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 agentmods add skills/lawyeah-tech/lawyeah/btnpx skills add Lawyeah-Tech/lawyeah --skill btgit clone --depth 1 https://github.com/Lawyeah-Tech/lawyeahWhat 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 | $0.00083 | $0.04190 |
| Opus 5 | $0.00042 | $0.02095 |
| Sonnet 5 | $0.00017 | $0.00838 |
| Haiku 4.5 | $0.00008 | $0.00419 |
Grade A, and why
BT合同·审查 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 2d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BT 合同·审查
任务目标
在单一立场下,只审查 建设工程 / BT 合同 的待签文本:核心给付是投资人融资并建设,竣工验收后移交,回购方按约定分期支付回购价款(建安工程费 + 融资利息 + 投资回报)。输出风险表、可回给对方的修改句或红线、谈判与签署提醒。
本技能类型锁死。不扫描其他类型。场景分层为 P1。显示名为「BT 合同·审查」。
depends-on 为空。不要求先跑导航。
主线是建设—移交—回购,不是按图进度付款,不是政府出资的代建管理费,也不是业主融资后的长期运营服务。
不交付:他类合同审查;从零起草;履约交底;争议文书;有效性或对方接受的保证;把纯政府付费 BT、政府投资垫资、必须招标未招、机关违规担保、挂靠或把 BT 伪装成特许经营/政府购买服务改成可履行结构。
工作边界
正触发:已有可读待签正文及附件,尚未签署,尚未成争;核心给付同时具备:(1)投资人承担建设期融资并组织建设;(2)竣工验收后向回购方移交项目;(3)回购方以回购价款(而非建设期进度款、代建管理费或运营分成)分期偿付投资。
负触发并输出 触发判定:负触发,未启动本任务:
- 核心给付是按图施工、建设期按进度付款、无融资回购 →
建设工程施工合同·审查; - 设计+采购+施工或设计+施工一体、发包人出资、无移交后回购 →
工程总承包合同·审查; - 设计+建造+长期运营,业主通常负责融资,承包人不以回购收回投资 →
DBO合同·审查; - 政府将建设管理职责委托代建人,对价是代建管理费,政府为投资主体 →
切开; - 含特许经营期内运营并向使用者收费或可行性缺口补助、期满移交,且以运营收益回收投资 → 引擎重新定性(特许/PPP),不得用本技能把“建成即移交、政府纯付费回购”改成特许经营外观;
- 商业代建、资本代建、股权代建或“代建+贷款配资” → 对应委托合同代建原子,不得用本技能吞并;
- 编制勘察报告 →
建设工程勘察合同·审查;出施工图 →建设工程设计合同·审查;监理 →建设工程监理合同·审查;咨询混签 →建设工程咨询服务合同·审查或引擎; - 联合体成员之间的内部分工文本 →
联合体协议·审查; - 无可读文本、本类型条件已谈妥、要出己方稿 →
BT合同·起草; - 已签只问融资到位日、移交日、回购款哪天催 → 本套导航的履约步骤;
- 已成争(催告回购、确认无效、优先受偿诉讼、隐性债务认定、立案仲裁)→
或或或。
挂靠、违法分包、必须招标未招、政府投资垫资、机关违规担保、把工程建设或融资包装成政府购买服务、把建成即移交包装成特许经营:只出告知,不改写成可履行结构。用户坚持“改到能签/先建后补招/机关出担保函就能放款”:整体停止。
本类型硬闸
执行时必须同时守住。每闸必须能落到修改句或明确停笔,不得用施工进度款、代建管理费或 DBO 运营考核替换。
-
建设—移交—回购
本类型成立必须同时读出三条链:投资人融资建设;竣工验收合格后签署《移交确认书》并转移占有/权属;回购价款自移交确认之日起算并按附件计划分期支付。回购价分账为建安工程费、融资利息、投资回报,三者不得混写成“工程款”。缺移交确认书、缺回购起算日、建设期仍按月进度付款且无融资义务:按核心给付负触发施工或总承包原子,不得硬套回购结构。
修改句方向:标题改为“建设工程 BT 投资建设合同”或“项目投融资建设移交协议”;标的写融资、建设、移交、回购全过程;增列附件《移交标准及清单》《回购款支付计划表》《融资计划书》;移交确认书签署日=回购起算日。 -
特许 / 采购程序
BT 含施工,落入依法必须招标范围的,须履行投融资与施工招标程序(可合一,但不得以“投资人直接指定”规避施工招标)。不得把工程建设或融资行为写成政府购买服务(财政部令第 102 号第 10 条明确排除货物、工程、工程与服务打包、融资行为)。不得把“建成即移交、政府纯付费回购”包装成基础设施特许经营:2024 年《基础设施和公用事业特许经营管理办法》第 7 条禁止在建设工程完成后直接将项目移交政府,或通过提前终止逃避运营义务;第 4 条将特许经营限定为基于使用者付费的合作。2015 年第 25 号令已失效。
修改句方向:鉴于条款锁定立项批复、招标文件、中标通知书;生效条件写明依法必须招标的已完成招标且合同与中标文件一致;删除“以政府购买服务预算安排支付回购款”“本合同即为特许经营协议、建成即移交”。未招标或先定后招:只告知,不改成倒签可履行。 -
与 DBO
