factory-llm-workflow-engineer

factory-llm-workflow-engineer is a skill for Claude Code from nonlinear-xyz/factory-kit. It costs 104 tokens per session (1,615 once invoked), scanned A, original, MIT.

A set of instructions for building applications that use large language models, including chatbots, document search, and tool-using agents. It guides LangGraph workflows, which connect model steps into a stateful process.

In plain words
What is it for?
Use it when building LangGraph workflows, retrieval-augmented generation systems, structured-output steps, streaming chat interfaces, or other stateful LLM applications.
Why use it?
It helps keep model workflows consistent and avoids using a graph for simple one-step tasks. It also sets conventions for shared state, dependencies, routing, structured results, and streaming chat.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the factory-kit plugin — 37 skills, 8 commands, 12 agents, 1 MCP server shipped together

Good fit Use it when building LangGraph workflows, retrieval-augmented generation systems, structured-output steps, streaming chat interfaces, or other stateful LLM applications.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nonlinear-xyz/factory-kit/factory-llm-workflow-engineer
Install

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.

Any agent
npx skills add nonlinear-xyz/factory-kit --skill factory-llm-workflow-engineer
Clone the repo
git clone --depth 1 https://github.com/nonlinear-xyz/factory-kit

Made for: Claude Code.

Or install factory-kit, the plugin that ships this one along with the rest of its 37 skills, 8 commands, 12 agents, 1 MCP server.

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 factory-llm-workflow-engineer

README.md
[![agentmods](https://agentmods.dev/badge/skills/nonlinear-xyz/factory-kit/factory-llm-workflow-engineer.svg)](https://agentmods.dev/skills/nonlinear-xyz/factory-kit/factory-llm-workflow-engineer)
Your own site
<a href="https://agentmods.dev/skills/nonlinear-xyz/factory-kit/factory-llm-workflow-engineer"><img src="https://agentmods.dev/badge/skills/nonlinear-xyz/factory-kit/factory-llm-workflow-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,615 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 $0.00104 $0.01615
Opus 5 $0.00052 $0.00807
Sonnet 5 $0.00021 $0.00323
Haiku 4.5 $0.00010 $0.00161

Measured 7d ago against content hash 07068d524c10, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

factory-llm-workflow-engineer 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.

skills/factory-llm-workflow-engineer/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Apply the llm-workflow-engineer specialist workflow. Build LLM workflows that fit the factory's conventions, not generic LangChain code. Load factory-llm-workflows through the host's skill capability when needed.

How to think (in order)

  1. What kind of LLM workflow is this? Pick one:

    • Single LLM call with structured output (intent classification, extraction) — no graph needed
    • Multi-step workflow with state (chat, claim verification, document Q&A) — LangGraph
    • RAG pipeline (retrieval + answer) — LangGraph with rag/general routing
    • Agent with tool calls (function calling, iterative reasoning) — LangGraph with tool dispatch
    • Streaming chat — LangGraph + SSE If it's not graph-shaped, don't reach for LangGraph.
  2. State shape? TypedDict with total=False and NotRequired for optional fields. Nested TypedDicts for complex types (e.g. RetrievedChunk). Never Pydantic — LangGraph merges shallowly.

  3. Node structure? Each node is a function returned by a factory that injects deps (LLM client, vector store, etc.). create_<node_name>_node(deps) -> async (state) -> partial_state. Don't put deps in module scope.

  4. Routing? If you have ≥2 paths, write a named _should_continue_after_<node>(state) -> str function. Don't inline conditionals in add_conditional_edges.

  5. Structured output? Define a JSON schema dict that serves both as LLM tool definition AND validation contract. One source of truth.

  6. RAG specifics:

    • Hybrid search (alpha = BM25 vs semantic blend, default 0.5)
    • Reranker if available (optional port — Port | None)
    • Confidence threshold gating (default 0.3)
    • Fallback supplement RAG (one-attempt-only, flagged in state)
    • Per-tenant vector store isolation (Weaviate tenant API or equivalent)
  7. Streaming? SSE with typed events. Backend yields {event, data} dicts via EventSourceResponse. Frontend registers callbacks per event name. Names must match exactly — share a constant module if possible.

  8. Multi-tenancy? Every vector store operation takes project_id / tenant_id. Never share an index across tenants.

  9. Prompts? Local template is source of truth. Optional PromptHub override wrapped in try/except so offline dev works.

  10. Ports/adapters? Only if you're actually swapping implementations (vector store, storage). Don't reach for hexagonal from day one.

Read the full file on GitHub · 160 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 · 160 lines · 104 tokens per session scan A 07068d524c10

Subscribe to this mod's changes

factory-llm-workflow-engineer is a skill published in the GitHub repository nonlinear-xyz/factory-kit (9 stars, last pushed 1mo ago), licensed MIT. It adds 104 tokens to every session and 1,615 once invoked, about $0.0005 per session on Opus 5. 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.

Related

Other skills, from other repositories

prompt-sensei

Stage-aware prompt coaching, prompt improvement, lookback analysis, prompting habit feedback, and local reports about prompt quality for AI coding agents such as Claude Code or Codex.

chengzhongwei/Prompt-sensei · 39 tokens

ai-ml

· Build/review AI apps: LLMs, RAG, embeddings, agents, evals, local inference. Triggers: 'llm', 'rag', 'embedding', 'openai sdk', 'agent loop', 'fine-tune', 'ollama', 'vllm'. Not for MCP (use mcp).

iuliandita/skills · 72 tokens

routine-writer

· Write Claude Code routine prompts for schedules, APIs, and GitHub events. Triggers: 'routine', 'claude routine', 'scheduled claude task', 'unattended claude', '/schedule', '/fire'. Not one-off prompts: prompt-generator.

iuliandita/skills · 58 tokens

prompt-generator

· Turn notes into structured LLM prompts or improve existing prompts. Triggers: 'write a prompt', 'system prompt', 'prompt template', 'evaluator prompt', 'delegation prompt', 'rewrite this prompt'. Not for skills or routines.

iuliandita/skills · 53 tokens

anti-ai-prose

· Strip AI tells from prose in docs, PRs, emails, and your own replies. Filters every response once loaded; full audit on request. Triggers: 'unslop', 'ai writing', 'sounds like chatgpt', 'llm voice'. Not for code (use anti-slop).

iuliandita/skills · 67 tokens

kanso-prompting

Use when rewriting, sharpening, or producing a prompt for Claude or another current frontier model. Sets standing rules for getting better LLM output through better prompts. Loaded by /kanso-task; not directly invoked by the user.

blakecyze/kanso · 51 tokens