By lucasmccomb
Captures permission events, tool failures, and user-correction signals; runs a daily analyzer via direct Anthropic API call; produces a local digest + opt-in Resend email; opt-in real-time security alerts and opt-in confidence-gated auto-apply. Cross-clone-safe via fcntl file locks. Webhook publisher seam is dormant by default.
Inspect the queue of pending autoheal proposals from the last 7 days,
Print the markdown digest for today (default) or a specific past date.
Suppress a specific autoheal proposal for N days. The proposal will not
Edit `~/.claude/autoheal/config.json` to enable, disable, or inspect
Inspect autoheal status and learn the slash command surface. Read-only:
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.
Modular configuration system for Claude Code - pick the modules you want, install in seconds. Works with Claude Code CLI, VS Code, Cursor, the macOS Claude app, and any other editor with Claude Code support.
CCGM is a curated collection of 71 configuration modules for Claude Code. Instead of hand-crafting rules, hooks, commands, and permissions from scratch, you pick modules and install them with a single command.
Each module is self-contained with its own README, so you can also copy individual files manually without the installer.
CCGM places files into ~/.claude/ (global) or .claude/ (project-level):
| Directory | What | How Claude Uses It |
|---|---|---|
rules/*.md | Behavior rules | Loaded automatically at session start |
commands/*.md | Slash commands | Available as /commit, /pr, etc. |
agents/*.md | Subagent prompts | Reusable prompts invoked by commands and skills via the Task tool |
hooks/*.py | Workflow hooks | Triggered on Claude Code events |
settings.json | Permissions | Controls tool access and auto-approval |
Paste the block below into a fresh Claude Code session. The agent detects your environment, picks a preset, runs the installer, and reports what was installed. No flags, no shell environment to configure first.
Install CCGM (Claude Code God Mode) for me.
Steps:
1. Detect my OS (uname -s), shell ($SHELL), and home directory ($HOME).
2. Clone the repo if it does not already exist:
git clone https://github.com/lucasmccomb/ccgm.git ~/code/ccgm
If it already exists, pull the latest main:
cd ~/code/ccgm && git fetch origin && git checkout main && git pull --ff-only origin main
3. Read the available presets: ls ~/code/ccgm/presets/
Available presets and what they include:
- minimal : global-claude-md, autonomy, git-workflow
- standard : the above + identity, hooks, settings, commands-core, commands-utility
- team : standard core + github-protocols, code-quality, systematic-debugging, verification
- cloud-agent : large set for power users running autonomous agents
- full : every stable module
Based on what you know about my workflow, recommend one preset. Ask me to confirm or pick a different one before continuing. (One question only — do not ask anything else.)
4. Check what is already installed by looking at ~/.claude/rules/, ~/.claude/commands/, ~/.claude/hooks/. List any CCGM files already present and note you will skip overwriting them.
5. Read ~/.claude/settings.json if it exists and note its content. The installer will merge non-destructively — it will not delete keys that are already there.
6. Run the installer:
cd ~/code/ccgm
CCGM_NON_INTERACTIVE=1 \
CCGM_USERNAME="$(gh api user --jq '.login' 2>/dev/null || echo '')" \
./start.sh --preset <chosen-preset>
7. Verify the install succeeded by checking that these paths exist:
~/.claude/rules/
~/.claude/CLAUDE.md (if global-claude-md was in the preset)
List the files now present in ~/.claude/rules/ and ~/.claude/commands/.
8. Report: which preset was installed, which modules were skipped (already present), and any errors.
For blocks pre-selecting a specific preset, and for how to dry-run this safely, see docs/install-via-agent.md.
npm install -g @anthropic-ai/claude-code)The installer checks for Claude Code, additional tools (jq, Python 3, gh CLI), and offers to install any that are missing.
git clone https://github.com/lucasmccomb/ccgm.git
cd ccgm
./start.sh
The interactive setup handles everything: prerequisite checks, module selection, and configuration. No flags needed.
Spec-driven development where E2E vision specs define target behavior. /atdd reads Playwright specs, iteratively builds app code until all tests pass, then ships.
/brainstorm - hard gate that forbids code, scaffolding, or implementation until a design spec is written and user-approved. Proposes 2-3 approaches with tradeoffs, writes a design doc, self-reviews for TBDs and contradictions, then hands off to /xplan. Pairs with /ideate (which refines the concept) to enforce spec-before-plan-before-code.
Configure Claude as a fully autonomous Staff-level engineer who executes tasks end-to-end without asking unnecessary questions.
Rules for browser automation tool selection: Chrome extension, Playwright, and WebMCP. Includes verification priority order and UI verification workflow.
/adrev - adversarial review of a plan or any entity (file, doc, PR, issue, directory, or stated concept). Dispatches a separate adrev-reviewer agent that attacks premises, hunts failure modes, and steelmans the case against. Plan targets get findings incorporated into the plan automatically unless told not to; all other targets get a report.
npx claudepluginhub lucasmccomb/ccgm --plugin autohealHarness-native ECC plugin for engineering teams - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
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
Efficient skill management system with progressive discovery — 410+ production-ready skills across 33+ domains