agent-graphs
Create and manage agent graphs — directed graphs of configs connected by edges with handoff logic. Use when building multi-agent workflows where configs route to each other.
- Installs
- 1.8K
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/launchdarkly/ai-tooling --skill agent-graphs- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads agent-graphs automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Config Agent Graphs
You're using a skill that will guide you through creating and managing agent graphs in LaunchDarkly. Your job is to design the graph topology, create it with the right edges and handoffs, and verify the routing between config nodes.
Prerequisites
This skill requires the remotely hosted LaunchDarkly MCP server to be configured in your environment.
Required MCP tools:
create-agent-graph-- create a new graph with nodes and edgesget-agent-graph-- inspect a graph's structure and edgeslist-agent-graphs-- browse existing graphs in the project
Optional MCP tools:
update-agent-graph-- modify edges, root config, or descriptiondelete-agent-graph-- permanently remove a graphget-ai-config-- inspect individual configs that serve as nodescreate-ai-config-- create new configs to use as graph nodes
Core Concepts
What Are Agent Graphs?
An agent graph is a directed graph where:
- Nodes are configs (each config is an agent with its own model, prompt, and tools)
- Edges define routing between configs (source -> target)
- Handoff data on edges controls how context is passed between agents
- Root config is the entry point — the first agent that receives user input
When to Use Agent Graphs
| Scenario | Example |
|---|---|
| Multi-step workflows | Triage agent -> Specialist agent -> Summary agent |
| Routing by intent | Router agent decides which specialist handles the request |
| Escalation chains | L1 support -> L2 support -> Human handoff |
| Pipeline processing | Extract -> Transform -> Validate -> Store |
Graph Structure
[Root Config] --edge--> [Config A] --edge--> [Config C]
\--edge--> [Config B]
Each edge has:
key-- unique identifier for the edgesourceConfig-- the config key that routes FROMtargetConfig-- the config key that routes TOhandoff(optional) -- data/instructions passed during the transition
Core Principles
- Design Before Building: Map out nodes and edges on paper/whiteboard first
- One Agent, One Job: Each node should have a clear, focused responsibility
- Root Config Is the Router: The entry point should understand how to dispatch
- Handoff Data Matters: Define what context flows between agents
- Verify the Full Path: Test that routing works end-to-end
Workflow
Step 1: Design the Graph
Before creating anything:
- Identify the agents (configs) needed — each is a graph node
- Map the routing: which agent hands off to which?
- Define handoff data: what context does each edge carry?
- Identify the root config: which agent receives initial input?
- Check existing graphs with
list-agent-graphsto avoid duplicates - Check existing configs with
get-ai-configto see what nodes already exist
Step 2: Ensure Nodes Exist
Each node in the graph must be an existing config. If configs don't exist yet:
- Use
create-ai-configto create each agent config - Set up variations with appropriate models and prompts for each agent's role
- Verify each config exists with
get-ai-config
Step 3: Create the Graph
Use create-agent-graph with:
projectKey-- the project containing the configskey-- unique identifier for the graphname-- human-readable display namedescription(optional) -- explain the graph's purposerootConfigKey-- the entry-point config keyedges-- array of connections between configs
{
"projectKey": "my-project",
"key": "support-triage-graph",
"name": "Customer Support Triage",
"description": "Routes customer queries to the appropriate specialist agent",
"rootConfigKey": "triage-agent",
"edges": [
{
"key": "triage-to-billing",
"sourceConfig": "triage-agent",
"targetConfig": "billing-specialist",
"handoff": {"category": "billing", "priority": "normal"}
},
{
"key": "triage-to-technical",
"sourceConfig": "triage-agent",
"targetConfig": "technical-specialist",
"handoff": {"category": "technical", "priority": "normal"}
}
]
}
Step 4: Verify
- Use
get-agent-graphto confirm the graph was created with the correct structure - Verify edges connect the right source and target configs
- Check that the root config key matches the intended entry point
- Confirm handoff data is present on edges that need it
Report results:
- Graph created with N nodes and M edges
- Root config set correctly
- All edges verified
Edge Cases
| Situation | Action |
|---|---|
| Config doesn't exist yet | Create it first with create-ai-config before referencing in a graph |
| Circular routing | Allowed but warn user — ensure there's a termination condition in the agent logic |
| Single-node graph | Valid but unusual — consider if a graph is actually needed |
| Updating edges | Use update-agent-graph — provide the complete new edge list |
What NOT to Do
- Don't create a graph before the config nodes exist
- Don't forget handoff data when agents need context from predecessors
- Don't create overly complex graphs — start simple and add nodes as needed
- Don't delete a graph without understanding if it's actively used in agent workflows
Other Resources
To learn more, read Agent graphs.
FAQ
What does the agent-graphs skill do?
Create and manage agent graphs — directed graphs of configs connected by edges with handoff logic. Use when building multi-agent workflows where configs route to each other.
How do I install agent-graphs?
Run npx skills add https://github.com/launchdarkly/ai-tooling --skill agent-graphs in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/agent-graphs/ (personal) or .claude/skills/agent-graphs/ (project).
Which AI agents can use agent-graphs?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is agent-graphs safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains agent-graphs?
It is published by launchdarkly in launchdarkly/ai-tooling. It has 1,805 recorded installs.
More from launchdarkly/ai-tooling
onboarding
launchdarkly/ai-tooling
Scripted onboarding for LaunchDarkly: quiet execution, fixed sequence, SDK install, first flag with a live reveal, MCP offered afterwards. Enforces step completion before advancing and redirects drift. Use when adding LaunchDarkly, setting up or integrating feature flags in a project, SDK integration, or 'onboard me'.
launchdarkly-flag-discovery
launchdarkly/ai-tooling
Audit your LaunchDarkly feature flags to understand the landscape, find stale or launched flags, and assess removal readiness. Use when the user asks about flag debt, stale flags, cleanup candidates, flag health, or wants to understand their flag inventory.
launchdarkly-flag-create
launchdarkly/ai-tooling
Create and configure LaunchDarkly feature flags in a way that fits the existing codebase. Use when the user wants to create a new flag, wrap code in a flag, add a feature toggle, or set up an experiment. Guides exploration of existing patterns before creating.
launchdarkly-flag-targeting
launchdarkly/ai-tooling
Control LaunchDarkly feature flag targeting including toggling flags on/off, percentage rollouts, targeting rules, individual targets, and copying flag configurations between environments. Use when the user wants to change who sees a flag, roll out to a percentage, add targeting rules, or promote config between environments.
launchdarkly-flag-cleanup
launchdarkly/ai-tooling
Safely remove a feature flag from code while preserving production behavior. Use when the user wants to remove a flag from code, delete flag references, or create a PR that hardcodes the winning variation after a rollout is complete.
launchdarkly-metric-choose
launchdarkly/ai-tooling
Choose the right metrics for a LaunchDarkly experiment, guarded rollout, or release policy. Use when the user wants to know which metrics to use, which is the primary metric for an experiment, what guardrails to add, or which events to monitor in a rollout. Surfaces what will auto-attach from existing release policies before making additional recommendations.
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available