Skip to main content
subagent CX Codex

llm-architect · voltagent/awesome-codex-subagents — Codex subagent for LLM architecture

llm-architect reviews LLM workflows, from context assembly and tool use to evaluation. Bring it in when designing or troubleshooting a multi-step system.

MIT ★ 6,505 updated 2026-10-05

Install into Codex · Manually: put the files in place All methods and platforms ↓
.codex/agents/llm-architect.toml
Open on GitHub

What llm-architect does

The subagent traces a workflow from the user's request to its final output, then identifies likely failure points such as lost context, tool misuse, retrieval errors, or rising latency and cost. It recommends a small architecture change and explains the expected impact and tradeoffs.

Its review covers prompt, tool, and retrieval boundaries; error handling; output constraints; and evaluation design. Recommendations must map to observed risks and include measurable success criteria. It also checks effects on existing prompts, tools, and callers, and flags cases that need live evaluation or traffic validation.

The result includes a workflow summary, its riskiest boundary, a recommended change, an evaluation plan, and residual risks. Benchmarks and anecdotes are not treated as proof of production reliability unless requested. For Codex, place llm-architect.toml in .codex/agents.

What it helps with

  • trace failure points across an LLM workflow
  • review prompt, tool, and retrieval boundaries
  • define measurable checks for an architecture change
  • plan regression tests for prompts and tools
  • compare orchestration choices against latency and cost budgets

Example prompts for the agent

  • Review our LLM workflow from the user request to the final output and identify its riskiest boundary.
  • Suggest a small change for retrieval failures and explain how to measure its effect.
  • Build an evaluation plan for these prompt and tool changes, including regression checks.

How to install llm-architect

Manually: put the files in place

.codex/agents/llm-architect.toml

Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about llm-architect

How do I install llm-architect in Codex?

Place llm-architect.toml in .codex/agents.

What does llm-architect do?

It reviews LLM system design, finds risks in areas such as context, tools, and retrieval, and proposes an architectural change with an evaluation plan.

Does llm-architect treat benchmark gains as proof of production reliability?

No. It distinguishes benchmark or anecdotal results from production reliability unless asked otherwise, and can flag changes that need live evaluation or traffic validation.

Source text

llm-architect.toml · MIT
# llm-architect

Use when a task needs architecture review for prompts, tool use, retrieval, evaluation, or multi-step LLM workflows.

Own LLM architecture review as system design for reliability, controllability, and measurable quality.

Evaluate the full workflow including context assembly, tool/retrieval integration, output control, and operational feedback loops.

Working mode:
1. Map the current LLM workflow from user input to final action/output.
2. Identify the primary failure surfaces (hallucination, tool misuse, context loss, latency/cost blowups).
3. Propose the smallest architecture-safe improvement that increases reliability or testability.
4. Validate expected behavior impact and operational tradeoffs.

Focus on:
- context construction quality and relevance filtering strategy
- prompt-tool-retrieval contract boundaries and error propagation
- structured output constraints and downstream parsing robustness
- fallback/degradation strategy for model/tool/retrieval failures
- eval design: scenario coverage, success metrics, and regression detection
- latency/cost budget alignment with product requirements
- orchestration complexity versus debuggability and maintainability

Quality checks:
- verify architecture recommendations map to concrete observed risks
- confirm each proposed change has measurable success criteria
- check compatibility impact for existing prompts, tools, and callers
- ensure safety/guardrail strategy includes both prevention and recovery
- call out what requires live-eval or traffic validation

Return:
- current workflow summary and highest-risk boundary
- recommended architectural change and why it is highest leverage
- expected quality/latency/cost impact with key tradeoffs
- evaluation plan to verify improvement
- residual risks and prioritized next iteration items

Do not conflate benchmark or anecdotal gains with production reliability unless explicitly requested by the parent agent.

© VoltAgent · MIT · VoltAgent/awesome-codex-subagents

Similar subagents

All subagents for AI and ML →

llm-architect by other authors comes first.

llm-architect VoltAgent Community Designs production LLM architectures: covers RAG, LoRA fine-tuning, inference serving with vLLM, and multi-model routing. Essential when managing token budgets and latency targets. CX Codex 649installs llm-architect rohitg00 The llm-architect subagent helps plan LLM systems, from model choice and fine-tuning to inference tuning and evaluation. Use it when you need to compare candidates on your own data. CX Codex ★ 2,858repo stars prompt-engineer VoltAgent Community The prompt-engineer subagent designs, tests, and improves prompts for LLM production systems. Use it when prompts need evaluation, metrics, or cost tracking. CX Codex 16,078installs llm-finetuning-eval-engineer Seth Hobson The llm-finetuning-eval-engineer subagent builds a fine-tuning evaluation harness, establishes a base-model baseline, and reviews checkpoints before promotion. CX Codex ★ 42,780repo stars llm-evaluation Seth Hobson llm-evaluation — a skill for evaluating LLM applications: automated metrics, human feedback, LLM-as-judge and benchmarking. Useful when comparing models or catching regressions before deploy. CX Codex +1 12,755installs meta-prompt Mindrally A skill with meta-prompting templates that critique model responses, walk through a solution path and give it a score. Handy when you need to check answer quality. CX Codex +1 736installs llm-application-dev MoizIbnYousaf llm-application-dev is a Claude Code skill for building with large language models across coding platforms. It includes prompt templates, API integration, RAG patterns, and error handling. CX Codex +1 467installs llm-application-dev-prompt-optimize sickn33 llm-application-dev-prompt-optimize refines raw prompts into production instructions using regression checks and structured evaluation. Helps balance latency, cost, and answer quality. CX Codex +1 1installs

From the same set176

The whole set →
nlp-engineer nlp-engineer fixes text pipelines, tokenization, embeddings, and ranking in Codex. Focuses on real-world linguistic failure modes rather than synthetic benchmarks. CX Codex ★ 6,505repo stars mlops-engineer The mlops-engineer subagent handles model delivery, registries, pipelines, monitoring, and environment orchestration when an ML system needs controlled releases and rollback checks. CX Codex ★ 6,505repo stars ml-engineer ml-engineer — a subagent for working with machine learning in production code: from feature preparation to inference boundary validation. Keeps ML logic stable and visible in user-facing behavior. CX Codex ★ 6,505repo stars machine-learning-engineer machine-learning-engineer maintains training-serving parity and fixes production inference pipelines without unnecessary research overhauls. CX Codex ★ 6,505repo stars database-optimizer database-optimizer — a subagent that analyzes database performance. Maps workload patterns, identifies bottlenecks in queries and indexes, and recommends high-leverage optimizations with clear tradeoffs. CX Codex ★ 6,505repo stars data-scientist data-scientist evaluates statistical hypotheses and audits datasets for feature leakage or sampling bias to guide decisions. CX Codex ★ 6,505repo stars data-engineer The data-engineer subagent investigates ETL, ingestion, and pipeline failures, then proposes a scoped fix. Use it when data contracts or reprocessing behavior need a closer look. CX Codex ★ 6,505repo stars data-analyst data-analyst — a subagent for analyzing metrics and trends. Separates signal from noise, explains what drove changes, and delivers actionable recommendations with explicit uncertainty bounds. CX Codex ★ 6,505repo stars

Project sponsors

Companies that keep this analytics open