claude

ralph

Ralph Loop — an autonomous agentic coding workflow with sandbox isolation, scoped memory, and self-managing task iteration.

1 on GitHubv0.1.9updated 4 days ago
/

Plugin ralph from marketplace zaksak in zakattack9/agentic-coding. Commands read from the repo's manifest — 4 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use and it starts local MCP servers. The exact commands are listed below; read them before installing.

What it installs

Skills (4)

  • ralph-archive

    Archive the current Ralph Loop and reset state files for the next loop

  • ralph-init

    Initialize a new Ralph Loop in the current project with state files from templates

  • ralph-install

    Install Ralph Loop scripts and templates into the current project's .ralph/ directory

  • ralph-plan

    Interactively generate a PRD and task list for a Ralph Loop — invoke to plan a feature before running ralph.sh

Subagents (4)

  • ralph-docs

    Researches library and framework documentation via Context7 for Ralph Loop planning. Use during /ralph-plan when the feature involves specific technologies where API details, configuration, or best practices matter.

  • ralph-explore

    Explores and analyzes project codebases for Ralph Loop planning. Use during /ralph-plan to understand project structure, tech stack, existing patterns, and files relevant to a proposed feature.

  • ralph-plan-tasks

    Architects detailed task hierarchies for Ralph Loop execution. Use during /ralph-plan after research and user requirements are gathered to produce optimal story breakdowns sized for fresh context windows.

  • ralph-web

    Performs web research for Ralph Loop planning. Use during /ralph-plan when the feature involves external services, third-party APIs, emerging patterns, or technology decisions where up-to-date information matters.

MCP servers (1)

  • context7

    runs: npx -y @upstash/context7-mcp

Hooks (3)

  • PostToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/context_monitor.py

  • Stop

    ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/stop_loop_reminder.py

  • SessionStart

    rm -f /tmp/claude-context-alerts-*

View source on GitHub

More from zakattack9/agentic-coding

All 10 plugins →

spec-ops

claude

A spec-driven development workflow that turns a rough idea into a verified implementation. It elicits and hardens an acceptance-criteria-first spec against your codebase, compiles it into an execution driver, then checks the built code against every criterion — with read-only adversarial judges gating quality at each stage and every spec change committed automatically. When OpenAI Codex CLI is available it adds an optional, fail-open second judge of a different provider, so every quality gate is cross-checked rather than one model auditing itself.

6 skills · 3 agents

1

Run a small team's entire software lifecycle on GitHub Projects v2 — deterministic, free, GitHub-native, and with no metered AI. It provisions a golden-template board and repo automation across an org, then drives work from issue intake through sprint planning and the full branch → PR → merge flow with check-gated, never-squashed merges, kept safe by GitHub App-token writes and skill-scoped guards.

8 skills

1

skill-ops

claude

Self-hosting toolkit for managing this skills marketplace: setup-project, promote-skill, sync-skill, new-skill, new-plugin, list-skills, skills-doctor.

7 skills

1

Manage your Claude Code skills and plugins from inside any project — switch which plugins are active, publish and sync local skills to a central marketplace, and diagnose and auto-repair a broken setup. Adapts to any repo layout and delegates skill authoring to the native skill-creator.

5 skills

1

codex

claude

Run the OpenAI Codex CLI from inside Claude Code as a cross-model escape hatch: hand a one-off review, question, or write task to a different provider's model for a second opinion, grounded in your repo with web search always on. Every call routes through one fail-open bridge — if Codex is absent, unauthenticated, or broken the skill reports and stops rather than answering as Claude, and Codex's output is surfaced verbatim as untrusted external text. Assumes an OpenAI-authenticated Codex setup.

3 skills · 1 agent

1

A git worktree workflow for running multiple Claude Code sessions in parallel — no restarts, no manual checkouts. Built on native worktrees, it covers the full lifecycle from spinning up an isolated worktree to finishing it through a guarded, never-squashed PR merge, with a live dashboard of in-flight work and deterministic guards against squash merges and committing unresolved conflicts.

4 skills

1

Maintain ralph?

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 plugins10 plugins