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/tjamet/har-mcpWrote 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/tjamet/har-mcp/go)<a href="https://agentmods.dev/rules/tjamet/har-mcp/go"><img src="https://agentmods.dev/badge/rules/tjamet/har-mcp/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.
<a href="https://agentmods.dev/rules/tjamet/har-mcp/go"><img src="https://agentmods.dev/badge/rules/tjamet/har-mcp/go.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 | $0.00486 |
| Opus 5.5 | $0.00000 | $0.00194 |
| Sonnet 5.5 | $0.00000 | $0.00097 |
| Haiku 4.5 | $0.00000 | $0.00049 |
Grade A, and why
go scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Go Development Rules for Cursor
Project Structure
- Use
cmd/${program}/main.gofor main applications - Use
pkg/**/*.gofor shared libraries and packages - Keep packages focused and cohesive
Build and Run Commands
- NO Make - use simple Go commands only
- Build:
go build ./cmd/har-mcp - Run:
go run ./cmd/har-mcp - Test:
go test ./... - Format:
go fmt ./... - Vet:
go vet ./... - Tidy dependencies:
go mod tidy
Code Style
- Follow standard Go formatting with
gofmt - Use standard Go naming conventions (PascalCase for exported, camelCase for unexported)
- Keep functions and methods small and focused
- Use meaningful variable and function names
- Avoid unnecessary else clauses when using early returns
Coding
- You should have access to a godoc tool. Use it as much as possible
- Don't guess interfaces. Use the tools that you have to doublecheck what you are doing is correct
Testing
- Use github.com/stretchr/testify for assertions
- NO table-driven tests - use test helpers instead
- Test file naming:
*_test.go - Test function naming:
TestFunctionName - Use
requirefor test setup that must succeed,assertfor actual test assertions - Create helper functions to reduce test duplication
- Test one thing per test function
Error Handling
- Always handle errors explicitly
- Use meaningful error messages
- Wrap errors with context using
fmt.Errorf("context: %w", err) - Return errors as the last return value
Dependencies
- Minimize external dependencies
- Use standard library when possible
- Pin dependency versions in go.mod
Comments
- Use godoc style comments for exported functions and types
- Comment explains WHY, not WHAT
- Keep comments concise and up-to-date
Performance
- Avoid premature optimization
- Profile before optimizing
- Use appropriate data structures
- Be mindful of memory allocations in hot paths
Concurrency
- Use channels for communication between goroutines
- Avoid shared mutable state
- Use context.Context for cancellation and timeouts
- Prefer composition over inheritance
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 · 68 lines · 486 tokens per session scan A fc21b49f9f33
go is a cursor rule published in the GitHub repository tjamet/har-mcp (27 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 486 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 2026-08-30.
Other cursor rules, from other repositories
go
Rules applied when working in Go files.
go-backend-scalability-cursorrules-prompt-file
Cursor rules for Go development with backend scalability.
go-servemux-rest-api-cursorrules-prompt-file
Cursor rules for Go development with ServeMux REST API integration.
go
Idiomatic Go rules. Explicit error handling, interface-based design, context-first concurrency.
go-temporal-dsl-prompt-file
Cursor rules for Go development with Temporal DSL integration.
go-backend-scalability
A set of coding and architecture rules for scalable Go backends. It covers databases, APIs, concurrency, performance, security, microservices, containers, monitoring, and deployment.