adk-review

A review checklist for uncommitted changes in the adk-python repository. It checks correctness, design, public API stability, tests, samples, and documentation, then reports findings without editing files.

In plain words
What is it for?
Use it to inspect a working-tree diff, prioritize issues, check tests and documentation gaps, and assess whether public behavior may have changed.
Why use it?
It helps catch problems and missing coverage before changes are sent for review or opened as a pull request.

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

Made for: Claude Code, Codex.

Per session 164 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,300 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 $0.00164 $0.01300
Opus 5 $0.00082 $0.00650
Sonnet 5 $0.00033 $0.00260
Haiku 4.5 $0.00016 $0.00130

Measured 2d ago against content hash 85933af5c1a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adk-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 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.

.agents/skills/adk-review/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADK Change Reviewer

Review the working-tree diff against the seven dimensions below, report what is wrong, and stop. Fix only what the user then asks you to fix.

Workflow

  1. git status and git diff (add --staged for staged work) to get the exact set of added, modified, and deleted files.
  2. Review the diff file by file against the checklist.
  3. Emit the report in the format below.
  4. Stop. Do not edit any file, and do not offer to. Wait for the user to ask.
  5. If the user asks for fixes, apply them, then re-run the affected tests (pytest tests/unittests/{path}) and pre-commit run --files {paths}.

Step 4 is the part that is easy to get wrong: an unrequested fix buries the findings the user asked for and mixes review output with new, unreviewed edits.

Checklist

1. Correctness

  • Types: no new mypy errors. CI diffs mypy output against the base branch and fails only on newly introduced errors, so a pre-existing error in a file you touched is not a blocker but a new one is.
  • Imports: no circular imports; absolute imports where the module already uses them.
  • Exceptions: no bare except:; catch a specific type and log with enough context to identify the caller.
  • Type discrimination: check an object's type before reading a type-specific attribute (for example confirm a node is an LlmAgent before inspecting mode), so an unexpected node type raises nothing.
  • Boundaries: None, empty collections, zero, and empty strings are handled by validation or a fallback default.
  • Preconditions: state invariants are checked before the core logic runs.

2. Design

  • Complexity: functions or classes that would be clearer split up.
  • Coupling: high cohesion, low coupling; no anti-patterns introduced.
  • Performance: redundant computation, repeated I/O in a loop, or allocations that scale with input where they need not.
  • Security: inputs validated, sensitive data not logged, no injection, resource exhaustion, or exposure of internal state.

Read the full file on GitHub · 119 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. 2d ago First seen · 119 lines · 164 tokens per session scan A 85933af5c1a0

Subscribe to this mod's changes

adk-review is a skill published in the GitHub repository google/adk-python (21,331 stars, last pushed 3d ago), licensed Apache-2.0. It adds 164 tokens to every session and 1,300 once invoked, about $0.0008 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.