By lucasmccomb
Team-shared learnings in docs/solutions/. After solving a non-trivial problem, /compound writes a structured markdown doc with YAML frontmatter that later /xplan and /review runs re-inject as grounding. Counterpart to self-improving's personal MEMORY.md.
Periodic maintenance pass over docs/solutions/. For each doc, classify as Keep / Update / Consolidate / Replace / Delete based on staleness, referenced-code existence, and overlap with newer learnings. Run monthly or after a major refactor. Modes - interactive, autofix, report-only. Triggers: compound refresh, clean up solutions docs, docs/solutions maintenance, solution doc audit.
Generate derived markdown artifacts from existing docs/solutions/ entries without mutating the source. Four projection types: qa (Q&A pairs), contradictions (disagreeing entries made explicit), summary (restructured alternative summary), outline (synthesized narrative outline). Output goes to docs/solutions/_reprojections/{type}-{timestamp}.md with traceable source IDs. Triggers: compound reproject, reproject learnings, synthesize solutions, generate qa from solutions, find contradictions in solutions.
After solving a non-trivial problem, extract a durable learning to docs/solutions/ in the current repo. Two modes - Full (parallel research subagents, strict schema, overlap check) and Lightweight (single-pass, direct from current conversation). Writes team-shared knowledge that /xplan and /review later re-inject as grounding. Runs a Discoverability Check so every repo's AGENTS.md or CLAUDE.md points at docs/solutions/. Triggers: compound, capture learning, write solution doc, post-mortem, retro, log this lesson, save this finding.
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.
npx claudepluginhub lucasmccomb/ccgm --plugin compound-knowledgeCaptures 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.
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.
/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.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
AI-powered wiki generator for code repositories. Generates comprehensive, Mermaid-rich documentation with dark-mode VitePress sites, onboarding guides, deep research, and source citations. Inspired by OpenDeepWiki and deepwiki-open.
Claude + Obsidian knowledge companion. Sets up a persistent, compounding wiki vault (Karpathy's LLM Wiki pattern). v1.7 "Compound Vault" + v1.8 methodology modes close 5 of 5 priority gaps from the May 2026 compass artifact. Ships: substrate alignment with kepano/obsidian-skills, default Obsidian CLI transport, hybrid retrieval (contextual prefix + BM25 + cosine rerank per Anthropic's Sept 2024 research), per-file advisory locking for multi-writer safety, pre-commit verifier agent, AND methodology modes (LYT / PARA / Zettelkasten / Generic) for first-class organizational support no other Claude+Obsidian competitor offers. v1.7.x audit closure: every BLOCKER + HIGH + MEDIUM + LOW finding from the v1.7.0 audit is CLOSED or DEFERRED-with-rationale. Optional DragonScale Memory extension (log folds, deterministic addresses, semantic tiling lint, boundary-first autoresearch).
Complete AI coding workflow system. Self-correcting memory + persistent FTS5-indexed research wikis + auto-research loop + multi-LLM council on a single SQLite store. 33 skills, 8 agents, 22 commands, 37 hook scripts across 24 events. Cross-agent via SkillKit.
Full API lifecycle management for Claude Code. Sync collections, generate client code, discover APIs, run tests, create mocks, publish docs, and audit security. Powered by the Postman MCP Server.