auto-optimize — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited auto-optimize (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
使用 auto-run-agent 编排 Claude Code 对目标项目进行持续自动优化。
| 轮次 | 维度 | 扫描目标 |
|---|---|---|
| 1 | Bug | 逻辑错误、死锁、TOCTOU、panic 路径、边界条件 |
| 2 | 架构 | 命名冲突、职责混乱、模块耦合、类型设计缺陷 |
| 3 | 重复 | 代码重复、可提取的公共逻辑、copy-paste 痕迹 |
| 4 | 性能 | 不必要的 clone/alloc、O(n²) 路径、阻塞调用 |
| 5 | 测试 | 缺失覆盖、脆弱断言、缺少边界用例 |
| 6 | API | 对标竞品的功能缺口、易用性问题、文档缺失 |
用户可指定维度,否则按项目当前状态自动选择最需要的维度。
对每个发现进行三分类:
FIX — 有明确方案,不破坏公开 API,收益 > 风险
SKIP — 附理由:breaking change / over-engineering / not a bug / intentional design
DEFER — 需要更多信息或用户决策,记录到 TASKS.md 的 backlog 区SKIP 判断标准(加载 rules/ 目录下对应语言的规则):
FIX 任务按依赖排序,生成结构化任务列表:
## 高优先级
- [ ] [BUG] 描述 | 文件 | 方案摘要
- [ ] [BUG] ...
## 中优先级
- [ ] [DEDUP] 描述 | 文件 | 方案摘要
- [ ] [DESIGN] ...
## 架构审查(高/中完成后触发)
- [ ] [ARCH] 全面审查架构合理性,发现问题追加新任务
## 低优先级
- [ ] [STYLE] ...
## Backlog(DEFER)
- [ ] [DEFER] 描述 | 需要的信息auto-optimize)<runner-dir>/
├── memory/
│ ├── TASKS.md # Phase 2 设计的任务列表
│ ├── CONTEXT.md # 项目背景、技术栈、规范、架构概览
│ └── DONE.md # 自动生成
├── workspace/ # 软链接到目标项目
├── logs/
└── config.yamlmax_iterations: 50
max_cost_usd: 0
max_duration: 6h
consecutive_no_progress: 3
stop_when_empty: true
cooldown_duration: 15s
worker_timeout: 30m
use_git_detection: truecd <auto-run-agent 目录>
./orchestrator --dir <runner-dir> --max-iterations 50 --max-cost 0 --max-duration 6tail -f <runner-dir>/logs/orchestrator_*.log — 实时日志cat <runner-dir>/memory/DONE.md — 查看完成记录cat <runner-dir>/memory/TASKS.md — 查看剩余任务规则文件位于 rules/ 目录,按语言分类。扫描时自动加载对应语言的规则。
auto-optimize/
├── SKILL.md
└── rules/
├── universal.md ← 通用规则(所有语言适用)
├── rust.md ← Rust 特定规则
├── python.md ← Python 特定规则
├── typescript.md ← TypeScript 特定规则
└── go.md ← Go 特定规则规则格式:每条规则有 ID、类别、描述、示例。Worker 在扫描和修复时参考这些规则来判断 FIX/SKIP。
~/Desktop/code/AI/<project-name>-runner/<auto-run-agent 目录>~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.