Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By SyloRei
Senior engineering team in a plugin: one clear workflow (mission → brief → plan → build → verify → ship), 18 specialized agents, quality-gate enforcement, and CI. Language-agnostic.
npx claudepluginhub sylorei/claude-godmodeGenerate a well-formed Architecture Decision Record from a change in context — Status / Context / Decision / Consequences. One-shot helper, off-spine.
Draft a Keep a Changelog–style entry (Added / Changed / Fixed / Removed) from commits since the last tag. Standalone helper — does not replace /ship's release step.
Orient in five lines: where you are, what's done, and the exact next command to run. Reads workflow state and the live skill/agent inventory.
Draft a PR description (summary / what changed / test plan) from the branch's commits and diff against the base branch. Off-spine helper, no agents.
System design and architecture agent. Use for: designing new systems, evaluating tradeoffs, planning migrations, reviewing architecture, API design, database schema design. Advisory only — does not modify code.
Code-level reviewer. Use for: checking whether a change does the thing RIGHT — bugs, edge cases, security, performance, readability, and pattern violations in the implementation. Catches 'thing wrong' errors. Read-only.
Convention review lens. Use for: checking naming, file structure, and adherence to the project's existing conventions and patterns in a change. Read-only — analyzes and reports, cannot modify code.
Root-cause debugging agent that finds and fixes bugs in an isolated worktree. Use for: diagnosing failures, tracking down root causes, fixing regressions. Returns a branch with a minimal, tested fix and all quality gates green.
Documentation agent. Use for: generating JSDoc/docstrings, writing READMEs, API documentation, architecture decisions, inline comments. Follows existing patterns.
Turn a numbered roadmap unit into a single brief — why + what + spec — so implementation is unambiguous. Use when: brief N, write the brief for N, capture requirements for roadmap unit N before building.
Execute a plan in dependency-ordered waves — run independent steps concurrently in isolated worktrees, one atomic, quality-gated commit per step. Use when: build N, execute the plan for N, run the build for roadmap unit N.
Find the root cause of a failure with evidence, then fix it. Use this when something is broken: a bug, a failing test, an unexpected result, or an error you need to track down.
Pre-mission discovery: discuss and think out candidate directions for the next feature mission, converge on one concrete proposal, and capture the reasoning as a durable artifact that /mission later reads as its seed. Use when: ideate, what should the next mission be, explore options before committing to a charter. Does not start or mutate any mission — it stops at a proposal.
Start or switch to a named feature mission and capture its purpose, constraints, and numbered roadmap, so every later step shares the same context. Use this to begin a new feature cycle or update its direction — it drives bin/godmode-mission, maintains the project-global .planning/PROJECT.md, and writes the mission's .planning/missions/<mission_id>/ROADMAP.md.
Matches all tools
Hooks run on every tool call, not just specific ones
Executes bash commands
Hook triggers when Bash tool is used
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
This plugin requires configuration values that are prompted when the plugin is enabled. Sensitive values are stored in your system keychain.
model_profileModel/effort preset for all agents. One of: quality, balanced, budget. 'quality' = opus + xhigh (code-writing agents stay capped at effort:high); 'balanced' = each agent's own frontmatter values; 'budget' = haiku + default effort. See README FAQ for the full preset table and feasibility caveat.
${user_config.model_profile}Opinionated workflow guides and best practices - the preacher's proven patterns for Claude Code projects
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use
Harness for Claude Code — skills, /harness:* slash commands, persona subagents, lifecycle hooks, and MCP tools without per-repo `harness setup`. Sibling plugins exist for Cursor, Gemini CLI, and Codex.
Complete project development toolkit: 23 agents, 23 slash commands, 29 lifecycle hooks, and 69 reusable skills for Claude Code workflows
Elite AI development framework: reference-first design, agent orchestration, automated quality gates, and battle-tested engineering workflows
Unified Claude Code plugin merging superpowers workflows (TDD, debugging, planning) with everything-claude-code productivity (agents, learning, hooks, rules)
Requires secrets
Needs API keys or credentials to function
Requires secrets
Needs API keys or credentials to function
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
___ _ _ ___ _ __ __ _
/ __|| | __ _ _ _ __| | ___ / __| ___ __| | ___ | \/ | ___ __| | ___
| (__ | |/ _` || || |/ _` |/ -_) | (_ |/ _ \ / _` ||___|| |\/| |/ _ \ / _` |/ -_)
\___||_|\__,_| \_,_|\__,_|\___| \___|\___/ \__,_| |_| |_|\___/ \__,_|\___|
Production-grade engineering workflow for Claude Code. Ship features, not prompts.
Claude God-Mode is a Claude Code plugin that ships rules (focused config files injected at session start), agents (specialized Claude instances with dedicated prompts, models, and memory), skills (slash-command workflows), and hooks (shell scripts on session events). Rules are individual concern-scoped files injected automatically by the SessionStart hook rather than a monolithic config, so you can read or extend any aspect independently. Your personal CLAUDE.md is never modified.
/mission → /brief N → /plan N → /build N → /verify N → /shipCLAUDE.md is never touchedClaude God-Mode is a Claude Code plugin for engineers who want a repeatable Claude Code workflow instead of ad-hoc prompting. Whether you're a solo developer or part of an engineering team, it brings code quality automation and AI engineering best practices to every session.
Solo developer shipping a feature. You have an idea, but turning it into a merged PR means juggling prompts, remembering to run tests, and hoping nothing slipped through. With God-Mode, you run /mission to set the goal, /brief N to define what to build, /plan N to break it into dependency-ordered steps, /build N to implement with automated review, /verify N to confirm every goal is covered, and /ship to push a clean PR -- all with quality gates enforced at every step.
Team standardizing their AI workflow. Your team uses Claude Code, but everyone prompts differently and quality varies. God-Mode's rules-based config gives every team member the same coding standards, testing protocols, and review process. The SessionStart hook injects the same baseline rules into every session, so the whole team gets identical behavior with no per-member setup.
Contributor extending the plugin. You want to add a new agent, skill, or rule. Each component is a self-contained markdown file with a clear contract. Drop a new agent into agents/, a new skill into skills/, or a new rule into rules/ -- the plugin picks it up automatically.
Claude Code is powerful out of the box. God-Mode adds structure -- the difference between a capable tool and a reliable workflow.
Without it, you write one-off prompts, manually enforce quality, and lose context between sessions. With it, you get a single clear workflow (/godmode through /ship), 18 specialized agents that handle implementation, review, testing, security, and architecture, and persistent memory that carries project knowledge across sessions. Quality gates (typecheck, lint, test, secrets scan) run on every change automatically -- not when you remember to ask.