code-review

code-review is a skill for Claude Code, Codex from shawnpang/startup-founder-skills. It costs 45 tokens per session (1,714 once invoked), scanned A, original, MIT.

A structured guide for examining source code, code changes, and pull requests for problems and design issues.

In plain words
What is it for?
Use it before merging changes, when hunting bugs, or when assessing whether a feature or architectural decision is ready for production.
Why use it?
It gives code feedback a consistent order, starting with the intended purpose before checking structure, correctness, security, and other concerns.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Use it before merging changes, when hunting bugs, or when assessing whether a feature or architectural decision is ready for production.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shawnpang/startup-founder-skills/code-review
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.

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

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for code-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/shawnpang/startup-founder-skills/code-review/github.svg)](https://agentmods.dev/skills/shawnpang/startup-founder-skills/code-review)
Your own site
<a href="https://agentmods.dev/skills/shawnpang/startup-founder-skills/code-review"><img src="https://agentmods.dev/badge/skills/shawnpang/startup-founder-skills/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.

agentmods 80×15 button for code-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/shawnpang/startup-founder-skills/code-review"><img src="https://agentmods.dev/badge/skills/shawnpang/startup-founder-skills/code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,714 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00045 $0.01714
Opus 5 $0.00023 $0.00857
Sonnet 5 $0.00009 $0.00343
Haiku 4.5 $0.00005 $0.00171

Measured 10d ago against content hash ef4b4cd1d870, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 10d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/code-review/SKILL.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review

When to Use

  • The user shares code (file, snippet, or diff) and asks for feedback
  • They paste a pull request or want to know if code is production-ready
  • Pre-merge quality gate or bug hunting
  • Reviewing architectural decisions in a PR

Context Required

From startup-context: tech stack, product stage, team size. Also need from the user:

  • The code or diff to review
  • What the code is supposed to do (PR purpose or feature context)
  • Any specific concerns (performance, security, correctness)
  • Language and framework if not obvious from the code

Workflow

Follow a structured five-step methodology. Each step must be completed before moving to the next.

  1. Context — Understand and summarize the PR's purpose before any analysis. Recap the intent back to the user in 1-2 sentences. If unclear, ask before proceeding. Never start reviewing without understanding what the code is trying to accomplish.
  2. Structure — Evaluate architectural decisions and design patterns:
    • Does the code belong in the right module/layer?
    • Are abstractions appropriate (not too many, not too few)?
    • Does this change align with the existing codebase patterns?
    • For non-obvious design choices, acknowledge the author's reasoning before proposing alternatives.
  3. Details — Assess code quality across multiple dimensions:
    • Correctness: Logic errors, off-by-one bugs, null/undefined handling, race conditions, edge cases
    • Security: OWASP Top 10 baseline — injection, broken auth, data exposure, XSS, access control, misconfig, insecure deserialization, vulnerable components
    • Performance: N+1 queries, unnecessary re-renders, O(n^2) on large datasets, missing caching, memory leaks
    • Naming and clarity: Do names communicate intent? Are functions focused on a single responsibility?
  4. Tests — Validate test coverage with equal rigor as code review:
    • Are behavioral assertions present (not just implementation testing)?
    • Are edge cases and error paths covered?
    • Are tests brittle or resilient to refactoring?
    • What test cases are missing?
  5. Feedback — Generate a prioritized, categorized report with specific code examples and concrete improvements. Recognize strong patterns and good decisions explicitly.

Read the full file on GitHub · 151 lines

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. 10d ago First seen · 151 lines · 45 tokens per session scan A ef4b4cd1d870

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository shawnpang/startup-founder-skills (320 stars, last pushed 5mo ago), licensed MIT. It adds 45 tokens to every session and 1,714 once invoked, about $0.0002 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 2026-08-30.