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 OKHP3/skillz --skill code-reviewgit clone --depth 1 https://github.com/OKHP3/skillzWrote 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/okhp3/skillz/code-review)<a href="https://agentmods.dev/skills/okhp3/skillz/code-review"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/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/okhp3/skillz/code-review"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/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 | $0.00109 | $0.01168 |
| Opus 5 | $0.00055 | $0.00584 |
| Sonnet 5 | $0.00022 | $0.00234 |
| Haiku 4.5 | $0.00011 | $0.00117 |
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 6d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code review
A review is a search for the ways this change fails in production, ranked by how badly. It is not a style pass. Style is the lint job's work — if you spend the review on formatting, you have used up the reader's attention on the cheapest possible findings.
The bar for reporting: could you write the input that makes this go wrong? If not, you have a question, not a finding. Say it as a question.
1. Understand the intent before reading the diff
Read the PR description, linked issue, or ask. Reviewing a change without knowing its goal produces suggestions that fight the author's purpose.
Then decide what should have changed. Files you expected to see and don't are the highest- yield finding in any review — a new state field with no migration, a new branch with no test, a new error path with no logging.
Done when: you can state the intent in a sentence, and you have a list of what you expect the diff to touch.
2. Read the change in dependency order
Not top to bottom, and not alphabetically, the order the tool shows you is meaningless. Start at the data model or interface, then the logic, then the callers, then the tests. Meaning flows that direction and reviewing against the flow means re-reading everything twice.
Done when: you have read every changed hunk, including the ones that look boring.
3. Hunt in priority order
Work down this list. Stop going deeper once you have found something serious enough to block — a review that reports one real bug promptly beats a complete review delivered late.
Correctness
- Off-by-one, inverted condition, wrong default, wrong variable in a copy-pasted block
- Error paths — what happens when the call fails, returns empty, times out, returns partial?
- Boundaries — empty, one, many, null, zero, negative, maximum, duplicate, out of order
- Concurrency — shared mutable state, non-atomic read-modify-write, assumed ordering
Blast radius
- Is it reversible? A schema change, a data migration, or a published API is not
- Does it change behaviour for existing callers or stored data?
- Is it behind a flag, and does the off path actually work?
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.
- 6d ago First seen · 107 lines · 109 tokens per session scan A baec0f167ab6
code-review is a skill published in the GitHub repository OKHP3/skillz (3 stars, last pushed yesterday), licensed MIT. It adds 109 tokens to every session and 1,168 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
ontoly-software-graph
Use Ontoly's deterministic Software Graph and MCP capabilities for architecture review, request tracing, dependency analysis, configuration lookup, and impact analysis before falling back to source-file search.
kelly-pr-review
GitHub pull request review desk (Busabase App-in-Skill) using the gh CLI for real GitHub access, an AirApp review UI for human approval, and a trusted gh pr review execution step. Use when the user invokes /kelly-pr-review or $kelly-pr-review, asks to review GitHub PRs, generate a PR review batch…
drupal-security-review
Use when auditing Drupal 11 custom modules/themes for security issues such as unsafe input handling, XSS risks, SQL injection, and access control gaps.
find-verified-code-review-agent
Find a Verified Code Review Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for software agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).
baoyu-comic
A tool for creating original educational comics that explain knowledge or ideas through multiple illustrated panels. It supports different art styles and tones and can create several comics in one batch.
refactor-advisor
A code review helper that finds common design and maintenance problems in a codebase and suggests ways to restructure the code.