Skip to content
View turleydesigns's full-sized avatar

Highlights

  • Pro

Block or report turleydesigns

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
turleydesigns/README.md

Matthew Turley

American in Paris. 3 kids. 20 years shipping product. Building Continuum + RelayPlane.

What I'm doing right now

Running a 6-agent code pipeline across 12 products (client and personal). Recent 6-week window:

  • 333 PRs shipped
  • $1,132 in token spend
  • $3.40 per shipped PR
  • 0 humans in the loop until final review

The pipeline writes specs, drafts code, runs three independent review agents, catches runaway loops with a kill-switch hook, and ships to production with no human intervention until final review before merge.

What I'm building

Continuum is my service brand. Two engagement shapes:

  • Fractional CTO/technical partner retainer for early and growth-stage SaaS
  • Continuum Sprint: 2-3 months to connect AI to operators' actual workflows (RAG knowledge base, custom chat on your docs, automated workflows, tool integrations)

RelayPlane is my product brand. AI cost intelligence for teams running real workloads. Free local proxy, optional cloud dashboard, mesh network for collective routing intelligence. Built because I needed it for my own multi-agent setups.

Recently shipped

  • ccaudit — local diagnostic that grades your Claude Code setup. npx @uxcontinuum/ccaudit
  • Loop Sentinel — PreToolUse hook that catches runaway agent loops before they burn tokens overnight

Where to find me

Pinned Loading

  1. claude-founder-type claude-founder-type Public

    The Founder Type

    Python

  2. claude-loop-sentinel claude-loop-sentinel Public

    Loop Sentinel

    Shell 1

  3. claude-memory-hook claude-memory-hook Public

    Claude Memory Hook

    Python

  4. claude-sprint-icp claude-sprint-icp Public

    Claude Sprint ICP

    Shell

  5. claude-wrapped claude-wrapped Public

    Claude Code Wrapped

    Python

  6. claude-audit claude-audit Public

    A diagnostic for your Claude Code setup. Grades your hooks, project hygiene, tool balance, prompt tells, and pipeline ops.

    JavaScript