Agents don’t behave, they swarm. Skills and plugins slot in mid flight, and somehow the whole thing is a mess
This repository also configures its own agents. See what eyay-toolkits tells them →
Skill Claude Code
Design Graph: the interface method. Job → Flow → Surface : surfaces, content (C), void states (V: empty, loading, partial, error, denied), needs (N), field boundaries, motion layers, attention scope, proof by swapping N. Use when designing or reviewing screens, flows, or components.
Skill Claude Code needs its repo
Graph Protocol: the orchestration method. X → Graph → Delegation : task nodes, execution graph in waves, delegation break points, worker requirements, AGENT SUBGRAPH prompt blocks, RETURN blocks, retry and evolution, IMPLEMENTED GRAPH compare. Use when splitting work across subagents or workers.
Skill Claude CodeCodex
Run as coordinator that plans a job, hands each coding task to a sub-agent worker (pi Agent tool / omp task agent), verifies every result itself, and lands passing work on local main as one squash commit per task. Use this whenever the user says "use pi", "spawn pi workers", "be the coordinator", "fan out workers"…
Skill Claude Code
Design Thinking: the code method. X → Graph → Effect , the §1-§10 pipeline: shapes, happy path (A), cardinality, break points (E: ⟳ ↯ ☠), requirements (R), boundaries, behavior layers, scope, test layers, code. Stack-agnostic. Use when planning, designing, reviewing, or refactoring code. Output format lives in…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: