By anortham
Miller-powered development workflow with subagent-driven execution, inline review, and Miller-first codebase orientation.
Use when a reported defect or requested tweak looks small and local — a button not disabled, a double-submit, an off-by-one, a wrong label, CSS/styling adjustments, copy changes, config value fixes — before invoking brainstorming, creating a worktree, or running any test suite.
Use when writing code against an external framework, library, or API — especially a version or feature newer than your training data, an unfamiliar dependency, or behavior that may have changed (new directives, breaking changes, renamed options, deprecations, changed defaults).
Use when the user says "razorback debt", "harvesting-debt", "debt ledger", "what did we defer", "list the shortcuts", or "what did we mark to do later" — any request to account for deliberate shortcuts marked with `razorback:` comments.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Use when executing a written implementation plan single-agent — separate-session, single-task, or no-delegation runs.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Miller-powered development workflow for Claude Code, Codex CLI / ChatGPT desktop app, and OpenCode.
Razorback is a skill set for coding-agent harnesses, diverged from Superpowers to add Miller MCP for token-efficient codebase orientation. Plan execution runs through subagent-driven-development on harnesses that support delegation, and executing-plans where delegation is unavailable.
Supported harnesses. Claude Code, Codex CLI / ChatGPT desktop app (rebranded from Codex), and OpenCode get the full plugin: skills, agents, bootstrap, and delegated execution. Cursor is frozen — its plugin support still works and is documented below, but it receives no new work. Copilot CLI is instruction-tier: it picks up razorback's Miller-first ruleset from .github/copilot-instructions.md and nothing else.
AI-assisted development burns tokens on repetitive codebase exploration. Every agent and subagent re-discovers the same code through Glob/Grep/Read chains. Razorback solves this two ways:
search, context, inspect, trace, impact, and workspace — that return targeted context in 1-2 calls instead of 5-8.multi_agent = true in ~/.codex/config.toml so parallel execution skills can dispatch subagentsRazorback is a pure-content plugin (skills, commands, hooks) — no build step or runtime dependencies required. Install paths below are all "pull from GitHub"; most harnesses support one-liner installs.
/plugin marketplace add anortham/razorback
/plugin install razorback@razorback
Scope to a specific project instead of user-wide:
/plugin install razorback@razorback --scope project
Or clone and load locally for development:
git clone https://github.com/anortham/razorback.git
claude --plugin-dir /path/to/razorback
Cursor support is frozen: it works as documented here, but receives no new development.
Cursor has a plugin marketplace, but razorback isn't listed there yet. For now, clone and point Cursor at the local checkout via its plugin-load mechanism:
git clone https://github.com/anortham/razorback.git ~/path/to/razorback
# Then in Cursor: add ~/path/to/razorback to your plugin paths
The plugin manifest at .cursor-plugin/plugin.json declares skills, agents, commands, and hooks.
The ChatGPT desktop app was rebranded from Codex; both use the same install path below.
Tell Codex:
Fetch and follow instructions from https://raw.githubusercontent.com/anortham/razorback/refs/heads/main/.codex/INSTALL.md
Preferred install: use the Codex plugin path documented in .codex/INSTALL.md. It installs razorback from the repo-scoped marketplace entry in .agents/plugins/marketplace.json, then relies on native skill discovery to load the bundled skills at startup.
Manual clone plus ~/.agents/skills/razorback symlink remains the local-development fallback. Delegated execution skills (subagent-driven-development, dispatching-parallel-agents) still require Codex's multi_agent feature.
Detailed docs: .codex/INSTALL.md
Tell OpenCode:
Fetch and follow instructions from https://raw.githubusercontent.com/anortham/razorback/refs/heads/main/.opencode/INSTALL.md
Detailed docs: .opencode/INSTALL.md
Copilot CLI gets the Miller-first ruleset only — no skills, no agents, no delegated execution. Copy razorback's instruction-tier ruleset into the repo you work in; Copilot reads that path natively:
npx claudepluginhub anortham/razorback --plugin razorbackCross-client MCP memory with checkpoints, recall, briefs, and standups for AI-assisted development
Local SQLite-backed code intelligence, content search, and workspace freshness for coding agents. Requires Node.js on PATH (the plugin launcher is a Node script).
Code intelligence server: search, navigation, and refactoring across 34 languages
Agent memory persistence - remember and recall across sessions
Composite workflows that orchestrate Julie (code intelligence), Sherpa (workflow guidance), and Goldfish (persistent memory) for powerful development patterns. Includes TDD Powerhouse, Bug Detective, Smart Session Start, and more.
Battle-tested Claude Code plugin for engineering teams — 38 agents, 156 skills, 72 legacy command shims, production-ready hooks, and selective install workflows evolved through continuous real-world use
One plugin to bridge and delegate across Claude Code, Codex CLI, and Antigravity CLI (agy) — single-source AGENTS.md, shared skills, mirrored hooks and MCP servers, and bidirectional delegation.
70+ Claude Code slash commands across 12 development phases with Dagger-based safety system, multi-dimensional validation, and specialized agents
oh-my-zsh for Claude Code — 11 agents, 34 commands, 26 skills, 15 hooks + 9 examples (21 events), 10 rules, 4 MCP (minimal: playwright, context7, jina-reader, [email protected]). One-line install: curl -fsSL https://raw.githubusercontent.com/sangrokjung/claude-forge/main/install.sh | bash
Multi-agent /workflow development pipeline (planner → plan-review → coder → code-review) with typed handoff contracts, lifecycle hooks, and MCP servers.
Delegate plan execution to Codex CLI via ASP. Part of cc-multi-cli-plugin. Requires the `multi` plugin.