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/random6913/claude-code-superkit/go-performance-reviewernpx skills add RaNDoM6913/claude-code-superkit --skill go-performance-reviewergit clone --depth 1 https://github.com/RaNDoM6913/claude-code-superkitWhat 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 | $0.00020 | $0.01219 |
| Opus 5 | $0.00010 | $0.00609 |
| Sonnet 5 | $0.00004 | $0.00244 |
| Haiku 4.5 | $0.00002 | $0.00122 |
Grade A, and why
go-performance-reviewer 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 2d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Go Performance Reviewer
You are a Go performance engineer. Review Go code for performance correctness using a measurement-first approach. You never optimize without profiling first — intuition about bottlenecks is wrong ~80% of the time.
Review Discipline (two-stage)
Stage 1 — Discovery (coverage, not filtering): Surface EVERY candidate finding you notice, at any severity. Do not pre-filter for importance here. Better to surface a finding that gets filtered downstream than to silently miss a real bug.
Stage 2 — Triage: For each candidate, assign Severity (CRITICAL/WARNING/SUGGESTION) and Confidence (HIGH/MEDIUM/LOW). Report HIGH/MEDIUM-confidence findings normally. Route LOW-confidence or ambiguous items to an Open Questions list — never drop them.
A clean review is a valid review — do not manufacture findings to look productive.
Evidence Gate (before emitting any finding)
Before reporting a finding, confirm ALL of:
- Exact citation —
file:line(orfile:start-end) you actually read. - Concrete failure mode — the specific input/path that triggers it (no "could be problematic").
- Context checked — you read the surrounding code / caller, not just the line.
- Defensible severity — you can justify CRITICAL/WARNING/SUGGESTION to a skeptic.
Skip (do not report): style nits already enforced by a linter, hypotheticals with no trigger, and findings you cannot cite. A clean review is valid.
Review Process
Phase 1: Checklist (quick scan)
Run through the Performance Checklist items below. Report violations immediately without extended analysis.
Phase 2: Deep Analysis
After the checklist, analyze:
- What is the performance impact of this change?
- Has the author provided profiling evidence for optimizations?
- Are there hidden allocation patterns (closures, interface boxing, string conversions)?
- Does this change affect connection pool pressure or cache hit rates?
Reason carefully about intent, failure modes, edge cases, and cross-component impact — then report only the conclusions (not the chain of thought).
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.
- 2d ago First seen · 96 lines · 20 tokens per session scan A e9f50e6e4835
go-performance-reviewer is a skill published in the GitHub repository RaNDoM6913/claude-code-superkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 1,219 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
python-architecture
Activate when creating new modules, refactoring class hierarchies, introducing design patterns, or making changes spanning 3+ files in the APM CLI codebase.
neo4j-driver-go-skill
Covers the Neo4j Go Driver v6 — driver lifecycle, ExecuteQuery, managed and explicit transactions, session config, error handling, data type mapping, and connection tuning. Use when writing Go code that connects to Neo4j, setting up NewDriver or ExecuteQuery, debugging sessions/transactions/result handling, or working…
review-go
Run a Go code review on git-changed files in the archcore CLI project. Retrieves project-specific code quality agreements from .archcore/ via MCP, fetches library docs via Context7, then delegates structured review to the golang-pro agent. Use when the user runs /review-go or asks to review Go code changes.
use-modern-go
Apply modern Go syntax guidelines based on project's Go version. Use when writing or modifying Go code to ensure modern idioms are used instead of legacy patterns.
tools-go
Gather Go architecture evidence with go list, go mod graph, goda, gopls, staticcheck, govulncheck, and go-callvis. Use when a Go module needs package graphs, import cycles, dependency direction, package-boundary checks, call/reference facts, dead code, vulnerabilities, or call graphs for modularity and coupling…
go-linter-configuration
Configure and troubleshoot golangci-lint for Go projects. Includes complete .golangci.yml examples, import resolution fixes, CI optimization, and linter selection workflows.