DBO合同·审查/ 政府代建切开切开
DBO:业主融资,承包人设计+建造+长期运营,回收靠运营服务费或考核付费,不是移交后回购投资本息。政府代建:政府是投资主体并支付代建管理费,代建人不承担项目融资,也不得把“全额垫资+分期回购”改成代建外观。本技能禁止输出运营绩效考核表、使用者付费调价公式、代建管理费费率或“三方使用人接收”作为主路径,禁止打开其 method。
修改句方向:删除运营期分成、可用性付费绑定运营、代建管理费;恢复融资义务、移交确认书和回购计划。来稿主给付是运营或代建管理:负触发对应原子。
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.
- 2d ago First seen · 132 lines · 83 tokens per session scan A b4ceebd9f81f
BT合同·审查 is a skill published in the GitHub repository Lawyeah-Tech/lawyeah (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 83 tokens to every session and 4,190 once invoked, about $0.0004 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
cn-law-hub
用于查询、检索、核验、下载、导出、批量采集中国官方法律法规、规章、条约和具体法条。Use this skill aggressively when the user asks to 查法律、查法规、查条例、查规章、查条约、查法条、查第几条、找法律依据、引用法律依据、核验现行有效、判断是否废止/已修改/尚未生效、下载法规全文、导出法规目录、批量下载法规文件、按关键词检索具体法条、展开法条分析,或在中国法律咨询、案例分析、合规审查、合同审查、劳动争议、行政法分析、公司合规、数据合规、政策研究中需要调用、核验或引用中国现行有效法律法规原文作为依据。Trigger also when phrases such as…
mnemos
Configure and use MNEMOS for persistent cross-session memory with Hermes — shared memory pool across profiles, full-text and semantic search, compression with quality manifests, knowledge-graph triples, and session transcript ingestion. Use when setting up MNEMOS, troubleshooting memory retrieval, storing…
mnemos-memory
Read and write persistent memory via MNEMOS. Use when you need to recall prior decisions, infrastructure facts, project context, or established patterns across sessions, and when you have learned something new worth persisting (solved problem, validated pattern, architectural decision, team standard). Covers full-text…
law-to-markdown
将法条/规范文件(.txt/.docx/.pdf)转为 Markdown。适用于用户要求“法条转 markdown”“pdf/docx 转 markdown”。处理 .pdf/.docx 时先检查是否已安装 mineru-ocr skill;未安装先引导安装,安装后优先用 mineru-ocr;仅在用户明确同意时再用本地回退方案。.
hq
Connect to the HQ via Supabase. Use when you need to register yourself, search knowledge, create/update pages and skills, claim tasks, post comments, manage contacts and organizations, log interactions, or query the audit trail. Also use at session startup to register and load boot knowledge.
saferskills
Use SaferSkills to find, evaluate, and safely install AI agent capabilities (skills, MCP servers, hooks, plugins, rules) and to assess a whole agent. Run this before you install, add, recommend, or trust any capability — or when asked whether one is safe or what its score is: scan and score it first with npx…