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 aiskillstore/marketplace --skill golang-benchmarkgit clone --depth 1 https://github.com/aiskillstore/marketplaceWrote 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/aiskillstore/marketplace/golang-benchmark)<a href="https://agentmods.dev/skills/aiskillstore/marketplace/golang-benchmark"><img src="https://agentmods.dev/badge/skills/aiskillstore/marketplace/golang-benchmark/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/aiskillstore/marketplace/golang-benchmark"><img src="https://agentmods.dev/badge/skills/aiskillstore/marketplace/golang-benchmark.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 | $0.00104 | $0.03153 |
| Opus 5.5 | $0.00042 | $0.01261 |
| Sonnet 5.5 | $0.00021 | $0.00631 |
| Haiku 4.5 | $0.00010 | $0.00315 |
Grade A, and why
golang-benchmark scanned grade A with 1 finding 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 23d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Read Edit Write Glob Grep Bash(go:*) Bash(golangci-lint:*) Bash(git:*) Agent WebFetch Bash(benchstat:*) Bash(benchdiff:*) Bash(cob:*) Bash(gobenchdata:*) Bash(curl:*) mcp__context7__resolve-library-id mcp_ The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- evals/evals.json 91 KB
- references/benchstat.md 16 KB
- references/ci-regression.md 11 KB
- references/compiler-analysis.md 11 KB
- references/investigation-session.md 7.7 KB
- references/pprof.md 37 KB
- references/prometheus-go-metrics.md 13 KB
- references/tools.md 3.9 KB
- references/trace.md 20 KB
- skill-report.json 141 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.
- 23d ago First seen · 207 lines · 104 tokens per session scan A 35f74a20f926
golang-benchmark is a skill published in the GitHub repository aiskillstore/marketplace (436 stars, last pushed today), with no licence file. It adds 104 tokens to every session and 3,153 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-24.
Other skills, from other repositories
integrate-arcjet-guard-agent-framework-go
Integrate Arcjet Guard into Microsoft Agent Framework for Go (github.com/microsoft/agent-framework-go). Wrap a functool or MCP tool with GuardTool, guard every tool an agent can see and screen inbound text with GuardMiddleware, or guard any Go function with arcjet.GuardAction. Use when asked to add Arcjet to a Go…
coding-guidance-go-tui
Go terminal UI implementation and review guidance for interactive Bubble Tea state machines. Includes Huh only when embedded in Bubble Tea; use coding-guidance-go for standalone or one-shot Huh prompts and other non-TUI Go work. Covers Bubbles, Lip Gloss, key bindings, focus, and supported Charmbracelet major versions.
coding-guidance-go
Go implementation and review guidance for non-interactive CLIs, libraries, workers, and services; use coding-guidance-go-tui for interactive Bubble Tea and go-testing-with-testify for testify-focused test work. Covers errors, contexts, concurrency, package boundaries, standard tests, and measured performance.
go-testing-with-testify
Write, review, or harden Go tests using stretchr/testify assert, require, mock, or suite. Use for assertion choice, test doubles, subtests, concurrency, and flake triage in an existing Go test setup. Use coding-guidance-go for production code or non-testify tests and tester-mindset for test strategy without concrete…
go-engineer
Go development including goroutines, channels, interfaces, error handling, testing, and production patterns. Trigger when users write Go code, need help with concurrency, interface design, error handling patterns, or Go project structure.
integrate-arcjet-guard-agent-framework-go
Integrate Arcjet Guard into Microsoft Agent Framework for Go (github.com/microsoft/agent-framework-go). Wrap a functool or MCP tool with GuardTool, guard every tool an agent can see and screen inbound text with GuardMiddleware, or guard any Go function with arcjet.GuardAction. Use when asked to add Arcjet to a Go…