code-review

A coding guide for reviewing code changes and pull requests, looking for bugs, regressions, edge cases, missing evidence, and problems that should block a merge.

In plain words
What is it for?
Use it to review a local diff, a branch, a GitHub pull request, or code generated by an agent.
Why use it?
It helps find correctness and safety issues before changes are merged or handed off.

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/kreek/consult/code-review
Any agent
npx skills add kreek/consult --skill code-review
Clone the repo
git clone --depth 1 https://github.com/kreek/consult

Made for: Claude Code, Codex.

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,219 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 $0.00025 $0.02219
Opus 5 $0.00013 $0.01110
Sonnet 5 $0.00005 $0.00444
Haiku 4.5 $0.00003 $0.00222

Measured 2d ago against content hash 720bf29222e6, 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.

agents/.agents/skills/code-review/SKILL.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review

Iron Law

FINDINGS FIRST. BLOCK ON CORRECTNESS, SAFETY, DATA LOSS, AND UNPROVEN CLAIMS.

When to Use

  • Independent review of your implementation diff in the workflow completion loop after proving behavior with proof, before claiming done. Default for any non-trivial agent-generated change. Use a fresh-context subagent, review agent, or separate session when the host provides one. Same-context review is only a labelled fallback when no independent mechanism is available.
  • Diff review (local, branch, or a GitHub PR through whatever GitHub surface the host provides).
  • Review-comment follow-up on the user's own PRs.
  • Agent-generated code review before merge or handoff.

When NOT to Use

  • Commit grouping or git history repair only; use git-workflow.
  • A narrow domain-only review where a specialist skill is sufficient (security, database, api, accessibility).

Core Ideas

  1. Review owns defect discovery, not proof execution. It should find behavioral bugs, regressions, unsafe edge cases, missing evidence, and merge blockers; proof owns turning claims into checks.
  2. Findings first. Summaries, compliments, and change descriptions come after concrete issues ordered by severity.
  3. Every review includes a security pass and a proof-evidence pass. If the review cannot verify a claim, report it as unproven.
  4. Repository constraints beat generic advice. Check declared runtime, framework, dependency, CI, and support-policy constraints before using a language reference.
  5. Maintainability findings need a concrete risk: hidden state, coupled effects, stale flags, duplicated rules, dead compatibility, unreachable paths, or behavior split across unrelated lifecycles.
  6. Review protects the human's mental model. Generated code that is too large, vague, or disconnected from the stated intent is comprehension debt even when it appears to work.

Independent Review

Code review should run in a fresh context. Use a subagent, review agent, fresh session, or host review command when the host provides one. Claude Code, Codex, Cursor, and Pi all have mechanisms for this; same-context review is not code review, only a labelled fallback when the host truly lacks an independent review surface. Host-provided review surfaces satisfy this requirement when they receive exactly the inputs below and nothing more; this skill defines the inputs and the lenses, the host provides the mechanism.

Read the full file on GitHub · 188 lines

Files

What ships with it

11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 188 lines · 25 tokens per session scan A 720bf29222e6

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository kreek/consult (1 stars, last pushed 7d ago), licensed MIT. It adds 25 tokens to every session and 2,219 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.

Related

Other skills, from other repositories

batch

Execute batch operations on multiple files in parallel. Automatically discovers files, splits into chunks, and processes with parallel worker agents. Use /batch followed by operation and file pattern.

QwenLM/qwen-code · 37 tokens

notion

Notion API for creating and managing pages, databases, and blocks. Use when the user wants to create a Notion page, query a Notion database, update Notion properties, search Notion, add content to Notion, manage Notion blocks, or interact with Notion data sources and workspaces via the API.

elizaOS/eliza · 69 tokens

review

5-pass structured code review — correctness, security, performance, readability, consistency.

SethGammon/Citadel · 17 tokens

scaffold

Project-aware file generation. Reads existing codebase conventions (naming, structure, imports, exports, test patterns) then generates new files that match exactly. Wires generated files into the project's registration points.

SethGammon/Citadel · 44 tokens

marshal

Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.

SethGammon/Citadel · 56 tokens

organize

Repository structure only: directory layout, file placement, naming conventions, and where-does-this-belong decisions. Detects the project's convention, audits files against it, and executes move plans with import-path updates. Never changes code inside files beyond the import updates a move forces; in-file…

SethGammon/Citadel · 66 tokens