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.
npx agentmods add skills/oleghq/agentpack/build-go-stacknpx skills add OlegHQ/agentpack --skill build-go-stackgit clone --depth 1 https://github.com/OlegHQ/agentpackWrote 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/skills/oleghq/agentpack/build-go-stack)<a href="https://agentmods.dev/skills/oleghq/agentpack/build-go-stack"><img src="https://agentmods.dev/badge/skills/oleghq/agentpack/build-go-stack.svg" alt="Measured on agentmods" 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 | $0.00121 | $0.01555 |
| Opus 5 | $0.00060 | $0.00777 |
| Sonnet 5 | $0.00024 | $0.00311 |
| Haiku 4.5 | $0.00012 | $0.00155 |
Grade A, and why
build-go-stack 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 yesterday.
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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build Go Stack
Build an idiomatic Go backend around cmd/ and internal/. Keep repository instructions and the requested product architecture authoritative.
Start with discovery
- Inspect repository instructions,
go.mod, build tooling, package layout, and established conventions before editing. - Preserve compatible choices. Do not restructure unrelated code merely to match this skill.
- Read references/architecture.md before scaffolding, moving packages, selecting dependencies, or changing backend build composition.
- Read references/dependency-graph.md before adding component dependencies, service calls, repositories, or cross-component workflows.
- Read references/performance.md before changing Go tests, build targets, generation, CI caches, or developer feedback loops.
- Read references/configuration.md before adding configuration, environment variables, Vault, logging, startup, shutdown, or dependency construction.
- Read references/serialization.md before changing API types, JSON, database records, dynamic values, or layer transforms.
- Read references/errors.md before changing error handling, retries, HTTP responses, worker failures, cleanup, or logging.
- Read references/mcp.md before adding an MCP command, endpoint, transport, tool, resource, prompt, or protocol behavior.
- Confirm unclear behavior only when a reasonable assumption could materially change the result.
Use the standard backend layout
Use this target unless the repository has a compatible variation:
backend/
cmd/
api/
main.go
config.go
logging.go
bootstrap.go
server.go
routes/
handlers/
middleware/
httpx/
apijson/
worker/
mcp/
internal/
components/
workspace/
project/
issue/
auth/
overview/
infrastructure/
mongodb/
messages/
queue/
go.mod
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 119 lines · 121 tokens per session scan A 1c075c6f6c60
build-go-stack is a skill published in the GitHub repository OlegHQ/agentpack (14 stars, last pushed today), licensed MIT. It adds 121 tokens to every session and 1,555 once invoked, about $0.0006 per session on Opus 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 2026-09-04.
Other skills, from other repositories
rust-engineer
Acquire expert Rust developer specialisation in rust systems programming, memory safety, and zero-cost abstractions. Masters ownership patterns, async programming, and performance optimisation for mission-critical applications.
wasm
WebAssembly (WASM) integration, WASI, component model, Rust/Go to WASM compilation. Use when implementing WASM modules, browser/edge compute, or polyglot runtime.
golang-development
You MUST activate this skill when working on Go projects.
rust-development
You MUST activate this skill when working on Rust projects.
jamjet-durability-patterns
Production durability patterns for AI agents on the JVM — crash recovery, audit trails, human-in-the-loop, and replay testing using JamJet runtime.
pn-go-scaffolding
Scaffolds new Go API projects (Gin, Fiber, Echo, Chi) or handlers. Use when adding a new route/module; covers idiomatic project layout, env/secrets, error handling, and Go-specific conventions.