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 skills add tmj-90/gaffer --skill go-conventionsgit clone --depth 1 https://github.com/tmj-90/gafferWrote 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/tmj-90/gaffer/go-conventions)<a href="https://agentmods.dev/skills/tmj-90/gaffer/go-conventions"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/go-conventions/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/skills/tmj-90/gaffer/go-conventions"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/go-conventions.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 | $0.00119 | $0.02148 |
| Opus 5.5 | $0.00048 | $0.00859 |
| Sonnet 5.5 | $0.00024 | $0.00430 |
| Haiku 4.5 | $0.00012 | $0.00215 |
Grade A, and why
go-conventions 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 27d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write idiomatic Go
Go rewards plain code: every error checked and wrapped, small interfaces, goroutines that always end. For the builder and the reviewer of a Go diff; the repo's config and existing code win over it.
Procedure
- Discover the repo's conventions first. Call
search_lorefor Go conventions. Readgo.mod(thegodirective gates features: per-iteration loop variables need ≥ 1.22,wg.Goandtesting/synctest≥ 1.25),go.work,.golangci.yml(v2 files startversion: "2"),staticcheck.conf, theMakefile, and the CI workflow. Open the nearest sibling package and its_test.goand copy their layout, error style, logging (log/slogor the repo's logger) and test helpers. Never hand-edit a file headed// Code generated … DO NOT EDIT.; change its source and rungo generate. - Pin the exact commands from CI or the
Makefile(therun-testsandrun-lintskills). Use the defaults below only when the repo defines none. - Write the change with the idioms below, then walk the concurrency section for every goroutine, shared value, file and outbound call you touched.
- Test each acceptance criterion's own behaviour. One test (or
t.Runcase) per AC that fails without your change, plus its error path — table-driven witht.Run, andt.Helper()in assertion helpers. If the AC involves shared state or persistence, add a test that runs N goroutines against it concurrently under-raceand asserts the invariant (no lost update, no error, exactly one winner). - Verify, then stop. Done when:
gofmt -l .prints nothing, build/vet/lint are clean at the repo's configuration,go test -raceis green,go mod tidy -diffis empty, and every AC has a test. Record the output with therecord-evidenceskill; the runner submits the work.
Commands
- Format:
gofmt -l .(orgoimports -l .) must print nothing. - Build and vet:
go build ./...andgo vet ./.... - Lint:
golangci-lint run ./...when configured, elsestaticcheck ./...when configured. - Test:
go test -race -count=1 ./...; one case:go test -race -run 'TestX/case' ./pkg/x. - Dependencies:
go mod tidy -diff(Go 1.23+) reports drift without rewritinggo.mod/go.sum. Nevergo getor letgo mod tidyadd a module: a new or bumped dependency is a blocker (thedependency-upgradeskill).govulncheck ./...if installed. - Do not run
go fix ./...(Go 1.26 modernizers) across the tree unless the ticket asks; it rewrites unrelated code.
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.
- 27d ago Changed · +52 lines · +35 tokens per session a340426b245c
- 1mo ago First seen · 75 lines · 84 tokens per session scan A c7d40143c69c
go-conventions is a skill published in the GitHub repository tmj-90/gaffer (2 stars, last pushed 28d ago), licensed Apache-2.0. It adds 119 tokens to every session and 2,148 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
sota-golang
State-of-the-art Go engineering rules (supported Go releases) that Claude applies when writing new Go code or auditing existing Go code. Covers error handling, interface/package design, goroutine and channel correctness, net/http hardening, security (SQL, exec, path traversal, CSPRNG, TLS, supply chain), performance…
concurrency-patterns-go
Apply safe, idiomatic Go concurrency patterns with goroutines and channels. Use when the user works with goroutines, channels, sync primitives, context cancellation, worker pools, fan-in/fan-out, select statements, or asks about concurrent Go programming and avoiding race conditions.
error-handling-go
Implement robust Go error handling with wrapping, sentinel errors, and custom types. Use when the user handles errors in Go, creates custom error types, wraps errors with fmt.Errorf and %w, uses errors.Is/As, or asks about Go error best practices and error propagation strategies.
idiomatic-go
Write clean, idiomatic Go following community conventions and effective patterns. Use when the user writes Go code, designs packages, defines interfaces, uses struct embedding, writes receiver methods, organizes Go projects, or asks about Go best practices and conventions.
golang-expert
Go programming expert for goroutines, channels, interfaces, modules, and concurrency patterns.
agent-go-expert
Specialist subagent: 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.