synthesis-codebase-review

synthesis-codebase-review is a skill for Claude Code, Codex from synthesisengineering/synthesis-skills. It costs 61 tokens per session (2,441 once invoked), scanned A, original, Apache-2.0.

A tiered method for auditing a software codebase, meaning reviewing its code, design, security, and operational risks. The depth of the review is matched to the project’s size and stakes.

In plain words
What is it for?
Use it for code reviews, architecture reviews, security audits, production-readiness checks, and broader health assessments of software projects.
Why use it?
It prevents both under-reviewing important systems and spending unnecessary effort on checks that do not fit a small project.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the synthesis-skills plugin — 63 skills, 4 hooks shipped together

Good fit Use it for code reviews, architecture reviews, security audits, production-readiness checks, and broader health assessments of software projects.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/synthesisengineering/synthesis-skills/synthesis-codebase-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 synthesisengineering/synthesis-skills --skill synthesis-codebase-review
Clone the repo
git clone --depth 1 https://github.com/synthesisengineering/synthesis-skills

Made for: Claude Code, Codex.

Or install synthesis-skills, the plugin that ships this one along with the rest of its 63 skills, 4 hooks.

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 synthesis-codebase-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-codebase-review.svg)](https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-codebase-review)
Your own site
<a href="https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-codebase-review"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-codebase-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,441 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00061 $0.02441
Opus 5 $0.00030 $0.01221
Sonnet 5 $0.00012 $0.00488
Haiku 4.5 $0.00006 $0.00244

Measured 7d ago against content hash 78ba4bcb5aaf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

synthesis-codebase-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 7d 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.

skills/synthesis-codebase-review/SKILL.md · 263 lines

How it starts

The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Enterprise-Grade Codebase Review

Purpose

A comprehensive, practical codebase audit methodology for projects of any size. Not every project needs every check — the tiered system ensures you apply the right level of rigor.

For the full detailed checklist, see references/detailed-checklist.md in this skill directory.


How to Use This Skill

Step 1: Assess Project Tier

Complete the Project Complexity Assessment to determine which tier applies.

Step 2: Review Applicable Sections

Each section and many individual items are marked with tier indicators:

  • Essential (Tier 1) — Apply to ALL projects, even weekend hacks
  • Standard (Tier 2) — Apply to team projects and production apps
  • Enterprise (Tier 3) — Apply to large-scale, multi-team, or regulated systems
  • Mission-Critical (Tier 4) — Apply to financial, healthcare, infrastructure, or high-stakes systems

Step 3: Skip What Doesn't Apply

  • Tier 1: focus only on Essential items (~50 checks)
  • Tier 2: include Essential and Standard items (~150 checks)
  • Tier 3: include Essential, Standard, and Enterprise items (~400 checks)
  • Tier 4: include everything (~900+ checks)

Pre-Flight Checklist

Complete these checks before starting any review. Skipping pre-flight has caused real wasted effort on real engagements.

Branch Selection

  • Confirm which branch represents the current working state — do NOT assume main is current
  • Check the most recent commit date on the target branch. If main has not been updated in weeks and there is an active branch with many commits ahead, you are likely reviewing a stale snapshot
  • Ask whether the team uses git-flow, trunk-based, or another model. In git-flow, develop is often the correct review target

Review Scope

  • Confirm which directories to exclude (vendor/, node_modules/, generated/, etc.)
  • Ask if a previous review has been conducted. If yes, obtain prior findings to enable delta review mode
  • Confirm expected output format (markdown, PDF, etc.) and audience (engineering team, leadership, both)

Read the full file on GitHub · 263 lines

Files

What ships with it

2 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. 7d ago First seen · 263 lines · 61 tokens per session scan A 78ba4bcb5aaf

Subscribe to this mod's changes

synthesis-codebase-review is a skill published in the GitHub repository synthesisengineering/synthesis-skills (18 stars, last pushed yesterday), licensed Apache-2.0. It adds 61 tokens to every session and 2,441 once invoked, about $0.0003 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.