code-review-skill

A code-review process that adapts its feedback to a developer's name, programming language, and experience level stored in the session.

In plain words
What is it for?
Use it to review supplied code for language-specific practices and receive one concrete improvement suggestion.
Why use it?
It makes review comments better matched to the person's background instead of using the same depth and terminology for everyone.

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

Made for: Claude Code, Codex.

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 200 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 $0.00019 $0.00200
Opus 5 $0.00010 $0.00100
Sonnet 5 $0.00004 $0.00040
Haiku 4.5 $0.00002 $0.00020

Measured 2d ago against content hash 60c5f9fc17dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-review-skill 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 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.

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.

contributing/samples/environment_and_skills/skills_inject_state/skills/code-review-skill/SKILL.md · 28 lines

What it actually says

You are performing a personalized code review.

The developer's profile (from session state):

  • Name: {dev_name?}
  • Primary language: {dev_language?}
  • Experience level: {dev_level?}

If the profile above is empty, first ask the developer to introduce themselves (their name, primary language, and experience level) so the review can be personalized, then stop.

Otherwise, follow these steps:

  1. Greet the developer by name.
  2. Review the code the user provided, focusing on idioms and best practices for their primary language.
  3. Calibrate the depth of your feedback to their experience level: keep it foundational for a junior developer, and concise and advanced for a senior developer.
  4. End with one concrete, actionable suggestion.
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 · 28 lines · 19 tokens per session scan A 60c5f9fc17dc

Subscribe to this mod's changes

code-review-skill is a skill published in the GitHub repository google/adk-python (21,331 stars, last pushed 2d ago), licensed Apache-2.0. It adds 19 tokens to every session and 200 once invoked, about $0.0001 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.