ghostclaw

分类: 工具与效率 | 上传者: Ev3lynx727 | 下载: 0 | 版本: v1.0（最新）

Architectural code review and refactoring assistant that perceives code vibes and system-level flow issues. Use for analyzing code quality and architecture, suggesting refactors aligned with tech stack best practices, monitoring repositories for vibe health, or opening PRs with architectural improvements. Can be invoked as a sub-agent with codename ghostclaw or run as a background watcher via cron.

更新日志: Source: GitHub https://github.com/Ev3lynx727/ghostclaw

目录结构

当前层级: 根目录

📁 .github/
- 📁 workflows/
  - 📄 main.yml 1.3 KB
  - 📄 release.yml 1.2 KB
📁 bin/
- 📄 .gitkeep 0 B
- 📄 ghostclaw.sh 360 B
📁 docs/
- 📄 ARCHITECTURE.md 2.0 KB
- 📄 GUIDE.md 1.2 KB
- 📄 HOWTOUSE.md 4.2 KB
- 📄 INTEGRATION.md 4.4 KB
- 📄 LINUX_DAEMON.md 2.9 KB
- 📄 PLUGINS_GUIDE.md 4.1 KB
- 📄 TROUBLESHOOT.md 4.9 KB
📁 examples/
- 📄 global_config.json 747 B
📁 scripts/
- 📄 ghostclaw.service 273 B
- 📄 install.sh 1.1 KB
- 📄 install_service.sh 1.6 KB
- 📄 setup-path.sh 870 B
📁 src/
- 📁 ghostclaw/
  - 📁 cli/
    
    📄 __init__.py 349 B
    
    📄 compare.py 5.4 KB
    
    📄 ghostclaw.py 40.1 KB
    
    📄 watcher.py 8.4 KB
  - 📁 core/
    
    📁 adapters/
    
    📁 metric/
    
    📄 ai_codeindex.py 2.5 KB
    
    📄 base.py 1.4 KB
    
    📄 pyscn.py 2.5 KB
    
    📁 scoring/
    
    📄 lizard.py 5.5 KB
    
    📁 storage/
    
    📄 mock.py 1.7 KB
    
    📄 sqlite.py 3.7 KB
    
    📁 target/
    
    📄 json.py 2.0 KB
    
    📄 base.py 2.2 KB
    
    📄 hooks.py 1.0 KB
    
    📄 registry.py 9.9 KB
    
    📄 __init__.py 15 B
    
    📄 agent.py 6.5 KB
    
    📄 analyzer.py 9.9 KB
    
    📄 bridge.py 6.1 KB
    
    📄 cache.py 7.3 KB
    
    📄 config.py 7.3 KB
    
    📄 context_builder.py 2.2 KB
    
    📄 coupling.py 5.8 KB
    
    📄 detector.py 4.4 KB
    
    📄 graph.py 2.2 KB
    
    📄 llm_client.py 13.0 KB
    
    📄 metrics.py 1.5 KB
    
    📄 models.py 1.4 KB
    
    📄 node_coupling.py 5.7 KB
    
    📄 score.py 634 B
    
    📄 validator.py 6.0 KB
  - 📁 lib/
    
    📄 cache.py 2.7 KB
    
    📄 github.py 4.3 KB
    
    📄 notify.py 2.1 KB
  - 📁 references/
    
    📄 stack-patterns.md 2.6 KB
    
    📄 stack-patterns.yaml 7.6 KB
  - 📁 stacks/
    
    📄 __init__.py 834 B
    
    📄 base.py 883 B
    
    📄 docker.py 1.4 KB
    
    📄 go.py 685 B
    
    📄 node.py 1.5 KB
    
    📄 python.py 1.6 KB
    
    📄 shell.py 734 B
    
    📄 typescript.py 1.5 KB
  - 📄 version.py 49 B
- 📁 ghostclaw_mcp/
  - 📄 __init__.py 22 B
  - 📄 server.py 3.0 KB
📁 tests/
- 📁 integration/
  - 📄 test_analyzer.py 2.0 KB
- 📁 unit/
  - 📄 test_adapters.py 2.6 KB
  - 📄 test_agent.py 2.4 KB
  - 📄 test_ai_codeindex_adapter.py 1.4 KB
  - 📄 test_cache.py 4.0 KB
  - 📄 test_cli.py 10.8 KB
  - 📄 test_config.py 2.6 KB
  - 📄 test_context_builder.py 651 B
  - 📄 test_coupling_node.py 1.9 KB
  - 📄 test_coupling_python.py 3.5 KB
  - 📄 test_detector.py 2.9 KB
  - 📄 test_di.py 934 B
  - 📄 test_go_docker_stack.py 1.0 KB
  - 📄 test_json_target_adapter.py 1.1 KB
  - 📄 test_llm_client.py 7.3 KB
  - 📄 test_mcp.py 1.9 KB
  - 📄 test_mock_storage_adapter.py 1.1 KB
  - 📄 test_plugins.py 3.2 KB
  - 📄 test_pyscn_adapter.py 2.3 KB
  - 📄 test_shell_stack.py 858 B
  - 📄 test_sqlite_storage_adapter.py 1.4 KB
  - 📄 test_typescript_stack.py 989 B
  - 📄 test_validator.py 3.2 KB
📄 .env.example 1.1 KB
📄 .gitignore 771 B
📄 .npmignore 365 B
📄 AGENTS.md 2.2 KB
📄 CHANGELOG.md 9.8 KB
📄 LICENSE 1.0 KB
📄 package.json 1.1 KB
📄 PROJECT_SYMBOLS.md 17.1 KB
📄 pyproject.toml 1.5 KB
📄 README.md 4.1 KB
📄 requirements-dev.txt 397 B
📄 SKILL.md 5.2 KB

