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/lerianstudio/ring/verifying-codenpx skills add LerianStudio/ring --skill verifying-codegit clone --depth 1 https://github.com/LerianStudio/ringWrote 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/lerianstudio/ring/verifying-code)<a href="https://agentmods.dev/skills/lerianstudio/ring/verifying-code"><img src="https://agentmods.dev/badge/skills/lerianstudio/ring/verifying-code.svg" alt="Measured on agentmods" 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 | $0.00101 | $0.01139 |
| Opus 5 | $0.00051 | $0.00570 |
| Sonnet 5 | $0.00020 | $0.00228 |
| Haiku 4.5 | $0.00010 | $0.00114 |
Grade A, and why
ring:verifying-code 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 yesterday.
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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Verification
When to use
- Before creating a pull request
- After completing implementation and wanting to confirm everything passes
- When user wants a quick "is this ready?" check
Skip when
- Project is not Go (no go.mod found)
- User only wants to run a single specific command
- Already inside a ring:running-dev-cycle execution (use the cycle gates instead)
Related
Complementary: ring:running-dev-cycle, ring:reviewing-code
Run everything. Get a verdict. This skill only REPORTS — it does NOT fix anything.
Step 0: Discover Commands
- Verify
go.modexists → if not, STOP: "Not a Go project." - Read
Makefileto discover available targets - Check tool availability:
goimports,gofmt
Command resolution:
| Check | Default | Makefile Override |
|---|---|---|
| Lint | golangci-lint run ./... |
make lint if target exists |
| Vet | go vet ./... |
make vet |
| Imports | goimports -l . |
make imports |
| Format | gofmt -l . |
make fmt or make format |
| Docs | make generate-docs |
make docs |
| Unit Tests | go test ./... |
make test-unit or make test |
| Integration Tests | make test-integration |
— |
| E2E Tests | make test-e2e |
— |
If Makefile target doesn't exist: use default command. If neither exists: SKIP (not a failure).
Phase 1: Static Analysis + Unit Tests (parallel)
Run all 6 in parallel. Capture stdout, stderr, exit code, duration for each.
| # | Check | Fail Condition |
|---|---|---|
| 1 | Lint | Non-zero exit |
| 2 | Vet | Non-zero exit |
| 3 | Imports | Any output (files listed need fixing) |
| 4 | Format | Any output (files listed need formatting) |
| 5 | Docs | Files modified (docs were stale) |
| 6 | Unit Tests | Non-zero exit |
Phase 1 gate: ALL pass → proceed to Phase 2. ANY fails → still run Phase 2, but verdict will be NEEDS_FIX.
Phase 2: Integration + E2E Tests (sequential)
Run sequentially. Continue even if first fails.
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.
- yesterday First seen · 117 lines · 101 tokens per session scan A 8836abe93cf3
ring:verifying-code is a skill published in the GitHub repository LerianStudio/ring (211 stars, last pushed 16d ago), licensed Apache-2.0. It adds 101 tokens to every session and 1,139 once invoked, about $0.0005 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
gosm
/gosm - Go Semi-Auto Orchestrator.
blitz
/blitz - Blitz Mode Commander.
hns-moaiadk-best-practices
Every change must pass all five dimensions before completion.
hns-moaiadk-patterns
Skill "hns-moaiadk-patterns" from modu-ai/moai-adk, covering moai-adk-go domain patterns, architecture quick reference, key source paths, pipeline specialist delegation map and template-first build cycle.
hns-moaiadk-dev-reference
Skill "hns-moaiadk-dev-reference" from modu-ai/moai-adk, covering hns-moaiadk-dev-reference, version management (from claude.local.md §5), single source of truth, build version injection and build with version injection.
golang-patterns
堅牢で効率的かつ保守可能なGoアプリケーションを構築するための慣用的なGoパターン、ベストプラクティス、規約。.