs.com/package/unsnooze) [](package.json) [](LICENSE)
Automatically resume every limit-stopped AI coding session when its usage limit resets.
Website · Documentation · Changelog · Feedback
Claude Code · Codex CLI · Grok · Qwen · Kimi · OpenCode · Antigravity · Cursor — when they hit the 5-hour or weekly usage limit ("You've hit your usage limit"), your session just... stops. unsnooze auto-resumes them: it tracks every limit-stopped session across all your projects and wakes each one up the moment the usage limit resets — in tmux, Zellij, herdr or cmux, and on macOS, Linux and Windows, with or without a terminal multiplexer.
npm install -g unsnooze && unsnooze setup
Why unsnooze
Overnight and long-running agent work dies at the 5-hour / weekly limit, and every existing tool solves only a slice of it:
5011822f2f0fOBSERVED · 2026-10-12Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add unsnooze-website --env NEXT_PUBLIC_SUPABASE_ANON_KEY=${NEXT_PUBLIC_SUPABASE_ANON_KEY} --env SECRET_API_KEY=${SECRET_API_KEY} --env SSH_ASKPASS=${SSH_ASKPASS} --env SSH_ASKPASS_PROMPT=${SSH_ASKPASS_PROMPT} -- npx -y unsnooze-website{
"mcpServers": {
"unsnooze-website": {
"command": "npx",
"args": [
"-y",
"unsnooze-website"
],
"env": {
"NEXT_PUBLIC_SUPABASE_ANON_KEY": "${NEXT_PUBLIC_SUPABASE_ANON_KEY}",
"SECRET_API_KEY": "${SECRET_API_KEY}",
"SSH_ASKPASS": "${SSH_ASKPASS}",
"SSH_ASKPASS_PROMPT": "${SSH_ASKPASS_PROMPT}"
}
}
}
}Exposed tools (1)
1 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
unsnooze | read | Wakes every limit-stopped AI coding session the moment the usage limit resets. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (5 observation(s))
- Network
- none-observed
- Shell
- declared (5 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (15)
const direct = newestChatIn(join(chats, createHash('md5').update(cwd).digest('hex')), cwd);return join(kimiDir, 'sessions', createHash('md5').update(cwd).digest('hex'));return { head, dirtyHash: createHash('sha1').update(dirty).digest('hex') };const project = hash ?? createHash('md5').update(cwd).digest('hex');const bare = join(DIR, 'chats', createHash('md5').update('/tmp/schema-drift').digest('hex'), 'chat-x');unsnooze installed; transport is your existing <C>~/.ssh/config</C>, keys, and
doubles as the destination (so any <C>~/.ssh/config</C> alias works as-is).
<C>authorized_keys</C> — that key can never open a shell.</li>
import { attachHintRemote } from '../../fleet.js';import { queueAdd, queueRemove } from '../../prompt-queue.js';import { listAgents } from '../../agents/index.js';import { getConfig } from '../../settings.js';import { readHosts, remoteQueueAdd } from '../../fleet.js';@clack/prompts, ink, picocolors, react
marked, next, ogl, react, react-dom
Gates applied: no_behavioural_pass.
5011822f2f0ffull audit observations/trust-audit/mcp-server/saaranshm__unsnooze.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-12 | 5011822f2f0f | SAFE | B | 89 | first audit |
Questions
What is the unsnooze MCP server?
Automatically resume Claude Code, Codex CLI, Grok, Qwen Code, Kimi CLI, OpenCode, and Antigravity sessions when 5-hour or weekly usage limits reset—across tmux, Zellij, VS Code, and desktop apps.
What tools does unsnooze expose?
1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is unsnooze safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does unsnooze need?
It reads NEXT_PUBLIC_SUPABASE_ANON_KEY, SECRET_API_KEY, SSH_ASKPASS, SSH_ASKPASS_PROMPT, SSH_ASKPASS_REQUIRE, UNSNOOZE_ASKPASS_HOST, UNSNOOZE_CONTEXT_GUARD_TOKENS and UNSNOOZE_NTFY_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How current is this page?
The grade is for one exact copy of the source (5011822f2f0f), read on 2026-10-12. The repository is watched and re-audited when it changes.