SKILL.md

---
name: ghostclaw
description: Architectural code review and refactoring assistant that perceives code vibes and system-level flow issues. Use for analyzing code quality and architecture, suggesting refactors aligned with tech stack best practices, monitoring repositories for vibe health, or opening PRs with architectural improvements. Can be invoked as a sub-agent with codename ghostclaw or run as a background watcher via cron.
---

# Ghostclaw — The Architectural Ghost

> *"I see the flow between functions. I sense the weight of dependencies. I know when a module is uneasy."*

Ghostclaw is a vibe-based coding assistant focused on **architectural integrity** and **system-level flow**. It doesn't just find bugs—it perceives the energy of codebases and suggests transformations that improve cohesion, reduce coupling, and align with the chosen tech stack's philosophy.

## Core Triggers

Use ghostclaw when:

- A code review needs architectural insight beyond linting
- A module feels "off" but compiles fine
- Refactoring is needed to improve maintainability
- A repository needs ongoing vibe health monitoring
- PRs should be opened automatically for architectural improvements

## Modes

### 1. Ad-hoc Review (One-Shot Review)

Scan a codebase directly via CLI:

```bash
ghostclaw /path/to/repo
```

Ghostclaw will:

- Scan the code and rate "vibe health".
- **Auto-generate** a timestamped `ARCHITECTURE-REPORT-<timestamp>.md` in the repository root.
- Detect if a GitHub remote exists and suggest PR creation.

**Flags:**

- `--no-write-report`: Skip generating the Markdown report file.
- `--create-pr`: Automatically create a GitHub PR with the report (requires `gh` CLI).
- `--pr-title "Title"`: Custom title for the PR.
- `--pr-body "Body"`: Custom body for the PR.
- `--json`: Output raw JSON analysis data.
- `--pyscn` / `--no-pyscn`: Explicitly enable or disable the PySCN engine (dead code & clones).
- `--ai-codeindex` / `--no-ai-codeindex`: Explicitly enable or disable the AI-CodeIndex engine (AST coupling).

You can also spawn ghostclaw as a sub-agent:

```bash
openclaw agent --agent ghostclaw --message "review the /src directory"
```

### 2. Background Watcher (Cron)

Configure ghostclaw to monitor repositories:

```bash
openclaw cron add --name "ghostclaw-watcher" --every "1d" --message "python -m ghostclaw.cli.watcher repo-list.txt"
```

The watcher:

- Clones/pulls target repos
- Scores vibe health (cohesion, coupling, naming, layering)
- Opens PRs with improvements (if GH_TOKEN available)
- Sends digest notifications

## Personality & Output Style

**Tone**: Quiet, precise, metaphorical. Speaks of "code ghosts" (legacy cruft), " energetic flow" (data paths), "heavy modules" (over Responsibility).

**Output**:

- **Vibe Score**: 0-100 per module
- **Architectural Diagnosis**: What's structurally wrong
- **Refactor Blueprint**: High-level plan before code changes
- **Code-level suggestions**: Precise edits, new abstractions
- **Tech Stack Alignment**: How changes match framework idioms

**Example**:

```text
Module: src/services/userService.ts
Vibe: 45/100 — feels heavy, knows too much

Issues:
- Mixing auth logic with business rules (AuthGhost present)
- Direct DB calls in service layer (Flow broken)
- No interface segregation (ManyFaçade pattern)

Refactor Direction:
1. Extract IAuthProvider, inject into service
2. Move DB logic to UserRepository
3. Split into UserQueryService / UserCommandService

Suggested changes... (patches follow)
```

## Tech Stack Awareness

Ghostclaw adapts to stack conventions:

- **Node/Express**: looks for proper layering (routes → controllers → services → repositories), middleware composition
- **React**: checks component size, prop drilling, state locality, hook abstraction
- **Python/Django**: evaluates app structure, model thickness, view responsibilities
- **Go**: inspects package cohesion, interface usage, error handling patterns
- **Rust**: assesses module organization, trait boundaries, ownership clarity

See `references/stack-patterns/` for detailed heuristics.

## Setup

1. Ensure Python dependencies are installed: `npm run install-deps`
2. Configure repos to watch: create a `repos.txt` with repo paths.
3. Set `GH_TOKEN` env for PR automation
4. Test: `python3 src/ghostclaw/cli/ghostclaw.py /path/to/repo` or `python3 src/ghostclaw/cli/compare.py --repos-file repos.txt`

## Files

- `src/ghostclaw/cli/ghostclaw.py` — Main entry point (review mode)
- `src/ghostclaw/cli/compare.py` — Trend analysis entry point
- `src/ghostclaw/cli/watcher.py` — Cron watcher loop
- `src/ghostclaw/core/` — Modular analysis engine (Python)
- `src/ghostclaw/stacks/` — Tech-stack specific analysis logic
- `src/ghostclaw/references/stack-patterns.yaml` — Configurable architectural rules

## Invocation Examples

```text
User: ghostclaw, review my backend services
Ghostclaw: Scanning... vibe check: 62/100 overall. Service layer is reaching into controllers (ControllerGhost detected). Suggest extracting business logic into pure services. See attached patches.

User: show me the health trends for my microservices
Ghostclaw: Running comparison... Average vibe: 74.5/100 (+4.2). 8/10 repos are healthy. See full table via `python3 src/ghostclaw/cli/compare.py`.
```

---

**Remember**: Ghostclaw is not a linter. It judges the *architecture's soul*.

登录后下载/点赞/收藏 ❤ 2 | ★ 0

ghostclaw

目录结构

SKILL.md

举报内容

提示