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.
npx agentmods add rules/kingemma7/cursor-os/debugginggit clone --depth 1 https://github.com/KingEmma7/cursor-osWhat 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 | $0.00017 | $0.00195 |
| Opus 5 | $0.00009 | $0.00097 |
| Sonnet 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 yesterday.
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.
- yesterday 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. 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.
react
React component conventions.
decision-review
Decision review — audit thinking quality, not just code quality.
react
React component conventions.
docs-structure
Best practices for organizing the docs/ directory.
cadence-nft-standards
Comprehensive standards and best practices for developing Non-Fungible Tokens (NFTs) using Cadence. Ensures proper implementation of NonFungibleToken interfaces, MetadataViews integration for marketplace compatibility, secure resource handling patterns, and advanced modular architectures for complex NFTs with traits…