agentmods.dev

multi-agent-system-pattern: Skill for Cursor

.cursor/skills/langgraph-orchestration/SKILL.md

langgraph-orchestration is a skill for Cursor from vpeetla-ai/multi-agent-system-pattern. It costs 52 tokens per session (366 once invoked), scanned A, original, MIT.

Instructions for building LangGraph StateGraph agents, which are programs whose work is organized as connected steps and decisions. They cover typed shared state, retries, memory, and pausing for human approval.

In plain words
What is it for?
Use them when adding orchestrators, coding loops, specialist-agent workflows, conditional routing, or human-in-the-loop approval to a LangGraph project.
Why use it?
They provide a consistent structure for multi-step or multi-agent workflows and prevent uncontrolled retry loops or unsafe actions from continuing automatically.

Skill for Cursor

Written for Cursor: installed under .cursor/.

This is vpeetla-ai/multi-agent-system-pattern's own configuration. It tells Cursor how to work on multi-agent-system-pattern itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything multi-agent-system-pattern configures →

not rated 2repo 2mo ago A scan 52 tokens original MIT
View source ↗ vpeetla-ai/multi-agent-system-pattern multi-agent-system-pattern.vercel.app
Reuse

Borrowing it

Nothing to install: this file belongs to vpeetla-ai/multi-agent-system-pattern. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/vpeetla-ai/multi-agent-system-pattern/main/.cursor/skills/langgraph-orchestration/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/vpeetla-ai/multi-agent-system-pattern

Made for: Cursor.

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 langgraph-orchestration

README.md
[![agentmods](https://agentmods.dev/badge/skills/vpeetla-ai/multi-agent-system-pattern/langgraph-orchestration/github.svg)](https://agentmods.dev/skills/vpeetla-ai/multi-agent-system-pattern/langgraph-orchestration)
Your own site
<a href="https://agentmods.dev/skills/vpeetla-ai/multi-agent-system-pattern/langgraph-orchestration"><img src="https://agentmods.dev/badge/skills/vpeetla-ai/multi-agent-system-pattern/langgraph-orchestration/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for langgraph-orchestration

Your own site · 80×15
<a href="https://agentmods.dev/skills/vpeetla-ai/multi-agent-system-pattern/langgraph-orchestration"><img src="https://agentmods.dev/badge/skills/vpeetla-ai/multi-agent-system-pattern/langgraph-orchestration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 366 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 $0.00052 $0.00366
Opus 5.5 $0.00021 $0.00146
Sonnet 5.5 $0.00010 $0.00073
Haiku 4.5 $0.00005 $0.00037

Measured 2mo ago against content hash ff51bf677029, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

langgraph-orchestration 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 2mo 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.cursor/skills/langgraph-orchestration/SKILL.md · 56 lines

What it actually says

LangGraph Orchestration

Standard pattern

START → observe/plan → specialist nodes → evaluate → route (retry|pass|hitl) → END

State

  • Use TypedDict with total=False for optional fields
  • Accumulate trace_events explicitly (list replacement per node unless using reducer)
  • Set max_iterations in state; enforce in routing

Nodes

  • Async wrappers: async def n_x(state): return sync_node(state, deps)
  • One responsibility per node (orchestrate, act, review, quality)
  • Return partial state updates only

Routing

builder.add_conditional_edges("quality", route_fn, {"retry": "plan", "pass": "ship", "escalate": "hitl"})
  • Security failures → escalate/HITL
  • Max iterations → escalate, never infinite loop

HITL

graph.compile(checkpointer=MemorySaver(), interrupt_before=["hitl"])

Resume with graph.ainvoke(update, config) after human approval.

Reference implementations

  • loop-engine-agent-platform/src/loop_engine/graph/build.py
  • loop-engine-agent-platform/src/loop_engine/graph/repo_build.py
  • venkat-ai-platform orchestrators

Tests

  • Mock LLM for deterministic paths
  • pytest.mark.asyncio + tmp_path for filesystem side effects
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. 2mo ago First seen · 56 lines · 52 tokens per session scan A ff51bf677029

Subscribe to this mod's changes

langgraph-orchestration is a skill published in the GitHub repository vpeetla-ai/multi-agent-system-pattern (2 stars, last pushed 2mo ago), licensed MIT. It adds 52 tokens to every session and 366 once invoked, about $0.0002 per session on Opus 5.5. 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.

Memory and contextMulti-AgentPythonai-agentslanggraphtutorial
Related

langgraph-orchestration compared with skills from other repositories

langgraph-orchestration next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
langgraph-orchestrationvpeetla-ai/multi-agent-system-patternSkill22mo agoMITA52Cursor
rememberlangchain-ai/deepagentsSkill31kyesterdayMITA71Claude Code, Codex
coding-prefslangchain-ai/deepagentsSkill31kyesterdayMITA36Claude Code, Codex
agents-bridgeellmos-ai/skillsSkill93d agoMITA48Claude Code, Codex
deepagents-thread-inspectorlangchain-ai/deepagentsSkill31kyesterdayMITA93Claude Code, Codex
mem0-tourmem0ai/mem0Skill68k2d agoApache-2.0A47Claude Code, Codex
query-writinglangchain-ai/deepagentsSkill31kyesterdayMITA57Claude Code, Codex