code-review

A structured review method for examining code changes in context. It checks whether the change works, handles unusual cases, avoids security problems, has suitable tests, and remains understandable.

In plain words
What is it for?
Reviewing pull requests or diffs, tracing changed code through its callers, checking security and error paths, assessing test coverage, and reporting findings by severity with file and line references.
Why use it?
It helps catch bugs that a quick glance or a passing happy-path test may miss, including failures involving empty data, boundaries, concurrency, or unsafe input.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/new1direction/korgex/code-review
Any agent
npx skills add New1Direction/korgex --skill code-review
Clone the repo
git clone --depth 1 https://github.com/New1Direction/korgex

Made for: Claude Code, Codex.

Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 287 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00018 $0.00287
Opus 5 $0.00009 $0.00143
Sonnet 5 $0.00004 $0.00057
Haiku 4.5 $0.00002 $0.00029

Measured 2d ago against content hash 67e262218868, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

src/skills_builtin/code-review/SKILL.md · 23 lines

What it actually says

Review the DIFF, but read enough surrounding code to judge it in context.

  1. Get the diff. git diff (or the relevant range). Read each hunk with its surrounding function and callers — a change is only correct in context.
  2. Check, in priority order:
    • Correctness: does it do what it claims? Off-by-one, null/empty, error paths.
    • Edge cases: boundaries, concurrency, large/empty inputs, failure modes.
    • Security: injection (command/SQL/XSS), path traversal, secrets in code, unvalidated input crossing a trust boundary.
    • Tests: is the new behaviour covered? Would a test have caught a regression?
    • Clarity: names, dead code, needless complexity, comments that explain WHY.
  3. Verify, don't assume. If unsure a branch is reachable or a value can be null, trace it or write a quick check rather than guessing.
  4. Report findings ranked by severity (blocker → nit), each with file:line and a concrete suggested fix. Call out what's GOOD too. Don't invent issues to seem thorough.
Changes

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.

  1. 2d ago First seen · 23 lines · 18 tokens per session scan A 67e262218868

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository New1Direction/korgex (5 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 287 once invoked, about $0.0001 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 2026-08-31.