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
.codex/agents/llm-architect.tomlWhat 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.tomlCodex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/
Manually: put the files in place
.claude/agents/llm-architect.mdFor all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention
Manually: put the files in place
.cursor/agents/llm-architect.mdCursor also reads .claude/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.