code-review-assist

A human-guided code-review assistant that summarizes a diff, the set of code changes under review, and highlights questions about behavior, tests, and low-risk areas.

In plain words
What is it for?
Use it during review of a pull request, diff, or code snippet to identify important review questions, assess test coverage, draft comments, and track review outcomes.
Why use it?
It helps a reviewer understand a change faster while keeping the final technical judgment with the person reviewing it.

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

Made for: Claude Code, Codex.

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,843 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 $0.00048 $0.02843
Opus 5 $0.00024 $0.01422
Sonnet 5 $0.00010 $0.00569
Haiku 4.5 $0.00005 $0.00284

Measured 2d ago against content hash c9598a501863, 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-assist 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.

.claude/skills/code-review-assist/SKILL.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review Augmentation

Purpose

Act as a senior review partner — not a replacement reviewer. Help the user understand and evaluate a code change faster, without rubber-stamping it.

How This Differs from the code-reviewer Agent

The code-reviewer agent runs autonomously and checks for best practices, security patterns, and conventions. This skill is for human-in-the-loop review sessions — the user is actively reviewing PRs and making decisions. Your role is to prepare the user to review faster and more thoroughly, surface what matters most, draft comments collaboratively, and track what worked so the review process itself improves over time.

Session Planning

When invoked without a specific PR, start by scoping the session:

  1. Discover PRs: Use GitHub to find (a) open PRs requesting the user's review, (b) PRs merged in the last 2 days that the user hasn't reviewed yet (use a longer lookback only if the user requests it), and (c) open PRs the user has previously reviewed that have new pushes or comments since their last review (contributors may push updates without re-requesting review).
  2. Load only metadata: Fetch PR title, author, description, and files-changed count. Do not load diffs during session planning — you only need high-level information to help the user prioritize.
  3. Present the list: Show each PR with title, author, and a risk estimate (high/medium/low based on files changed, area of codebase, and change size). Also note any existing review activity — approved reviews, changes-requested, pending reviews from others, or review comments — so the user knows what's already been covered. If any PRs form a stack (one PR's base branch is another PR in the list), group them and note the dependency chain and what each PR in the stack is responsible for.
  4. Ask the user:
    • Which PRs to include — all open, all merged, or a subset?
    • Preferred review order — chronological, highest-risk-first, or by author/area?
  5. Track coverage: At the end of the session, report which PRs were reviewed, skipped, or deferred so nothing falls through the cracks.

Read the full file on GitHub · 152 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 · 152 lines · 48 tokens per session scan A c9598a501863

Subscribe to this mod's changes

code-review-assist is a skill published in the GitHub repository stacklok/toolhive (2,065 stars, last pushed today), licensed Apache-2.0. It adds 48 tokens to every session and 2,843 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 2026-08-30.