pilot-space: Command for Claude Code

.claude/commands/review-claude-sdk.md

review-claude-sdk is a command for Claude Code from pilotspace/pilot-space. It costs 0 tokens per session (4,496 once invoked), scanned A, original, Apache-2.0.

A command for reviewing the architecture and technical debt of a chat platform built with Claude's agent software tools. Technical debt is complexity that makes software harder to change or maintain.

In plain words
What is it for?
Use it to review real-time chat systems using Python, FastAPI, SQLAlchemy, Next.js, React, server-sent events, or WebSockets.
Why use it?
It looks for unnecessary abstractions, fragile streaming behavior, and weak architectural choices that can lead to rework or outages.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: positional $N argument.

This is pilotspace/pilot-space's own configuration. It tells Claude Code how to work on pilot-space 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 pilot-space configures →

Reuse

Borrowing it

Nothing to install: this file belongs to pilotspace/pilot-space. 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/pilotspace/pilot-space/main/.claude/commands/review-claude-sdk.md
Clone the repo
git clone --depth 1 https://github.com/pilotspace/pilot-space

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-claude-sdk

README.md
[![agentmods](https://agentmods.dev/badge/commands/pilotspace/pilot-space/review-claude-sdk.svg)](https://agentmods.dev/commands/pilotspace/pilot-space/review-claude-sdk)
Your own site
<a href="https://agentmods.dev/commands/pilotspace/pilot-space/review-claude-sdk"><img src="https://agentmods.dev/badge/commands/pilotspace/pilot-space/review-claude-sdk.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,496 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 $0.00000 $0.04496
Opus 5 $0.00000 $0.02248
Sonnet 5 $0.00000 $0.00899
Haiku 4.5 $0.00000 $0.00450

Measured 7d ago against content hash eb1f04772faa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

review-claude-sdk 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 7d 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-claude-sdk.md · 556 lines

How it starts

The opening of the file, as written. The whole thing — 556 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Principal Full-Stack Architect and Technical Debt Hunter with 15 years specializing in:

  • Real-time chat platforms built on Claude Agent SDK (Python & TypeScript)
  • Streaming architectures (SSE, WebSocket) with graceful degradation
  • AI agent orchestration using Anthropic's Claude SDK for multi-turn conversations
  • Production-grade Python (FastAPI, SQLAlchemy 2.0 async) and Next.js/React (App Router, streaming)
  • Technical debt eradication through ruthless simplification without sacrificing functionality

You excel at penalty analysis: identifying over-engineering, unnecessary complexity, and architectural weak points that create maintenance burden, then proposing simpler alternatives that achieve identical outcomes.

Stakes Framing

This chat platform architecture review is critical to avoiding:

  • $50,000+ in technical debt from over-complex abstractions
  • 3-6 months of rework when simple patterns would suffice
  • Production outages from fragile streaming state management
  • Agent SDK integration failures from misunderstanding Claude's capabilities

I'll tip you $2,000 for a ruthlessly honest, technically precise review that prevents these outcomes.

Task Decomposition

Take a deep breath and work through this step-by-step penalty analysis:

Step 1: Architecture Plan Intake & Context Building

Input: Receive the architectural plan document for the Claude Agent SDK chat platform

Actions:

  1. Read the full plan to understand:

    • Proposed streaming architecture (SSE/WebSocket/hybrid)
    • Session management approach (stateful/stateless)
    • Claude Agent SDK integration patterns (single-turn vs multi-turn)
    • State synchronization strategy (frontend ↔ backend)
    • Database schema for conversation persistence
    • Error handling and reconnection logic
  2. Extract critical assumptions the plan makes about:

    • Claude SDK capabilities (streaming, tool use, session resumption)
    • Real-time requirements (latency SLAs, concurrency limits)
    • Scale targets (concurrent users, message throughput)
    • Deployment environment (serverless vs long-running processes)

Read the full file on GitHub · 556 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. 7d ago First seen · 556 lines · 0 tokens per session scan A eb1f04772faa

Subscribe to this mod's changes

review-claude-sdk is a command published in the GitHub repository pilotspace/pilot-space (2 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 4,496 tokens. 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 2026-08-31.