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/Jkudjo/oh-my-cursorWrote 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/jkudjo/oh-my-cursor/chaos)<a href="https://agentmods.dev/rules/jkudjo/oh-my-cursor/chaos"><img src="https://agentmods.dev/badge/rules/jkudjo/oh-my-cursor/chaos/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/jkudjo/oh-my-cursor/chaos"><img src="https://agentmods.dev/badge/rules/jkudjo/oh-my-cursor/chaos.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 | $0.00014 | $0.00769 |
| Opus 5.5 | $0.00006 | $0.00308 |
| Sonnet 5.5 | $0.00003 | $0.00154 |
| Haiku 4.5 | $0.00001 | $0.00077 |
Grade A, and why
chaos 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@chaos
Trigger: After implementing a feature, before shipping. Tests resilience, not just correctness.
What it tests
Correctness testing asks: "does it work under normal conditions?" Chaos testing asks: "does it degrade gracefully under hostile conditions?"
Protocol
- Load the implementation (from approved plan or recent changes).
- For each failure scenario below: mentally or actually inject the failure and trace what happens.
Dependency failures
- Service unavailable: external API returns 503 — does the app retry? fail gracefully? surface a useful error?
- Intermittent failures: dependency fails 30% of requests — does state corrupt? does partial success cause inconsistency?
- Slow dependency: upstream takes 10s instead of 100ms — does it timeout properly? does it block a thread pool?
- Wrong response shape: dependency returns unexpected schema — does it crash or handle gracefully?
Data failures
- Null/empty inputs: pass null, "", [], {} to every public interface — what breaks?
- Boundary values: max int, negative numbers, very long strings, special characters, unicode
- Corrupt state: what if the DB has partial write from a previous failed transaction?
- Stale cache: cache returns old data while DB has new — is this handled?
Infrastructure failures
- Redis unavailable: does the app fall back or crash?
- DB connection pool exhausted: does it queue? fail fast? surface a clear error?
- Network partition: partial network failure between services — can state become inconsistent?
- Disk full: what happens to logging, temp files, uploads?
Concurrency failures
- Race condition: two requests modify the same resource simultaneously — is there a lock?
- Duplicate request: same request sent twice (retry, double-click) — is it idempotent?
- Out-of-order events: message queue delivers events out of sequence — does ordering matter?
Security failures
- Auth bypass attempts: what if the auth token is expired? forged? from wrong tenant?
- Privilege escalation: what if a low-privilege user calls a high-privilege endpoint?
- Input injection: SQL, HTML, command injection in every user-controlled field
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 · 81 lines · 14 tokens per session scan A f160ad44272b
chaos is a cursor rule published in the GitHub repository Jkudjo/oh-my-cursor (1 stars, last pushed 6mo ago), licensed MIT. It adds 14 tokens to every session and 769 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
minimax-m3-verification
Extended M3 verification playbook: proof selection, multimodal-grounded checks, shell checks, browser checks, and recovery loops.
bug-fix-tdd-guard
A rule for fixing software bugs with test-driven development, or TDD: first reproduce the bug, then write a test that fails, then make the smallest code change that passes it, and finally run the full checks.
refactoring
Refactoring: systematic approach, extract/inline, guard clauses, early returns.
performance
Performance: profiling-first optimization, caching, bottleneck patterns.
jest
Jest: describe/it, matchers, mocking, async testing.
testing
Testing: test design, mocking strategy, coverage philosophy.