aa-code-review

aa-code-review is a skill for Claude Code, Codex from agentarea/agentarea. It costs 66 tokens per session (1,642 once invoked), scanned A, original, Apache-2.0.

A code-review skill for reviewing pull requests and working changes in the AgentArea repository. It checks the change against repository rules such as workspace isolation, persistence, extension points, migrations, and generated frontend contracts.

In plain words
What is it for?
It is for reviewing AgentArea changes, checking the real base diff, applying repository guidance, and validating the checks expected before a change is merged.
Why use it?
It helps reviewers find correctness problems and broken required behavior that ordinary tests or a quick diff review may miss.

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

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 aa-code-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/agentarea/agentarea/aa-code-review.svg)](https://agentmods.dev/skills/agentarea/agentarea/aa-code-review)
Your own site
<a href="https://agentmods.dev/skills/agentarea/agentarea/aa-code-review"><img src="https://agentmods.dev/badge/skills/agentarea/agentarea/aa-code-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,642 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 $0.00066 $0.01642
Opus 5 $0.00033 $0.00821
Sonnet 5 $0.00013 $0.00328
Haiku 4.5 $0.00007 $0.00164

Measured yesterday against content hash 0a619afc6852, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aa-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 yesterday.

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/skills/aa-code-review/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reviewing an AgentArea Change

This is guidance, not a checklist. Read the diff and enough surrounding code to understand the design before judging it. Prioritize correctness, workspace isolation, and broken required behavior over style. One substantiated blocker beats a list of nits.

Start by establishing the real scope against the live base:

git diff --stat "$(git merge-base HEAD origin/main)"...HEAD

Re-establish the base after a retarget or a merge; a stale diff makes you review code that is no longer proposed.

Sources of truth

Verify the author ran the checks that aa-pre-push-checks selects for this diff, and review the semantic gaps neither those nor CI can detect.

Blocking requirements

  1. Workspace isolation holds. Every repository takes a UserContext; every persisted model carries WorkspaceScopedMixin; services receive a RepositoryFactory rather than constructing sessions. A query that reaches the database without workspace scoping is a cross-tenant data leak, not a style issue — trace the new query to the scoping that constrains it, and do not accept "the caller filters it" as the constraint.

  2. Events are persisted, not just published. A domain event that goes to Redis pub/sub without a DB write disappears for anyone who was not listening. Three independent consumers read this stream — the webapp, A2A, and the CLI — so an event vocabulary change breaks surfaces the diff does not touch. Verify the CLI too; it has silently rotted on an invented vocabulary before.

Read the full file on GitHub · 132 lines

Files

What ships with it

1 file 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. yesterday First seen · 132 lines · 66 tokens per session scan A 0a619afc6852

Subscribe to this mod's changes

aa-code-review is a skill published in the GitHub repository agentarea/agentarea (49 stars, last pushed yesterday), licensed Apache-2.0. It adds 66 tokens to every session and 1,642 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 2026-09-03.