review-code

A structured code-review guide for software design, Go code, Protocol Buffers, and API design. It examines how parts of a codebase are organized, connected, and tested, and can use static-analysis tools.

In plain words
What is it for?
Use it for architecture reviews, Go reviews, protobuf reviews, API design reviews, SOLID checks, package-design reviews, and pull-request reviews of relevant files.
Why use it?
It helps uncover design problems, excessive coupling, hard-to-test code, and common Go or API issues before they become harder to change. It produces prioritized findings tied to the code being reviewed.

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

Made for: Claude Code, Codex.

Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,201 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00075 $0.05201
Opus 5 $0.00037 $0.02601
Sonnet 5 $0.00015 $0.01040
Haiku 4.5 $0.00007 $0.00520

Measured 2d ago against content hash 7ee7540588f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

review-code scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- Findings must cite probed evidence (`path:line`, grep output, command result), not pattern-matched suspicion. Per `~/.claude/rules/probe-not-assume.md`.
skills/review-code/SKILL.md · 251 lines

How it starts

The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review

Structured code review covering architecture, Go best practices, and protobuf/API design. Produces actionable, prioritized findings with code-level references.

Workflow

1. Scope and explore

  • Confirm scope with the user: full codebase, specific packages/directories, changed files only (PR or branch diff), or specific concern.
  • Resolve scope to a file/package list. Based on what the user requested:
    • Changed files (PR or branch): Run git diff --name-only --diff-filter=d <base>...HEAD to get changed files (default <base> is main). If the user references a PR number, use gh pr diff <number> --name-only instead. Filter to relevant file types (.go, .proto). Derive affected Go packages from the file paths (unique parent directories containing .go files).
    • Explicit paths/packages: The user may specify directories (e.g. internal/auth/), Go package patterns (e.g. ./internal/auth/...), or individual files. When given a directory or package pattern, include all files under it. Derive Go package paths for static analysis tool invocations.
    • Full codebase: No filtering. Explore everything (default).
  • Pass the resolved scope (file list and derived package paths) to all exploration and investigation subagents so they only read and analyze scoped files. Static analysis tools receive package paths; manual review subagents receive the file list.
  • Explore the scoped code using parallel subagents (subagent_type="explore"). Read all relevant source files, paying attention to package structure, type definitions, interfaces, import graphs, .go files, .proto files, and test files.
  • Classify the scope for change-aware subagents:
    • has_changes: true when scope is "changed files (PR or branch)", or when scope is "explicit paths" and those paths have a diff against the base ref (run git diff --name-only --diff-filter=d <base>...HEAD -- <paths> to check; default base is main). False for full-codebase reviews with no diff baseline. When true, derive the changed file list (intersection of scoped files and files with diffs) and carry the base ref forward for subagents that need them.
  • Determine which subagents are applicable:
    • Architecture and Design: applicable if code files (.go, .rs, .ts, .tsx, .js, .jsx, .swift, .kt, .kts, .py, .rb) exist in scope
    • Go Best Practices: applicable if .go files exist in scope
    • Protobuf and API Design: applicable if .proto files exist in scope
    • Go Static Analysis: applicable if .go files exist in scope
    • Protobuf Linting: applicable if .proto files exist in scope
    • Regression History: applicable if code files exist in scope and has_changes is true
    • Conformance Check: applicable if code files exist in scope (lightweight mode by default; full mode when conformance_mode is full)
    • Dependency Evaluation: applicable if a dependency manifest (go.mod, package.json, requirements.txt, pyproject.toml, Cargo.toml, Gemfile, mix.exs, composer.json) is in scope and has_changes is true

Read the full file on GitHub · 251 lines

Files

What ships with it

3 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 · 251 lines · 75 tokens per session scan B 7ee7540588f7

Subscribe to this mod's changes

review-code is a skill published in the GitHub repository paultyng/skill-issue (9 stars, last pushed 21d ago), licensed MIT. It adds 75 tokens to every session and 5,201 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.