Dotforge
插件 已验证 活跃Behavior governance for Claude Code — declarative runtime policies on tool calls (search-first, no-destructive-git, verify-before-done, …) compiled to PreToolUse hooks, plus configuration governance: 18 skills, 7 agents, 16 stacks, audit scoring, practices pipeline.
To enforce consistent and high-quality Claude Code configurations across projects, improving developer productivity and reducing configuration drift.
功能
- Declarative runtime policies on tool calls
- Compiled PreToolUse hooks for enforcement
- Cross-project configuration governance
- Audit scoring and practices pipeline
- Stack and agent management
使用场景
- Standardizing Claude Code configurations across a team's projects.
- Enforcing security and best practices in AI-assisted development workflows.
- Automating the setup and maintenance of project-specific Claude Code configurations.
- Auditing and scoring the quality of Claude Code configurations over time.
非目标
- Replacing Claude Code itself
- Directly managing code implementation beyond configuration and behavior.
- Providing AI models or core LLM functionalities.
实践
- Code quality
- Security
- Configuration management
- Workflow automation
- Best practices
- Auditability
先决条件
- Claude Code CLI
- bash (macOS, Linux, WSL)
- python3 (optional, for JSON validation and some hooks)
- jq (optional, for hook input parsing)
安装
请先添加 Marketplace
/plugin marketplace add luiseiman/claude-kit/plugin install claude-kit@dotforge包含 19 个扩展
Skill (19)
Audits the Claude Code configuration of a project against the dotforge template. Generates a report with score and gaps.
Compare Claude Code output with full config vs minimal config using standardized tasks per stack.
Initializes the Claude Code configuration in a new or existing project using the dotforge template.
Captures an insight or practice discovered during work and registers it in the dotforge practices/inbox.
Shows what changed in dotforge since the project's last sync, to decide whether running /forge sync is worthwhile.
Extract domain knowledge from existing project sources and generate domain rules. Also handles vault sync and domain listing.
Export dotforge configuration to other AI code editors (Cursor, Codex, Windsurf, OpenClaw).
Manage dotforge v3 behavior governance — view status, toggle behaviors, adjust strictness. Use when the user asks about active behaviors, wants to disable one for the current session, or adjust escalation thresholds.
Quick-start Claude Code configuration. Auto-detects stack, asks 4 questions to understand the project, generates complete config.
Scan project code to detect patterns, dependencies, and conventions. Propose domain rules based on what the code actually does.
Install an MCP server template from dotforge into a project or global Claude Code config with a single command.
Generate a Claude Code plugin package from the current project's dotforge configuration, ready for marketplace submission.
Restore a project's .claude/ directory to the dotforge template from scratch, with backup and rollback option.
Analyze which rules are actively used vs inert. Detect coverage gaps. Recommend pruning to reduce token consumption.
Fetch .claude/ configs from curated repos in sources.yml, compare against dotforge template, report novel patterns.
Analyze past Claude Code sessions to extract patterns, metrics, and recommendations.
Update an existing project's Claude Code configuration against the current dotforge template, without losing local customizations.
Process the practices inbox, evaluate, incorporate into dotforge, and suggest propagation to projects.
Fetch official Anthropic/Claude Code docs, detect changes relevant to dotforge, report deltas.
质量评分
已验证类似扩展
Dotforge Stack Python Fastapi
100Python 3.12+ with FastAPI, async/await, type hints, and Ruff linting rules for Claude Code.
Karpathy Coder
100Active coding discipline enforcer based on Karpathy's 4 principles: surface assumptions, keep it simple, make surgical changes, define verifiable goals. Ships 4 Python tools (complexity_checker, diff_surgeon, assumption_linter, goal_verifier), a review agent, /karpathy-check slash command, and a pre-commit hook. All tools stdlib-only.
Autoresearch Agent
100Autonomous experiment loop that optimizes any file by a measurable metric. 5 slash commands, 8 evaluators, configurable loop intervals (10min to monthly).
Dotforge
100Node.js 20+ with Express/Fastify, TypeScript, and ESM module rules for Claude Code.
Deployhq
100使用 DeployHQ CLI 部署代码、管理服务器和自动化基础架构
Vue Skills Bundle
99Install all Vue.js skills at once, including best practices, testing, router, Pinia, JSX, Options API, debug guides, and composable patterns.