claude

mediator-loop

Blind implement -> review -> fix loop between two agents that never learn of each other's existence, mediated until an independent reviewer returns APPROVED. Engine-agnostic, disconnect-proof, usage-limit aware.

0 on GitHubby sapoepsilonv0.1.0MITupdated 2 months agoautomation
/

Plugin mediator-loop from marketplace pragmatic-skills in sapoepsilon/pragmatic-skills. Commands read from the repo's manifest — 1 month ago.

What it installs

Skills (1)

  • mediator-loop

    Run a blind implement -> review -> fix loop between two agents that never learn of each other's existence, mediated until an independent reviewer returns APPROVED. Engine-agnostic — implementer and reviewer can be any two CLIs (or the same one twice). Use when the user says "mediator loop", "blind l

View source on GitHub

More from sapoepsilon/pragmatic-skills

All 9 plugins →

pragmatic

claude

Bundle of all pragmatic-skills. Install once to get everything, including mobile autoship and privacy-safe macOS QA capture.

14 skills

0

mobile

claude

Mobile auto-shipper. Drive a chat request through analyze -> implement -> QA -> PR on a real simulator/emulator/device. The orchestrating agent is the coder — no separate engine CLI. Includes backend/Supabase and Flutter QA setup.

6 skills

0

Persistent session memory for Claude Code backed by an Obsidian vault exposed through an MCP filesystem server. Provides /resume and /save with first-run bootstrap that registers the vault MCP on each new machine.

2 skills

0

Multi-agent end-to-end backend/API PR review: phased orchestrator with parallel review passes, real-request runtime verification against a project-configured non-prod target, and a PR-ready verdict. Auto-configures a per-repo review extension.

1 skill

0

loopcopy

claude

Package the work you are doing right now into one self-contained /loop command and copy it to the clipboard, ready to paste into a fresh session on any OS.

1 skill

0

Privacy-safe macOS QA evidence capture through a user-configured Aqua-session LaunchAgent: signed install verification, clean-desktop staging, visual privacy review, user-owned storage upload, and desktop restoration.

1 skill

0

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer

8 skills · 1 MCP server

ChromeDevTools/chrome-devtools-mcp 55,181

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Maintain mediator-loop?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins9 plugins