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.
curl -O https://raw.githubusercontent.com/pilotspace/pilot-space/main/.claude/commands/review-claude-sdk.mdgit clone --depth 1 https://github.com/pilotspace/pilot-spaceWrote 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.
[](https://agentmods.dev/commands/pilotspace/pilot-space/review-claude-sdk)<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>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.
| Model | Per session | Once 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 |
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.
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:
-
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
-
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)
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.
- 7d ago First seen · 556 lines · 0 tokens per session scan A eb1f04772faa
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.
Other commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
review-sdk-app
Review and validate a Claude Agent SDK application against best practices.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
argos
A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.