RocketRide is an open-source AI development environment and data-pipeline runtime that lets developers compose, debug, observe, and deploy model-based workflows from an IDE or terminal. Its C++ engine runs portable pipelines with extensible nodes for language models, vector databases, document processing, and agent orchestration on the user's infrastructure. The catalogue entries relate to operating and developing with RocketRide's workflows, SDKs, and tooling.
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.
npx agentmods add agents/rocketride-org/rocketride-server/rocketride_common_mistakesgit clone --depth 1 https://github.com/rocketride-org/rocketride-serverWrote 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/agents/rocketride-org/rocketride-server/rocketride_common_mistakes)<a href="https://agentmods.dev/agents/rocketride-org/rocketride-server/rocketride_common_mistakes"><img src="https://agentmods.dev/badge/agents/rocketride-org/rocketride-server/rocketride_common_mistakes.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 | $0.10854 |
| Opus 5 | $0.00000 | $0.05427 |
| Sonnet 5 | $0.00000 | $0.02171 |
| Haiku 4.5 | $0.00000 | $0.01085 |
Grade A, and why
ROCKETRIDE_COMMON_MISTAKES scanned grade A with 2 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
requests.get(url) # Use: async with aiohttp.ClientSession() Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
child_process.execSync('cmd'); // Use: await promisify(exec)() How it starts
The opening of the file, as written. The whole thing — 1,501 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RocketRide Common Mistakes & Troubleshooting Guide
A comprehensive guide to avoiding common pitfalls when building RocketRide pipelines and applications.
Last Updated: March 26, 2026
Table of Contents
- Pipeline Configuration Mistakes
- SDK Mistakes (Python & TypeScript)
- Blocking the Async Event Loop - CRITICAL
- Language-Specific SDK Mistakes
- Component Configuration Mistakes
- Data Flow Mistakes
- Engine Extension (Python–C++ Interop)
- Quick Reference
Pipeline Configuration Mistakes
Mistake 1: Mismatched Response Keys
Problem:
# Pipeline has custom laneName
{'provider': 'response_answers', 'config': {'lanes': [{'laneId': 'answers', 'laneName': 'chat_response'}]}}
# But code expects default key
response = await client.chat(token=token, question=question)
answer = response['answers'] # ERROR: KeyError! Key is 'chat_response'
Why This Happens:
The response component's laneName parameter changes the JSON key in the response. When you customize it, your client code must match.
Solution:
# Match your pipeline configuration
answer = response['chat_response'] # CORRECT: Use custom key from pipeline
Better Solution:
# Use default response configuration (no custom lanes)
{
"provider": "response_answers",
"config": {} // CORRECT: Use defaults
}
# Then your code works with standard keys
answer = response['answers'] # CORRECT: Works with default config
Rule: If you customize laneName in your pipeline, you MUST update your client code to match. When in doubt, don't customize - use defaults!
Note: Response components are lane-specific. Use response_answers for answers, response_text for text, response_documents for documents, etc.
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.
- 6d ago First seen · 1,501 lines · 0 tokens per session scan A 1006006ce1fd
ROCKETRIDE_COMMON_MISTAKES is an agent published in the GitHub repository rocketride-org/rocketride-server (7,923 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 10,854 tokens. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
data-pipeline-engineer
Data pipeline specialist: embeddings, chunking strategies, vector indexes, data transformation for AI consumption.
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
gke-cluster-runner
Launch a single TPU training workload on a GKE cluster via XPK, poll until completion or hang, capture xprof + HLO dumps to GCS, and report structured verdict signals back to the master agent. Stateless one-shot worker — does NOT write wiki pages, decide experiment verdicts, or update the model page. Use for every…
Reviewer
Use when: reviewing C++ code for quality, checking memory safety and RAII compliance, verifying cross-platform portability, enforcing API consistency, reviewing for thread safety, checking const-correctness, auditing error handling patterns.