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.
git clone --depth 1 https://github.com/cdbattags/aiWrote 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/rules/cdbattags/ai/no-sleep-process-monitoring)<a href="https://agentmods.dev/rules/cdbattags/ai/no-sleep-process-monitoring"><img src="https://agentmods.dev/badge/rules/cdbattags/ai/no-sleep-process-monitoring/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/rules/cdbattags/ai/no-sleep-process-monitoring"><img src="https://agentmods.dev/badge/rules/cdbattags/ai/no-sleep-process-monitoring.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 | $0.00318 | $0.00318 |
| Opus 5 | $0.00159 | $0.00159 |
| Sonnet 5 | $0.00064 | $0.00064 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
no-sleep-process-monitoring scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**ABSOLUTE RULE: Never use `sleep`, polling loops (`while ! curl; do sleep; done`), or `for` loops with delays in the Cursor Shell tool.** What it actually says
No Sleep Commands - Use Shell Tool's Built-In Waiting
ABSOLUTE RULE: Never use sleep, polling loops (while ! curl; do sleep; done), or for loops with delays in the Cursor Shell tool.
The Shell tool already has block_until_ms for waiting and terminal files for monitoring. You never need to build your own waiting logic.
Quick Reference
| Scenario | Pattern |
|---|---|
| Terminating command (build, seed, test) | Set block_until_ms > expected runtime |
| Dev server / watcher | block_until_ms: 0, then Read terminal file for readiness |
| Check if background command finished | Read terminal file, look for exit_code footer |
| Verify server is up | Read terminal file for "ready in" / "listening" marker |
Before Using sleep — STOP
If you are about to type sleep in a shell command, do not. Instead:
- For commands that finish: increase
block_until_ms - For servers: read the terminal file for output markers
- For checking process state: read the terminal file header for
running_for_secondsorexit_code
Detailed Skill
For full patterns and examples, read: ~/.cursor/skills/process-monitoring/SKILL.md
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.
- 12d ago First seen · 32 lines · 318 tokens per session scan A 1a0fa14ffa7b
no-sleep-process-monitoring is a cursor rule published in the GitHub repository cdbattags/ai (4 stars, last pushed 6mo ago), licensed MIT. It adds 318 tokens to every session, about $0.0016 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other cursor rules, from other repositories
core
The engineering contract for this repo lives in AGENTS.md (auto-loaded). Follow it. This rule only adds Cursor-specific behavior so the contract is not duplicated token-for-token on every request.
frontend
UI/component conventions. Apply when building or changing user-facing frontend code.
debugging
Debugging discipline. Apply when investigating a bug, test failure, or unexpected behavior.
no-auto-commit
Never commit or push without explicit user instruction.
tailwind-v4-migration
Tailwind CSS v3-to-v4 migration rules. Activated when the agent determines migration work is needed. Covers step-by-step upgrade process, common pitfalls, and automated migration tooling.
tailwind-v4-anti-patterns
Tailwind CSS v4 anti-pattern detection. Prevents the most common AI-generated mistakes: version mixing, deprecated config patterns, and removed utilities.