smith-horn

72 mods across 2 repositories, 87 stars between them.

smith-horn/skillsmith

Agent Claude Code

Use this agent when you need to create foundational templates, boilerplate code, or starter configurations for new projects, components, or features. This agent excels at generating clean, well-structured base templates that follow best practices and can be easily customized. Examples: Context: User needs to start a…

77 yesterday A 249 tokens

smith-horn/skillsmith

Agent Claude Code

Enforces engineering standards and code quality policies. Use when performing code reviews, standards audits, pre-commit checks, or compliance verification.

77 yesterday A 33 tokens

smith-horn/skillsmith

Agent Claude Code

Multi-perspective plan review specialist that coordinates VP Product, VP Engineering, and VP Design perspectives to identify blockers, anti-patterns, conflicts, and regressions. Use when reviewing implementation plans, design docs, or wave plans.

77 yesterday A 50 tokens

agent-types

08

smith-horn/skillsmith

Agent Claude Code

Guide to available agent types in Ruflo (exact count unverified — see agent list for the live registered set).

77 yesterday A 0 tokens

performance-report

10

smith-horn/skillsmith

Command Claude Code

Generate comprehensive performance reports for swarm operations. There is no analysis verb and no performance report subcommand in v3 — the CLI surface is performance metrics; the MCP surface is mcprufloperformancereport.

77 yesterday A 0 tokens

token-efficiency

11

smith-horn/skillsmith

Command Claude Code

Reduce token consumption while maintaining quality through intelligent coordination.

77 yesterday A 0 tokens

token-usage

12

smith-horn/skillsmith

Command Claude Code

Analyze token usage patterns and optimize for efficiency. There is no analysis verb and no token-usage command in v3 — token savings come from hooks token-optimize, and per-model routing stats come from hooks model-stats.

77 yesterday A 0 tokens

auto-agent

13

smith-horn/skillsmith

Command Claude Code

Automatically route a task to the optimal agent using Q-Learning. There is no auto agent family in v3 — the closest live surface is route, backed by swarm coordinate / autopilot for full multi-agent orchestration.

77 yesterday A 0 tokens

self-healing

14

smith-horn/skillsmith

Command Claude Code

Automatically detect and recover from errors without interrupting your flow.

77 yesterday A 0 tokens

session-memory

15

smith-horn/skillsmith

Command Claude Code

Maintain context and learnings across Claude Code sessions for continuous improvement.

77 yesterday A 0 tokens

smart-agents

16

smith-horn/skillsmith

Command Claude Code

Automatically spawn the right agents at the right time without manual intervention.

77 yesterday A 0 tokens

smart-spawn

17

smith-horn/skillsmith

Command Claude Code

There is no automation verb and no smart-spawn subcommand in v3 — no single command replicates "analyze workload, then auto-spawn agents." The closest live building blocks are hooks route (route a task to the agent learned patterns favor) and hooks build-agents (generate agent configs from pretrain data), combined…

77 yesterday A 0 tokens

agent-spawn

19

smith-horn/skillsmith

Command Claude Code

Command "agent-spawn" from smith-horn/skillsmith, covering agent-spawn, usage, options, examples and spawn coder agent.

77 yesterday A 0 tokens

init

20

smith-horn/skillsmith

Command Claude Code

This tool coordinates Claude Code's actions. It does NOT write code or create content.

77 yesterday A 0 tokens

orchestrate

21

smith-horn/skillsmith

Command Claude Code

This tool coordinates Claude Code's actions. It does NOT write code or create content.

77 yesterday A 0 tokens

spawn

22

smith-horn/skillsmith

Command Claude Code

This tool coordinates Claude Code's actions. It does NOT write code or create content.

77 yesterday A 0 tokens

swarm-init

23

smith-horn/skillsmith

Command Claude Code

Initialize a Ruflo swarm with specified topology and configuration.

77 yesterday A 0 tokens