The command center for a complete Claude Code workflow — hooks, rules, methodology, and the connective tissue between every tool in the ecosystem.
Built through 500+ real-world AI collaboration sessions by a non-developer. Every hook, every rule, every framework earned its place by solving an actual problem.
┌─────────────────────┐
│ cc-empire │
│ hooks + rules + │
│ methodology + glue │
└──────────┬──────────┘
│
┌────────────┬───────────┬──────────┼──────────┬────────────┬────────────┐
│ │ │ │ │ │ │
┌────┴────┐ ┌────┴────┐ ┌────┴───┐ ┌────┴────┐ ┌───┴───┐ ┌─────┴─────┐ ┌────┴────┐
│ Memory │ │ Content │ │Pipeline│ │ Remote │ │ Multi │ │ Clone │ │Workflow │
│ │ │ │ │ │ │ Control │ │Session│ │ │ │Orchestr.│
│recallnest│ │alchemy+│ │alchemy │ │ TG + │ │studio │ │ digital │ │orchestr.│
│ │ │publisher│ │ new │ │ WX │ │ │ │ clone │ │ │
└─────────┘ └─────────┘ └────────┘ └─────────┘ └───────┘ └───────────┘ └─────────┘
| Module | Stars | Description | Category |
|---|---|---|---|
| recallnest | 8 | Persistent memory via LanceDB. Hybrid retrieval, 40 MCP tools | Core |
| content-alchemy | 16 | 5-stage article pipeline with multi-perspective review | Content |
| content-publisher | 3 | Image generation, layout, and WeChat publishing | Content |
| workflow-orchestrator | new | Natural language pipeline: ideation, multi-role review, auto-routing | Orchestration |
| telegram-ai-bridge | 7 | Run N parallel CC sessions from your phone | Remote |
| wechat-ai-bridge | 4 | Full CC in WeChat, not an API wrapper | Remote |
| claude-code-studio | 2 | Multi-session collaboration platform | Orchestration |
| digital-clone-skill | 1 | Build digital clones from corpus data | Content |
All modules are optional. Install what you need.
git clone https://github.com/AliceLJY/cc-empire.git
cd cc-empire
bash install.shThe installer will:
- Check prerequisites (Claude Code, git, etc.)
- Show available modules — pick what you need
- Install hooks into
~/.claude/hooks/ - Set up CLAUDE.md and workflow templates
- Clone selected module repos
Production-grade hooks covering all 6 Claude Code lifecycle events.
Safety Guards
| Hook | Trigger | What it does |
|---|---|---|
bash-guard.sh |
PreToolUse:Bash | Blocks rm, enforces tmux for dev servers, PR guards |
edit-guard.sh |
PostToolUse:Edit | README bilingual check, API signature change alerts |
secret-guard.sh |
UserPromptSubmit | Detects API keys/secrets before they leak |
Workflow Automation
| Hook | Trigger | What it does |
|---|---|---|
auto-commit.sh |
Stop | Reminds about uncommitted changes at session end |
nag-reminder.sh |
PostToolUse | ReAct drift detection — nudges observation notes |
track-edit.sh |
PostToolUse:Edit | Tracks which repos were touched per session |
Lifecycle Management
| Hook | Trigger | What it does |
|---|---|---|
load-context.sh |
SessionStart | Injects identity and project status on startup |
pre-compact.sh |
PreCompact | Saves active state before context compression |
session-summary.sh |
Stop | Auto-generates session index for later lookup |
Quality Checks
| Hook | Trigger | What it does |
|---|---|---|
ts-check.sh |
PostToolUse:Edit | Auto TypeScript syntax check after edits |
Feedback Capture
| Hook | Trigger | What it does |
|---|---|---|
rating-capture.sh |
UserPromptSubmit | Captures 1-10 ratings for quality tracking |
All hooks support profile control (CC_HOOK_PROFILE=off to disable all) and individual disable (CC_DISABLED_HOOKS=hook1.sh,hook2.sh).
See docs/hook-lifecycle.md for the complete lifecycle diagram.
Distilled from 500+ sessions into reusable patterns. Located in rules/.
Methodology — How to work with AI
| Rule | What it solves |
|---|---|
| research-plan-implement | Three-stage discipline. No skipping. |
| react-loop | Act → Observe → Reflect → Record. Every step. |
| task-contracts | Define completion criteria before starting |
| scope-drift-detection | Catch when work drifts from the original goal |
| harness-engineering | Shape AI behavior through rules, not hope |
| skill-evolution | How skills improve through feedback loops |
Thinking Frameworks — How to think clearly with AI
| Framework | What it does |
|---|---|
| anti-sycophancy | Neutral prompts that get honest answers |
| bias-correction-matrix | Systematic bias detection and correction |
| xy-problem-detection | Catch when means and goals are misaligned |
| confidence-impact-filter | Prioritize by confidence level and impact |
| completion-taxonomy | DONE / DONE_WITH_CONCERNS / BLOCKED / NEEDS_CONTEXT |
Borrowed Patterns — Proven techniques adapted for AI workflows
| Pattern | Origin |
|---|---|
| boil-the-lake | Exhaustive enumeration before optimization |
| failure-modes-five-layers | Systematic failure analysis |
| measurable-outcome | Every skill needs a measurable success criterion |
| report-first-pattern | Report findings before acting on them |
| two-stage-classification | Rough sort, then fine-grade |
Architecture — System design patterns
| Doc | Covers |
|---|---|
| memory-architecture | How persistent memory is structured |
| confidence-tagging | Tagging claims with confidence levels |
| reply-discipline | Scan before replying, don't miss items |
- CLAUDE.md.example — Project contract template (execution rules, verification, reply discipline)
- workflow.md — Research → Plan → Implement methodology with ReAct loop
- memory/ — Memory index structure (MEMORY.md + identity + feedback templates)
| Variable | Default | Purpose |
|---|---|---|
CC_HOOK_PROFILE |
standard |
Set to off to disable all hooks |
CC_DISABLED_HOOKS |
— | Comma-separated list of hooks to skip |
CC_MEMORY_DIR |
auto-detect | Override project memory directory |
CC_GITHUB_ORGS |
— | Your GitHub org names (comma-separated), for PR guard |
CC_NAG_THRESHOLD |
5 |
Tool calls before ReAct reminder triggers |
Edit ~/.claude/hooks/repos.conf to add your project directories:
TRACKED_REPOS=(
"$HOME/Projects/my-app"
"$HOME/Projects/my-lib"
)This project was built by a non-developer through AI collaboration. The perspective is different from most CC workflow tools:
- Cross-domain, not just coding — Writing pipelines, bot operations, remote control, not just TDD
- Production-tested rules — Every rule exists because its absence caused a real problem
- Memory as infrastructure — Persistent memory isn't optional; it's how the AI gets better over time
- Honest methodology — Anti-sycophancy prompts, neutral verification, confidence tags
- First-principles thinking — Patterns are cross-domain; a writing review framework becomes a code review framework
See docs/architecture.md for how modules work together.
Issues and PRs welcome. If you've built hooks or workflow rules that made your CC life better, share them.
MIT