210-go

210-go is a cursor rule for Cursor from d-padmanabhan/agent-engineering-handbook. It costs 19 tokens per session (22,462 once invoked), scanned A, original, MIT.

A set of guidance for writing and reviewing Go, a programming language commonly used for services and systems software. It covers secure, idiomatic, maintainable code and performance checks based on evidence.

In plain words
What is it for?
Use it when generating or reviewing Go code, especially code involving concurrency, APIs, security, testing, or performance.
Why use it?
It sets checks for formatting, testing, static analysis, race detection, and vulnerability scanning, helping catch defects and unsafe code early.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc). Also seen: positional $N argument.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is cmd = "go build -o ./tmp/app ./cmd/server".

Good fit Use it when generating or reviewing Go code, especially code involving concurrency, APIs, security, testing, or performance.

Compare 6 cursor rules from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/d-padmanabhan/agent-engineering-handbook
agentmods
npx agentmods add rules/d-padmanabhan/agent-engineering-handbook/210-go

Made for: Cursor.

Wrote 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.

agentmods badge for 210-go

README.md
[![agentmods](https://agentmods.dev/badge/rules/d-padmanabhan/agent-engineering-handbook/210-go/github.svg)](https://agentmods.dev/rules/d-padmanabhan/agent-engineering-handbook/210-go)
Your own site
<a href="https://agentmods.dev/rules/d-padmanabhan/agent-engineering-handbook/210-go"><img src="https://agentmods.dev/badge/rules/d-padmanabhan/agent-engineering-handbook/210-go/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.

agentmods 80×15 button for 210-go

Your own site · 80×15
<a href="https://agentmods.dev/rules/d-padmanabhan/agent-engineering-handbook/210-go"><img src="https://agentmods.dev/badge/rules/d-padmanabhan/agent-engineering-handbook/210-go.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 22,462 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00019 $0.22462
Opus 5.5 $0.00008 $0.08985
Sonnet 5.5 $0.00004 $0.04492
Haiku 4.5 $0.00002 $0.02246

Measured 1mo ago against content hash ad12e8cc10f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

210-go 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.

rules/210-go.mdc · 3,496 lines

How it starts

The opening of the file, as written. The whole thing — 3,496 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Go Engineering Ruleset - (December 2025)

Audience: engineers writing and reviewing Go code Goal: secure, idiomatic, efficient, and highly maintainable Go - without over-engineering

Core Philosophy: Correctness & Safety Simplicity & Maintainability Evidence-Based Performance

  • Formatting: gofmt -s (required); tab indentation (Go standard); no line length limit.
  • Linting: Run go vet, staticcheck, golangci-lint, and govulncheck. Code must pass go test -race.

Essential Reading:

  • Go Proverbs - Simple, poetic, pithy principles from Rob Pike
  • Effective Go - Official idiomatic Go guide (note: written in 2009, still valuable for language idioms)

Go Proverbs (Core Principles)

These proverbs from Rob Pike guide idiomatic Go:

  • "Don't communicate by sharing memory, share memory by communicating" - Use channels for coordination
  • "Concurrency is not parallelism" - Concurrency is about structure, parallelism is about execution
  • "Channels orchestrate; mutexes serialize" - Use channels for coordination, mutexes for mutual exclusion
  • "The bigger the interface, the weaker the abstraction" - Keep interfaces small and focused
  • "Make the zero value useful" - Types should work correctly when zero-initialized
  • "interface{} says nothing" - Prefer specific types; use generics or type assertions when needed
  • "Gofmt's style is no one's favorite, yet gofmt is everyone's favorite" - Always use gofmt
  • "A little copying is better than a little dependency" - Prefer copying small code over adding dependencies
  • "Clear is better than clever" - Readability over cleverness
  • "Reflection is never clear" - Avoid reflection unless necessary
  • "Errors are values" - Handle errors explicitly; don't ignore them
  • "Don't just check errors, handle them gracefully" - Provide context and recovery paths
  • "Don't panic" - Use errors, not panics, for normal error handling

Read the full file on GitHub · 3,496 lines

Changes

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.

  1. 1mo ago Changed · +20 lines ad12e8cc10f0
  2. 1mo ago Changed · +5 lines 406c843392b5
  3. 2mo ago First seen · 3,471 lines · 19 tokens per session scan A 3b6b95fa491e

Subscribe to this mod's changes

210-go is a cursor rule published in the GitHub repository d-padmanabhan/agent-engineering-handbook (20 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 22,462 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 2026-08-30.