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 ApexIQ/skillsmith --skill code_reviewgit clone --depth 1 https://github.com/ApexIQ/skillsmithWrote 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/apexiq/skillsmith/code_review)<a href="https://agentmods.dev/skills/apexiq/skillsmith/code_review"><img src="https://agentmods.dev/badge/skills/apexiq/skillsmith/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/apexiq/skillsmith/code_review"><img src="https://agentmods.dev/badge/skills/apexiq/skillsmith/code_review.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 | $0.00027 | $0.00394 |
| Opus 5.5 | $0.00011 | $0.00158 |
| Sonnet 5.5 | $0.00005 | $0.00079 |
| Haiku 4.5 | $0.00003 | $0.00039 |
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 1mo 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.
What it actually says
👁️ Code Review
Philosophy: Code review is not about finding blame. It's about finding bugs before users do.
The Checklist
1. Correctness
- Does the code do what the PR description says?
- Are edge cases handled (empty lists, null values, network errors)?
- Are there any off-by-one errors in loops?
2. Security
- Is user input validated/sanitized?
- Are ownership checks in place for resources?
- Are secrets hardcoded? (They shouldn't be.)
3. Performance
- Any N+1 queries? (Fetching in a loop instead of batch)
- Are large lists paginated?
- Is there unnecessary re-rendering in React components?
4. Readability
- Are variable/function names descriptive?
- Is complex logic explained with comments?
- Is the code DRY (no copy-paste)?
5. Testing
- Are there tests for the new code?
- Do the tests cover the happy path AND error cases?
Examples
- Good PR: Small, focused, with tests and a clear description.
- Bad PR: 500+ lines, touches unrelated files, no tests.
Guidelines
- Review in <30 mins. If PR is too large, ask to split it.
- Be kind. "Consider using X" is better than "This is wrong."
- If unsure, ask questions instead of blocking.
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.
- 1mo ago First seen · 51 lines · 27 tokens per session scan A a5be465fb823
code-review is a skill published in the GitHub repository ApexIQ/skillsmith (5 stars, last pushed 6mo ago), licensed MIT. It adds 27 tokens to every session and 394 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
qa-review
Perform a thorough code review. Use when the user requests a review, wants to verify code quality, or before merging a PR.
dev-refactor
Code refactoring to improve quality. Trigger when the user wants to clean up, restructure, or improve existing code.
pr-review
Use this before requesting review on a pull request.
pr-standards
Enforce pull request best practices: size limits, description templates, testing requirements, and review workflows. Activate whenever the user creates a PR, asks about PR best practices, sets up PR templates, discusses code review turnaround, or mentions PR size, review requirements, or branch protection rules.
review-checklist
Systematic code review checklist with severity classification. Activate whenever the user asks for a code review, wants feedback on their code, submits a PR for review, or asks what to look for when reviewing code. Also activate when writing review comments or discussing code quality standards.
pr-workflow
Guide pull request creation, review process, CI gates, and merge strategies. Use when the user creates a PR, asks about PR templates, review workflows, CODEOWNERS setup, or merge strategies. Apply when running gh pr create.