Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/aiocean/claude-pluginsnpx agentmods add skills/aiocean/claude-plugins/aio-golang-masteryWrote 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/aiocean/claude-plugins/aio-golang-mastery)<a href="https://agentmods.dev/skills/aiocean/claude-plugins/aio-golang-mastery"><img src="https://agentmods.dev/badge/skills/aiocean/claude-plugins/aio-golang-mastery/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/aiocean/claude-plugins/aio-golang-mastery"><img src="https://agentmods.dev/badge/skills/aiocean/claude-plugins/aio-golang-mastery.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 | $0.00111 | $0.04003 |
| Opus 5 | $0.00056 | $0.02001 |
| Sonnet 5 | $0.00022 | $0.00801 |
| Haiku 4.5 | $0.00011 | $0.00400 |
Grade A, and why
aio-golang-mastery 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 6d 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 — 416 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Go Mastery
Environment
- go: !
go version 2>/dev/null || echo "NOT INSTALLED" - golangci-lint: !
golangci-lint version --short 2>/dev/null || echo "NOT INSTALLED" - govulncheck: !
which govulncheck 2>/dev/null || echo "NOT INSTALLED"
Lint Mode (when user has Go code to review)
Use this mode to systematically lint and fix a Go codebase using the full tooling chain.
Step 1: RUN
Execute the 7-step tooling chain in order. Capture all output:
go build ./... # 1. Compilation errors
go vet ./... # 2. Suspicious constructs
golangci-lint run ./... # 3. Style, bugs, performance, security
govulncheck ./... # 4. Known CVEs in deps
nilaway ./... # 5. Nil pointer dereference detection
deadcode ./... # 6. Unreachable functions
go test -race -count=1 ./... # 7. Data races
Skip any tool that is not installed (check Environment above) and note it in the report.
Step 2: ANALYZE
Parse all tool output and group findings:
| Severity | Source | Examples |
|---|---|---|
| Critical | govulncheck, race detection | Known CVEs, data races |
| High | go vet, nilaway | Nil derefs, printf mismatches, suspicious constructs |
| Medium | golangci-lint | Style violations, inefficient code, unchecked errors |
| Low | deadcode | Unused functions (safe to remove) |
Step 3: FIX
For each finding, apply the idiomatic Go fix using the reference patterns below. Prioritize critical and high severity first. Common fix mappings:
- Unchecked error -> add explicit
if err != nilhandling - Nil deref -> add nil guard or restructure control flow
- Race condition -> add mutex, use atomic, or redesign with channels
- Dead code -> remove or gate behind build tag
- CVE -> update dependency with
go get pkg@latest
Step 4: VERIFY
Re-run the full tooling chain to confirm all fixes. Repeat Step 3 for any remaining findings.
Reference Mode (patterns and knowledge)
What ships with it
10 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.
- references/concurrency.md 5.7 KB
- references/error-handling.md 2.8 KB
- references/generics.md 4.3 KB
- references/grpc.md 5.1 KB
- references/interfaces.md 4.1 KB
- references/naming-and-style.md 21 KB
- references/production.md 5.3 KB
- references/project-structure.md 3.9 KB
- references/static-analysis.md 15 KB
- references/testing.md 5.5 KB
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.
- 6d ago First seen · 416 lines · 111 tokens per session scan A 475ab3d88389
aio-golang-mastery is a skill published in the GitHub repository aiocean/claude-plugins (4 stars, last pushed 7d ago), licensed MIT. It adds 111 tokens to every session and 4,003 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 2026-09-03.
Other skills, from other repositories
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.
investigate
Systematic root-cause debugging: find the cause before writing any fix.
sandbox-unblock
Diagnostic protocol to run before reporting a sandbox blocker or asking for a configuration change. Eight checks that eliminate false positives, then a report template the person holding the settings can act on. On one measured day, six of eight reported blockers turned out to be false, all from the same handful of…
qa
Systematic QA testing of a web application: diff-aware, tiered, with fix-and-verify loop.
optimize
Analyze and suggest performance improvements for code, queries, or systems.
code-review
Review code changes for concrete defects.