codebase-review

codebase-review is a skill for Codex from HoangNguyen0403/agent-skills-standard. It costs 38 tokens per session (1,260 once invoked), scanned A, original, MIT.

A codebase-wide review workflow that examines architecture, engineering health, and exploitable risk, then creates a prioritized remediation plan, system knowledge document, or both.

In plain words
What is it for?
Use it to locate source code, tests, documentation, infrastructure, configuration, entry points, and data stores before producing a review or knowledge artifact.
Why use it?
It turns a large and unfamiliar codebase into an evidence-based map of its structure, risks, and most important improvements.

Skill for Codex

Written for Codex: installed under .codex/.

Good fit Use it to locate source code, tests, documentation, infrastructure, configuration, entry points, and data stores before producing a review or knowledge artifact.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hoangnguyen0403/agent-skills-standard/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 HoangNguyen0403/agent-skills-standard --skill codebase-review
Clone the repo
git clone --depth 1 https://github.com/HoangNguyen0403/agent-skills-standard

Made for: 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 codebase-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/hoangnguyen0403/agent-skills-standard/codebase-review/github.svg)](https://agentmods.dev/skills/hoangnguyen0403/agent-skills-standard/codebase-review)
Your own site
<a href="https://agentmods.dev/skills/hoangnguyen0403/agent-skills-standard/codebase-review"><img src="https://agentmods.dev/badge/skills/hoangnguyen0403/agent-skills-standard/codebase-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 codebase-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/hoangnguyen0403/agent-skills-standard/codebase-review"><img src="https://agentmods.dev/badge/skills/hoangnguyen0403/agent-skills-standard/codebase-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,260 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 $0.00038 $0.01260
Opus 5 $0.00019 $0.00630
Sonnet 5 $0.00008 $0.00252
Haiku 4.5 $0.00004 $0.00126

Measured 9d ago against content hash 1b4a3c1a5b1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

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 9d 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.

.codex/skills/codebase-review/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codebase Review Skill

[!IMPORTANT] Review an entire codebase for architecture, engineering health, and exploitable risk; generate a prioritized remediation plan, an evidence-anchored system knowledge document, or both.

Optional args: slug=, ticket=<id/url>, mode=interactive|autonomous|channel, channel=, auto_continue=true|false, profile=business|hybrid|technical.

Instructions

When the user asks to perform this workflow, execute the following steps:

🛸 Codebase Review Orchestrator

Goal: Map a codebase from evidence, expose systemic risk, and produce the review and/or knowledge artifact requested.

Steps

  1. Set the review contract:

    • Select analysis=fast|deep and deliverable=review|knowledge|both; default to fast + review to preserve the existing audit behavior. Use deep for knowledge or both unless the user explicitly requests otherwise.
    • Read stack markers (package.json, go.mod, pubspec.yaml, pom.xml) and locate source, tests, docs, IaC, runtime config, entry points, data stores, and generated paths.
    • Load common-architecture-audit, common-security-audit, common-owasp, and common-llm-security.
    • Build a source bundle from code, docs, tickets, diagrams, runbooks, and runtime evidence. Classify each as trusted, semi-trusted, or untrusted; record missing or inaccessible evidence.
  2. Map the system before judging it:

    • Inventory components, ownership boundaries, entry points, shared state, data stores, background jobs, external dependencies, configuration owners, and tests. Prioritize by runtime criticality plus import/call fan-in and fan-out; exclude generated/vendor files unless they define a public boundary.
    • Trace each critical flow as trigger -> validation/auth -> state mutation -> side effect -> consumer. Map cross-cutting logging, caching, error handling, authentication, and authorization.
    • Build an interaction and blast-radius matrix for shared schemas, libraries, configuration, state stores, events, and external contracts. Label every relationship as fact, inference, or unknown and cite its file/function/config evidence.

Read the full file on GitHub · 65 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. 9d ago First seen · 65 lines · 38 tokens per session scan A 1b4a3c1a5b1c

Subscribe to this mod's changes

codebase-review is a skill published in the GitHub repository HoangNguyen0403/agent-skills-standard (565 stars, last pushed 3d ago), licensed MIT. It adds 38 tokens to every session and 1,260 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 2026-09-03.