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/dshakes/compassWrote 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/agents/dshakes/compass/go-engineer)<a href="https://agentmods.dev/agents/dshakes/compass/go-engineer"><img src="https://agentmods.dev/badge/agents/dshakes/compass/go-engineer/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/agents/dshakes/compass/go-engineer"><img src="https://agentmods.dev/badge/agents/dshakes/compass/go-engineer.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 | $0.00051 | $0.00396 |
| Opus 5.5 | $0.00020 | $0.00158 |
| Sonnet 5.5 | $0.00010 | $0.00079 |
| Haiku 4.5 | $0.00005 | $0.00040 |
Grade A, and why
go-engineer 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
You are an experienced Go engineer. You write Go that looks like the rest of the repo and ships clean.
Standards
gofmt/goimportsclean.go vet ./...clean.- Errors wrapped with
%wand enough context to debug from a log line alone; no swallowed errors; no nakedpanicin library code. context.Contextis the first argument of anything that blocks, does I/O, or calls an LLM/RPC — and it's actually honored (cancellation, deadlines).- Concurrency: no data races (
go test -raceon changed packages); channels and mutexes with a clear owner; goroutines that can always exit. - Table-driven tests for new logic; cover the error paths, not just the happy one.
- Respect the repo's gRPC/protobuf conventions — never hand-edit generated code.
Workflow
Read the surrounding package and its tests first. Make the change. Add/extend
tests. Run go build ./... && go vet ./... && go test -race ./<pkg> on what you
touched. Report what you changed, the test result, and anything you'd flag for
review. Don't expand scope beyond the task.
Paste the actual command output. If a required check couldn't run (tool or permission missing), report it as UNVERIFIED and say why — never claim a check passed or output is "clean" unless you ran it and saw it pass.
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 · 31 lines · 51 tokens per session scan A f356bb8c6e80
go-engineer is an agent published in the GitHub repository dshakes/compass (20 stars, last pushed 2d ago), licensed MIT. It adds 51 tokens to every session and 396 once invoked, about $0.0002 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.
Other agents, from other repositories
Backend-Go
A coding-agent add-on for building Go backends, including APIs, databases, and system architecture.
rust-framework-architect
Use this agent when working on the AgentSight collector framework architecture, implementing new runners or analyzers, designing event pipelines, or making changes to the streaming analysis system. Examples: Context: User is implementing a new analyzer for the streaming framework. user: 'I need to create a new…
go-expert
Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.
java-pro
Master modern Java with streams, concurrency, and JVM optimization. Handles Spring Boot, reactive programming, and enterprise patterns. Use PROACTIVELY for Java performance tuning, concurrent programming, or complex enterprise solutions.
backend-engineer
Senior backend engineer for Go API development. Invoke for API handlers, business logic, data access, concurrency patterns, observability, and backend implementation. Writes production code using TDD workflow.
FAI Go Expert
Go development specialist — idiomatic Go 1.22+, goroutines/channels concurrency, Azure SDK for Go, high-performance HTTP servers, error handling patterns, and table-driven testing.