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 clubpay/ronykit --skill code-reviewgit clone --depth 1 https://github.com/clubpay/ronykitWrote 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/clubpay/ronykit/code-review)<a href="https://agentmods.dev/skills/clubpay/ronykit/code-review"><img src="https://agentmods.dev/badge/skills/clubpay/ronykit/code-review/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/clubpay/ronykit/code-review"><img src="https://agentmods.dev/badge/skills/clubpay/ronykit/code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00080 | $0.01371 |
| Opus 5.5 | $0.00032 | $0.00548 |
| Sonnet 5.5 | $0.00016 | $0.00274 |
| Haiku 4.5 | $0.00008 | $0.00137 |
Grade A, and why
code-review 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Review for correctness and design first, style last (a formatter owns style). Prioritize feedback so the important things aren't lost in nits.
When to use
- Reviewing a teammate's PR or diff.
- Self-reviewing your own change before requesting review.
- Deciding whether a change is safe to merge.
What to check, in priority order
- Correctness — does it do what it claims? Edge cases, error paths, off-by-one, nil/empty, concurrency, boundary conditions.
- Security & safety — input validation, authz checks, injection, secrets in code/logs, unsafe defaults.
- Design fit — right layer/abstraction; follows existing architecture and
package-selection rules; no leaking concerns across boundaries. For RonyKit
features, read
go-design— handlers thin, logic ininternal/app, persistence behindinternal/repo/port.go, imports pointing inward. - Tests — meaningful tests for new behavior and fixed bugs; deterministic; assert behavior not internals.
- Readability — clear names, small functions, comments only where intent is non-obvious.
- Style — defer to the formatter/linter; don't hand-review spacing.
Watch for over-engineering
Complexity is a cost, not a credential. Flag code built to impress (or "just in case") rather than to meet a real requirement — it compounds maintenance with no user value. Quick lenses:
- Deletion test — if this were removed, who'd notice and when? "Only the author" means it's not pulling its weight.
- Abstraction needs ≥3 uses — one implementation behind an interface is
indirection, not abstraction. Don't add a layer for a hypothetical second case.
(Architectural boundaries such as
internal/repo/port.goare the exception: they exist to keep the app testable and storage-independent.) - Scale is actual, not imagined — generality/caching/sharding for traffic you don't have is speculation; prefer the simplest thing that fits today.
- Dependencies earn their keep — a new library must save more than its
footprint and upgrade burden; prefer a workspace helper (
x/*,rony/*). - Premature optimization — no micro-optimizations without a measurement; readable beats clever on cold paths.
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 Changed · +1 lines 65b74b59509e
- 23d ago Changed · +21 lines · +33 tokens per session d1935e5ce55a
- 1mo ago First seen · 86 lines · 47 tokens per session scan A 5f07bc91f87c
code-review is a skill published in the GitHub repository clubpay/ronykit (38 stars, last pushed today), licensed BSD-3-Clause. It adds 80 tokens to every session and 1,371 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
ci-orchestrator
Run a CI-like pipeline locally (format, lint, vet, static-analysis, tests) and summarize per-step results with remediation guidance.
printing-press-output-review
Internal sub-skill: agentic review of a printed CLI's sampled command output for plausibility issues that rule-based checks can't encode (substring-match relevance, format bugs, silent source drops, ranking failures). Invoked via the Skill tool by the main printing-press skill at Phase 4.85 and printing-press-polish…
pr-to-go-linter
Generate a new pkg/linters analyzer from a merged or open PR pattern.
code-review
You are a senior code reviewer. You receive diffs via stdin.
ring:verifying-code
Verifying a Go project: runs every quality check (lint, vet, imports, format, docs, unit, integration, E2E) and returns a single MERGEREADY or NEEDSFIX verdict. Report-only: never fixes anything. Use for a quick pre-merge or pre-PR check outside a full dev-cycle. Skip when not a Go project, when you want a single…
go-concurrency-safety
L1 supplement - audits Go-specific concurrency hazards in node client code: map iteration non-determinism, goroutine leaks, mutex ordering, panic boundaries, context cancellation.