Skip to content

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 

Repository files navigation

Graph Engineering — a Claude Code skill

Teach Claude to design multi-agent workflows as dependency graphs, not linear pipelines: fan-out what's independent, gate what's untrusted, and spend expensive tokens only where judgment lives.

Reference: "Graph Engineering with Claude: 14-Step Roadmap" by @0xCodez.

Why

Most agent workflows are accidental pipelines: step B runs after step A only because you wrote it after step A, not because B consumes A's output. Graph engineering makes the dependency structure explicit:

  • Node = one agent, one bounded job, one input in, one output out.
  • Edge = a real data dependency — nothing else.
  • Everything without an edge between it runs in parallel.
  • Orchestration, dedup, routing, and transforms are code, not agents — edges are free; tokens are not.

The workhorse shape is the diamond:

graph LR
    A[Split] --> B[Worker 1]
    A --> C[Worker 2]
    A --> D[Worker 3]
    B --> E[Verify gate]
    C --> E
    D --> E
    E --> F[Merge / synthesize]
Loading

What the skill covers

  1. Fan-out / fan-in, and when a barrier is actually justified
  2. The diamond topology
  3. Conditional routing in plain code
  4. Verification gates: adversarial refuters, perspective-diverse lenses, judge panels
  5. Per-node failure isolation
  6. Convergent loop-until-dry cycles (dedup against all seen, not just confirmed)
  7. Pipeline-over-barriers streaming
  8. "Edges are free" — no-agent-needed as a design win
  9. Model tiering with a concrete allocation table:
Node type Model Effort
Orchestration (routing, dispatch, merge) Most capable available low
Planning / investigation Most capable available xhigh
Implementation / execution Second tier medium

Plus a pre-ship checklist for any workflow script.

The skill also self-triggers when your prompt sequences steps with "and then" / "next" — Claude checks whether the steps truly depend on each other before defaulting to a linear pipeline.

Install

As a plugin (recommended):

/plugin marketplace add HM-Li/graph-engineering
/plugin install graph-engineering@graph-engineering

Manual: copy skills/graph-engineering/ into your project's .claude/skills/ (or ~/.claude/skills/ for all projects):

mkdir -p ~/.claude/skills
cp -r skills/graph-engineering ~/.claude/skills/

Credit

Key reference: @0xCodez's Graph Engineering roadmap. This repo packages the ideas as an installable Claude Code skill and adds the per-node-type model/effort allocation policy.

License

MIT

About

Claude Code skill: design multi-agent workflows as dependency graphs, not linear pipelines

Topics

Resources

Stars

Watchers

Forks

Releases

Packages

Contributors