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/KingEmma7/cursor-osWrote 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/kingemma7/cursor-os/debugging)<a href="https://agentmods.dev/rules/kingemma7/cursor-os/debugging"><img src="https://agentmods.dev/badge/rules/kingemma7/cursor-os/debugging/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/kingemma7/cursor-os/debugging"><img src="https://agentmods.dev/badge/rules/kingemma7/cursor-os/debugging.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 | $0.00017 | $0.00195 |
| Opus 5.5 | $0.00007 | $0.00078 |
| Sonnet 5.5 | $0.00003 | $0.00039 |
| Haiku 4.5 | $0.00002 | $0.00019 |
Grade A, and why
debugging 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.
What it actually says
Opt-in debugging discipline: find the root cause before changing code. For a structured walkthrough, use the debugging-loop skill.
- Reproduce first. Establish the exact steps and the expected-vs-actual behavior before forming a fix.
- Diagnose before editing. Read the failing path and form a hypothesis; don't guess-and-check by mutating code.
- Change the cause, not the symptom. Avoid masking errors with broad try/catch, retries, or silencing logs.
- Make the smallest fix that addresses the root cause. Keep unrelated cleanup out of the bugfix.
- Prove it. Add or run a test (or a concrete manual check) that fails before the fix and passes after.
- If the bug revealed a gap in project memory, note it in
docs/repo-memory.mdso it doesn't recur.
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 · 14 lines · 17 tokens per session scan A 48415f3ddd4d
debugging is a cursor rule published in the GitHub repository KingEmma7/cursor-os (2 stars, last pushed 20d ago), licensed MIT. It adds 17 tokens to every session and 195 once invoked, about $0.0001 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 cursor rules, from other repositories
project
Project conventions - canonical source is AGENTS.md.
ai-mcp-development
Rule Name: ai-mcp-development Description: Guidelines for developing and debugging MCP servers and tools. Filters.
performance
Performance: profiling-first optimization, caching, bottleneck patterns.
error-handling
Error handling: typed errors, boundaries, user messages.
logging
Logging: structured logs, levels, correlation.
vscode
VS Code: settings, extensions, workspace config.