awesome-code — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited awesome-code (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.
本技能用于“复杂开发任务”的多代理编排：确定性脚本只负责路径发现、Agent 摘要收集、配置约束读取和 required route 可用性门禁；任务理解、Agent 选择与执行策略由 AI 自主完成。
bensz-collect-bugs 规范记录到 ~/.bensz-skills/bugs/，不要直接修改用户本地已安装的 skill 源码；若有 workaround，先记 bug，再继续完成任务。gh 上传新增 bug 到 huangwb8/bensz-bugs；不要 pull / clone 整个仓库。在调用任何脚本之前，必须先运行 scripts/get_path.py 动态发现真实安装路径，并使用返回的绝对路径执行后续命令（避免硬编码 ~/.claude/skills/ / .claude/skills/）。
python3 ~/.claude/skills/awesome-code/scripts/get_path.py
python3 ~/.codex/skills/awesome-code/scripts/get_path.py
# 或（项目级安装）
python3 .claude/skills/awesome-code/scripts/get_path.py
python3 .codex/skills/awesome-code/scripts/get_path.py从 JSON 输出中读取：
skill_rootexecutable_scripts.*（例如 executable_scripts.agent_coordinator）agents/*/SKILL.md frontmatter 摘要提取、配置加载、Agent 缺失检查dispatch_guidance.minimal_change_scope_defaultdispatch_gate 阻塞继续执行dispatch_receipts 才能证明门禁已被满足SKILL.md| role | 领域 |
|---|---|
| tdd-workflow | TDD 测试驱动开发 |
| systematic-debugging | 系统化调试与根因分析 |
| code-reviewer | 代码审查与质量保证 |
| git-workflow | Git 工作流与版本控制 |
| frontend-specialist | 前端开发与组件设计 |
| backend-specialist | 后端开发与 API 设计 |
| devops-specialist | DevOps 与自动化运维 |
| security-specialist | 应用安全与合规 |
| documentation-specialist | 技术文档与 API 文档 |
| context-optimizer | 上下文管理与优化 |
| brainstorming | 交互式设计优化 |
| mirror-optimizer | 镜像源优化 |
| writing-plans | 实施计划与任务拆解 |
| multi-agent-coordinator | 多代理协调 |
get_path.py，拿到 executable_scripts.agent_coordinator 的绝对路径。agent_coordinator.py 收集规划上下文，读取 available_agents、config_constraints、dispatch_guidance 与 dispatch_gate。dispatch_gate.can_proceed = false：blocking_reason 与 missing_agentsavailable_agents 的 descriptionsingle-pass、focused-agent、parallel 或 sequentialawesome-code/agents/{role}/SKILL.mdconfig_constraints.required_routes 适用，该 route 中的 agents 视为 requireddispatch_guidance 的最小变更边界dispatch_receiptsagent_coordinator.py 不再输出 recommended_agents、confidence 或 execution_plan。这些属于 AI 的语义规划职责。
脚本输出至少包含：
planning_modeavailable_agentsagent_countconfig_constraints.required_routesdispatch_gate.can_proceeddispatch_gate.blocking_reasondispatch_gate.missing_agentsdispatch_guidancesystematic-debugging；先根因，后修复。tdd-workflow。security-specialist。frontend-specialist；需要先探索方向时可先用 brainstorming。backend-specialist。devops-specialist。documentation-specialist。writing-plans 与 multi-agent-coordinator。最小示例：
python3 ~/.claude/skills/awesome-code/scripts/get_path.py
python3 /ABS/PATH/awesome-code/scripts/agent_coordinator.py "fix login bug"注意：脚本路径以 get_path.py 输出为准。
scripts/get_path.py：输出 skill_root 与可执行脚本绝对路径（JSON）scripts/agent_coordinator.py：Agent 摘要收集 + 配置约束 + dispatch_gatescripts/subagent_policy.py：读取 required routes 并校验配置中 required route agents 是否可用scripts/subagent_dispatch_audit.py：生成 dispatch_manifest 并校验 dispatch_receiptsscripts/create_test_session.py：创建 A/B 轮会话目录与计划骨架（便于追溯）scripts/test_runner.py：运行测试/覆盖率scripts/code_analyzer.py：静态分析与质量检查scripts/performance_benchmark.py：基准测试与报告awesome-code/config.yaml:skill_info.version 维护；SKILL.md 不记录版本历史。awesome-code/config.yaml:multi_agent.enabled_agentsawesome-code/config.yaml:multi_agent.dispatch_policy.*awesome-code/config.yaml:tdd、awesome-code/config.yaml:code_review 等awesome-code/CHANGELOG.mdawesome-code/references/tdd-best-practices.mdawesome-code/references/debugging-systematic.mdawesome-code/references/code-review-checklist.mdawesome-code/references/git-workflow.mdawesome-code/references/multi-agent-patterns.mdawesome-code/references/context-optimization.mdawesome-code/references/CRITICAL_THINKING_GUIDE.mdawesome-code/references/A_ROUND_PLAN_TEMPLATE.mdawesome-code/references/CONSTRUCTIVE_SUGGESTION_GUIDELINES.mdawesome-code/references/ISSUE_DISCOVERY_TECHNIQUES.mdawesome-code/references/ANTI_PATTERNS_LIBRARY.mdawesome-code/references/SCRIPT_PATH_STRATEGY.md~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.