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/kok-o/koko-contextos-agentsWrote 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/kok-o/koko-contextos-agents/node)<a href="https://agentmods.dev/rules/kok-o/koko-contextos-agents/node"><img src="https://agentmods.dev/badge/rules/kok-o/koko-contextos-agents/node/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/kok-o/koko-contextos-agents/node"><img src="https://agentmods.dev/badge/rules/kok-o/koko-contextos-agents/node.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 | $0.00000 | $0.01489 |
| Opus 5.5 | $0.00000 | $0.00596 |
| Sonnet 5.5 | $0.00000 | $0.00298 |
| Haiku 4.5 | $0.00000 | $0.00149 |
Grade A, and why
node 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Node.js
Node.js
Overview
A brief summary of what the skill does and its core philosophy.
When to Use
Context for when this skill is applicable.
Negative Constraints (What NOT to Do)
- NEVER execute synchronous filesystem/crypto calls in request handlers (
fs.readFileSync): Always use async promises (fs.promises.*) to avoid blocking the event loop. - NEVER leave uncaught promise rejections: Every async route must use
express-async-errorsor wrap operations in try/catch callingnext(err). - NEVER buffer large files/payloads entirely in memory (
fs.readFile): Always use Streams or Pipelines (stream.pipeline) for processing large files. - NEVER store in-memory session or user state on a single process instance: Use Redis or an external state store to allow multi-instance scaling.
- NEVER ignore
SIGTERM/SIGINTshutdown signals: Always implement graceful shutdown to close open DB pools and drain active HTTP connections.
Rules & Patterns
Architecture
- Layered architecture: Routes → Controllers → Services → Repositories
- Dependency injection — don't import dependencies directly in services
- Config from environment — never hardcode secrets, use env variables
- Graceful shutdown — handle SIGTERM, close connections, drain requests
Error Handling
- Never swallow errors — always handle or re-throw
- Custom error classes — extend Error with HTTP status codes
- Global error handler — catch unhandled rejections and uncaught exceptions
- Structured logging — JSON logs with request ID, timestamp, level
class AppError extends Error {
constructor(
public message: string,
public statusCode: number = 500,
public code: string = 'INTERNAL_ERROR'
) {
super(message);
this.name = 'AppError';
}
}
API Design
- RESTful conventions — GET (read), POST (create), PUT (full update), PATCH (partial), DELETE
- Consistent response format —
{ data, error, pagination } - Validation at the edge — validate request body/params with Zod or Joi
- Rate limiting — protect against abuse
- CORS — configure explicitly, never use
*in production
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 · 213 lines · 0 tokens per session scan A 11aa5c8532d7
node is a cursor rule published in the GitHub repository kok-o/koko-contextos-agents (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,489 tokens. 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
hatch3r-dotnet-patterns
.NET 10 + C# 14 conventions covering minimal APIs, nullable reference types, async/await, Entity Framework Core, dependency injection, structured logging, and xUnit testing.
hatch3r-go-patterns
Go 1.23+ conventions covering modules, error wrapping, context propagation, generics, testing with table-driven tests, and the standard library net/http + log/slog.
hatch3r-ruby-rails-patterns
Ruby 3.3+ and Rails 8.x conventions covering Hotwire (Turbo + Stimulus), ActiveRecord patterns, Sidekiq jobs, RSpec testing, RuboCop / Standard, and YJIT performance.
best-practices
FastAPI Best Practices - enforces current best practices when working with FastAPI code.
symfony-6.4-best-practices
Cursor rule "symfony-6.4-best-practices" from fiddike/Cursor-Rules-MDC, covering symfony 6.4 best practices and symfony 6.4 best practices.
python_tests
We use the unit tests to cover internal behavior that can work without the web / backend counterpart. We aim for 95%+ unit test coverage of our Python code in lib/streamlit.