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/hiromaily/docs-ssotWrote 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/hiromaily/docs-ssot/go)<a href="https://agentmods.dev/rules/hiromaily/docs-ssot/go"><img src="https://agentmods.dev/badge/rules/hiromaily/docs-ssot/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/hiromaily/docs-ssot/go"><img src="https://agentmods.dev/badge/rules/hiromaily/docs-ssot/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 | $0.01229 |
| Opus 5.5 | $0.00000 | $0.00492 |
| Sonnet 5.5 | $0.00000 | $0.00246 |
| Haiku 4.5 | $0.00000 | $0.00123 |
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.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Go File Rules
Go version
This project uses Go 1.26. Prefer modern language and standard library features:
for rangeover integers (for i := range n) — available since Go 1.22slicesandmapspackages from the standard libraryanyinstead ofinterface{}t.Context()in tests instead ofcontext.Background()errors.Newfor static error strings;fmt.Errorf("...: %w", err)for error wrappingnew(expr)for pointer literals — available since Go 1.26
Pointer literals
Go 1.26 allows passing expressions directly to new, eliminating the need for a temporary variable or helper functions like ToPtr():
// Before Go 1.26 — create a temp variable first
n := int64(300)
ptr := &n
// Also before — helper function workaround
func ToPtr[T any](v T) *T { return &v }
ptr := ToPtr(int64(300))
// Go 1.26+ — pass the expression directly
ptr := new(int64(300))
Rules:
- Do not define or use
ToPtr,Ptr, or similar pointer-helper functions. - Do not create a temporary variable solely to take its address.
- Use
new(expr)for all pointer literals to optional/nullable fields.
Toolchain setup
All Go commands run from mcp-server/. The module lives at github.com/hiromaily/claude-forge/mcp-server.
To set up the dev environment (installs lefthook hooks and pins golangci-lint as a tool in go.mod):
cd mcp-server && make install
golangci-lint is pinned as a Go tool dependency (go get -tool — available since Go 1.24). Run it via go tool golangci-lint, not a globally installed binary. The version is locked in go.mod under the tool directive.
Running tests
cd mcp-server && go test ./...
Git hooks (lefthook)
Lefthook runs automatically on git operations. Both hooks only trigger when **/*.go files are staged/pushed, and both run from mcp-server/.
| Hook | Command | Behaviour |
|---|---|---|
pre-commit |
make go-fmt |
Formats staged .go files and re-stages the fixes (stage_fixed: true) |
pre-push |
make go-lint |
Lints and auto-fixes .go files before push |
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 · 106 lines · 0 tokens per session scan A 950640c920d6
go is a cursor rule published in the GitHub repository hiromaily/docs-ssot (2 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,229 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
gonavi-go
A Go coding rule set for the GoNavi repository, based on common Go style guides and the project's own conventions. It covers file structure, errors, context, concurrency, logging, and tests.
backend
You are an expert in Go, Gin, Gorm, Gen, Cosy (https://cosy.uozi.org/) with a deep understanding of best practices and performance optimization techniques in these technologies.
code-style
Formatting, lint, comments language.
20-testing-generated-and-structure
Testing expectations, generated-file boundaries, and CLI structure contract.
shared-libraries
Shared libraries - condition framework, inventory containers, file-backed DB, itinerary, references.
05-go-helpers
In a module whose go.mod requires x/rkit, use rkit before writing a small helper — and over the standard library when both have it (rkit.Contains not slices.Contains, rkit.Coalesce not cmp.Or, rkit.IntToStr not strconv.Itoa). Task → helper map and edge cases: x/rkit/README.md.