Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add flanliulf/SpecLite --skill speclite-brownfield-backend-tech-stack-diggergit clone --depth 1 https://github.com/flanliulf/SpecLiteWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/flanliulf/speclite/speclite-brownfield-backend-tech-stack-digger)<a href="https://agentmods.dev/skills/flanliulf/speclite/speclite-brownfield-backend-tech-stack-digger"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-brownfield-backend-tech-stack-digger/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/flanliulf/speclite/speclite-brownfield-backend-tech-stack-digger"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-brownfield-backend-tech-stack-digger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00135 | $0.01253 |
| Opus 5 | $0.00068 | $0.00626 |
| Sonnet 5 | $0.00027 | $0.00251 |
| Haiku 4.5 | $0.00014 | $0.00125 |
Grade A, and why
speclite-brownfield-backend-tech-stack-digger scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
[Overview(技能说明)] Speclite Brownfield Backend Tech Stack Digger 是 1-analysis 阶段的通用后端技术栈报告契约。它不绑定 Java、Node.js、Python 或任何单一生态,只规定如何基于代码事实抽取技术栈、标注证据和写入用户指定输出目录。
[Core Capabilities(核心能力)]
- 输出目录参数化:从用户请求中解析 {output-dir} 和可选 {report-name},默认生成 {output-dir}/backend-tech-stack.md。
- 仓库与模块发现:识别 monolith、multi-module、monorepo、service directory 和 backend entrypoint,定位后端边界与构建入口。
- 代码事实提取:读取构建声明、依赖锁定文件、运行配置、部署配置、数据库迁移、源码入口和框架标识;历史文档只作为候选线索。
- 版本解析优先级:优先使用锁文件、resolved dependency graph、运行镜像和工具链声明;直接依赖声明次之;无法确认时标记 unknown。
- 技术栈归类:按语言、运行时、包管理/构建工具、Web/API 框架、Web server、数据库、MQ、缓存、数据访问、调度、文件存储、安全认证、观测和测试等类别输出。
- 证据链接与不确定性标注:每个关键版本必须带来源说明;服务端外部版本无法由代码证明时明确写为需要运维确认。
- Markdown 报告生成:按 assets/tech-stack-report-template.md 生成面向交付的清单式文档,并追加证据摘要。
[Workflow(执行流程)]
本 Skill 使用顺序分析工作流。详细证据矩阵、版本解析规则和输出模板约束见 references/tech-stack-digger-workflow.md。
1. 解析用户输入,确认 `{project-root}`、`{output-dir}` 和 `{report-name}`。若缺少 `{output-dir}`,必须先询问;不得写入默认项目根目录。
2. 创建或确认 `{output-dir}`,默认报告文件名为 `backend-tech-stack.md`。若目标文件已存在,先读取并说明将覆盖、追加或生成带时间戳文件;用户未授权时不覆盖。
3. 扫描仓库结构、语言生态和构建入口。若识别到已有专属生态 Skill 可提供更精确解析,优先建议或路由到对应专属 Skill;未命中时按通用证据规则分析。
4. 读取运行配置和源码证据,补充数据库、Redis、MQ、调度、文件存储、安全认证、服务发现、网关、监控和测试工具事实。
5. 按证据优先级合并事实。冲突时保留全部候选、标注来源和优先级,不自行猜测生产运行版本。
6. 使用 `assets/tech-stack-report-template.md` 输出 Markdown:先给出用户要求的编号清单,再给出证据摘要、未确认项和核验命令。
7. 写入 `{output-dir}/{report-name}` 后,检查文件存在、标题、编号清单和 evidence anchors;最终回复只给出路径、核心发现和无法确认项。
[Notes(注意事项)]
- 本 Skill 是分析与文档生成工具,不修改业务源码、构建配置或运行配置。
- 代码事实优先于 README、历史方案、聊天记录和人工记忆;文档事实必须能被构建文件、配置文件或源码交叉验证后才能写成确定结论。
- 数据库 Server、消息中间件 Server、缓存 Server、对象存储 Server 等外部服务端版本通常不能仅由应用仓库证明;只能在配置、Compose、Helm、运维脚本或锁定镜像中找到证据时写确定版本。
- 依赖版本来自生态专属解析机制时,必须写明来源,例如 lockfile、resolved dependency graph、constraints file、runtime image 或 internal framework baseline。
- 生成报告必须包含 Generated By(生成来源) 标注:speclite-brownfield-backend-tech-stack-digger。
- 如用户要求更新 _speclite/tech-stack.md,必须先确认这是目标输出文件;否则只写入用户指定目录。
[Generation Metadata(生成信息)] 本 Skill 由 skills-creator 根据既有后端项目技术栈分析流程提取生成。后续修改必须同步更新 SKILL.md、SKILL.en.md、CHANGELOG.md,并同步 forge/ 与 SpecLite assets 源目录。
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 50 lines · 135 tokens per session scan A 44e8b4f771fe
speclite-brownfield-backend-tech-stack-digger is a skill published in the GitHub repository flanliulf/SpecLite (4 stars, last pushed 2mo ago), licensed MIT. It adds 135 tokens to every session and 1,253 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
API Design Checklist
Naming, status-code, error-shape, and versioning conventions for keeping an API internally consistent as it grows.
Backend Test Patterns
Guidance for covering the failure and edge paths of a backend change — bad input, concurrent writes, partial failure — not just the happy path.
API Discoverability for Agents
Making self-hosted services agent-discoverable — bake in a machine-readable API description (OpenAPI spec or a minimal API.md) when building, and discover-first (spec paths, repo search) before probing when integrating.
Layered Architecture
Controller → service → repository layering, DTO boundaries, @Transactional placement, and exception hierarchy.
Contract-First Development
How to define, document, and maintain the shared contract between frontend and backend.
Full-Stack Error Handling
Error propagation patterns — backend error shape to API response to frontend fetch wrapper to UI state.