mcp-gateway: Command for Claude Code

.claude/commands/review-with-plan.md

review-with-plan is a command for Claude Code from Kuadrant/mcp-gateway. It costs 10 tokens per session (1,499 once invoked), scanned A, original, Apache-2.0.

A code-review command that checks branch or pull-request changes against a related design plan and reviews their quality. A pull request is a proposed change for merging into a shared codebase.

In plain words
What is it for?
Use it to review a pull request, compare a branch with a base branch, inspect changed files, and check whether the implementation still follows its design plan.
Why use it?
It helps find differences between the planned work and the implementation, as well as problems hidden by looking only at a small diff.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

This is Kuadrant/mcp-gateway's own configuration. It tells Claude Code how to work on mcp-gateway itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-gateway configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Kuadrant/mcp-gateway. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Kuadrant/mcp-gateway/main/.claude/commands/review-with-plan.md
Clone the repo
git clone --depth 1 https://github.com/Kuadrant/mcp-gateway

Made for: Claude Code.

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 review-with-plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/kuadrant/mcp-gateway/review-with-plan/github.svg)](https://agentmods.dev/commands/kuadrant/mcp-gateway/review-with-plan)
Your own site
<a href="https://agentmods.dev/commands/kuadrant/mcp-gateway/review-with-plan"><img src="https://agentmods.dev/badge/commands/kuadrant/mcp-gateway/review-with-plan/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 review-with-plan

Your own site · 80×15
<a href="https://agentmods.dev/commands/kuadrant/mcp-gateway/review-with-plan"><img src="https://agentmods.dev/badge/commands/kuadrant/mcp-gateway/review-with-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,499 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.
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 $0.00010 $0.01499
Opus 5 $0.00005 $0.00749
Sonnet 5 $0.00002 $0.00300
Haiku 4.5 $0.00001 $0.00150

Measured 11d ago against content hash 36fde67c878e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

review-with-plan 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 11d 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/commands/review-with-plan.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review with Plan

Review the current branch's changes for code quality and — when a design plan exists — compare the implementation against the plan to catch drift.

Input: $ARGUMENTS — a PR number, PR URL, or base branch name. Defaults to main if not provided.

Step 1: Gather changes

Determine the input type and collect the diff:

  • PR number or URL — use gh pr view <number> --json body,title,files and gh pr diff <number> to get the PR description and full diff
  • Branch name or empty — use git diff $(git merge-base HEAD <base>)..HEAD and git log --oneline $(git merge-base HEAD <base>)..HEAD

Read every changed file in full (not just the diff) so you understand surrounding context. If more than ~15 files changed, prioritize files that appear in the plan's task list, then files in hot paths (internal/broker/, internal/mcp-router/, internal/controller/), then the rest.

Step 2: Find the associated plan

Search for a design plan connected to this PR. Try these in order:

  1. Changed files — check if the diff touches anything under docs/design/*/tasks/ or docs/design/*.md. If a subdirectory match, that design directory is the plan. If a flat file match (e.g. docs/design/session-mgmt.md), that file is the plan.
  2. PR description / commit messages — scan for references to design docs (paths like docs/design/..., Jira story IDs, or feature names that match a docs/design/<feature>/ directory).
  3. Feature area heuristic — if the diff changes files in a specific feature area (e.g. internal/broker/tokens.go), check if a design directory exists for that feature (e.g. docs/design/gateway-url-token-elicitation/).

If a plan directory is found, read all files in it:

  • The design doc (*-design.md or *.md at the root of the design directory)
  • tasks/tasks.md — implementation plan with ordered tasks and acceptance criteria
  • tasks/e2e_test_cases.md — expected e2e test cases
  • tasks/documentation.md — documentation deliverables (if present)

Read the full file on GitHub · 155 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. 11d ago First seen · 155 lines · 10 tokens per session scan A 36fde67c878e

Subscribe to this mod's changes

review-with-plan is a command published in the GitHub repository Kuadrant/mcp-gateway (100 stars, last pushed yesterday), licensed Apache-2.0. It adds 10 tokens to every session and 1,499 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.