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 BackToCimaCoppi/Praxis --skill legacy-archaeologygit clone --depth 1 https://github.com/BackToCimaCoppi/PraxisWrote 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/backtocimacoppi/praxis/legacy-archaeology)<a href="https://agentmods.dev/skills/backtocimacoppi/praxis/legacy-archaeology"><img src="https://agentmods.dev/badge/skills/backtocimacoppi/praxis/legacy-archaeology/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/backtocimacoppi/praxis/legacy-archaeology"><img src="https://agentmods.dev/badge/skills/backtocimacoppi/praxis/legacy-archaeology.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 | $0.00105 | $0.08427 |
| Opus 5 | $0.00053 | $0.04214 |
| Sonnet 5 | $0.00021 | $0.01685 |
| Haiku 4.5 | $0.00011 | $0.00843 |
Grade A, and why
legacy-archaeology 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 421 lines — stays where its author put it; the contents beside it link to each section on GitHub.
legacy-archaeology（老代码考古）
把一个黑盒老项目反推成「树形下钻、业务/库/接口讲清」的知识库，给后续重构的 AI 做背景注入。 承诺只到「边界内可审计覆盖 + 残余风险显式登记」——不吹「我没漏」，只保证「我已识别的盲区、未证实项、未获取的真值源都显式登记了」。
这个 skill 是一个编排器，不是文档生成器。它指挥主 agent 粗扫、切块、派出 agent team 逐模块调查，把结果汇聚成一棵 README 层层索引的知识库树。一个项目一棵树，多个项目共享一个 平台层调用图。重构 AI 平时只读 L1，要哪块钉哪块往下读：省上下文，又能审计到每一处盲区。
§1 干什么 / 不干什么（边界）
1.1 只产三层，不碰其余
- 产出：业务逻辑 / 数据库 / 接口。这三层讲清楚，足够给重构 AI 注入背景。
- 不碰：需求文档、代码实现细节、测试。它们要么是重构后才重写的（需求），要么是被替换掉的 （代码、测试）。把它们写进来只会增重、过期、抢上下文。
- 不描述代码：讲的是「系统做什么决策、存什么数据、暴露什么契约」，不是「类怎么继承、方法怎么调」。 描述代码 = 把旧包袱原样搬进新系统。
1.2 读者是 AI，不是人
- 风格索引重、表格化、叙事轻。每个目录一个 README 当导航节点，逐层下钻。
- 不写给人读的连贯散文；写给 AI 检索：标题密、锚点全、状态标注清楚。
1.3 一次性快照
- 老项目不再大改、不会继续腐烂，所以不设防过期机制。这是某一时刻的考古快照，带「快照批次号」。
- 推论：不必为「文档与代码持续同步」付出任何设计成本——那是 doc-layer-system 的活，不是这里的活。
1.4 承诺口径（地基，全文不得违反）
本 skill 不承诺「业务逻辑零遗漏」。 白盒静态扫描无法证明「我枚举出来的 = 系统里全部」， 把无法证明的东西写成承诺就是自欺。
本 skill 承诺的是：① 边界内可审计覆盖（写下来的每条都有源码锚点、可回查）； ② 残余风险显式登记（没覆盖到的、没证实的、失传的，全部明确列出来，不藏）。
任何产物、任何对账，禁止出现「已查全 / 零遗漏 / 完整」字样。只能说「在已知枚举边界内已覆盖， 未覆盖部分见残余风险清单」。
1.5 与其他 skill 的边界
本 skill 与 code-to-guide、code-to-7layer 机制有重叠，但定位不同。逐机制区别见
references/与现有skill边界对照.md。一句话：本 skill 只产「重构背景知识索引」，不产需求结论、
不产七层正式真值；能复用的已验证机制（fan-out、证据分级、硬暂停）尽量复用，不另造轮子。
§2 产出落点 & 路径命名规范（索引承重墙）
这个 skill 的路径就是索引本身。 重构 AI「读 L1 → 钉下去」靠的全是各层 README 里的下钻链接， 链接就是相对路径。命名不钉死 → 增量建库（一次一个项目、跨多次运行）时结构漂移、导航断链。 所以路径规范是硬约束，不是建议。
2.1 固定骨架（雷打不动）
<知识库根>/
README.md ← 平台总览（导航总入口）
_platform/ ← 下划线前缀，永远排最前、区别于业务项目
service-registry.md ← 稳定服务标识注册表（防重名 / 防仓名漂移）
call-graph.md ← 服务调用图（稳定标识做主键 + 悬空边 + 待接通清单）
platform-coverage.md ← 覆盖率总台账（各项目进度 + 残余风险汇总）
<服务标识>/ ← 一个项目一棵树
README.md ← L1：概况 + 模块清单 + 可选流程/场景索引 + 台账链接
discovery-ledger.md ← 发现来源台账（枚举策略 / 命中范围 / 未识别入口）
coverage-ledger.md ← 对象覆盖台账（逐对象认领状态）
<模块名>/ ← 裸名，无前缀
README.md ← L2：模块概览 + 下钻链接
business-logic.md ← L3 叶子（固定 ASCII 文件名）
database.md ← L3 叶子
api.md ← L3 叶子
What ships with it
8 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.
- 12d ago First seen · 421 lines · 105 tokens per session scan A 5ba8462b052d
legacy-archaeology is a skill published in the GitHub repository BackToCimaCoppi/Praxis (6 stars, last pushed 18d ago), licensed Apache-2.0. It adds 105 tokens to every session and 8,427 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
neurolink-guide
Guide for using the NeuroLink SDK and CLI. Invoke when users ask how to use neurolink, integrate AI providers, add MCP tools, configure RAG, set up memory, deploy servers, or work with multimodal content. Covers SDK, CLI, providers, tools, and enterprise features.
github-commenting
How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules. Load before posting or fixing any PR comment.
repo-conventions
NeuroLink's review standards — the critical rules to enforce, what NOT to comment on, the security bar, hot paths. Load before reviewing any change in this repository.
session-manager
A fallback skill for recording development sessions and restoring project context from an Obsidian vault, a folder of linked notes. It handles explicit resume, handoff, status, and end-of-session requests when automatic capture is unavailable.
wincreator
Proves that agent work is actually done: each claim becomes a ledger row with a gate that was executed, captured raw evidence, and a status a builder is not allowed to write for itself. Use when a technical result must be auditable later — shipping or migrating something users depend on, a change whose failure is…
dev-research
A research workflow that uses NotebookLM, a tool for asking questions about a selected collection of documents, to answer development questions with citations.