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 AgenticAIPlan/AgenticAISkills --skill ai-project-quotegit clone --depth 1 https://github.com/AgenticAIPlan/AgenticAISkillsWrote 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/agenticaiplan/agenticaiskills/ai-project-quote)<a href="https://agentmods.dev/skills/agenticaiplan/agenticaiskills/ai-project-quote"><img src="https://agentmods.dev/badge/skills/agenticaiplan/agenticaiskills/ai-project-quote/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/agenticaiplan/agenticaiskills/ai-project-quote"><img src="https://agentmods.dev/badge/skills/agenticaiplan/agenticaiskills/ai-project-quote.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 | $0.00089 | $0.06807 |
| Opus 5 | $0.00044 | $0.03403 |
| Sonnet 5 | $0.00018 | $0.01361 |
| Haiku 4.5 | $0.00009 | $0.00681 |
Grade A, and why
ai-project-quote 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 — 492 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI报价专家 (ai-project-quote)
描述
政企AI应用项目开发报价专家（ai-project-quote）。输入项目需求，同时输出三种独立报价模板（AI+传统分离计价、功能模块计价、角色人天计价），并提供信息完整度评估与补充建议。
能力
- 解析用户输入的AI项目需求（业务场景、痛点、目标、数据源等）
- 自动拆解AI智能体与传统信息化模块
- 同时生成三种独立报价模板
- 评估信息完整度，标注不确定环节
- 提供补充信息建议，提升报价精准度
报价维度体系
一、智能体复杂度分级（实战版）
| 级别 | 定义 | 技术特征 | 人天 | 说明 |
|---|---|---|---|---|
| 简单RAG | 单轮对话/固定流程 | 标准RAG、单工具调用、无记忆 | 8-12人天 | 含联调测试，勉强够用 |
| 中等多轮 | 多轮对话/工具组合 | 多轮状态管理、多工具编排、基础记忆 | 15-25人天 | 状态管理+编排+记忆，实操成本较高 |
| 复杂多智能体 | 多智能体协作/自主规划 | 智能体编排、自主决策、复杂推理 | 25-40人天 | 多智能体调试成本很高，需充分预留 |
| 高复杂微调 | 领域深度定制/大模型微调 | Fine-tuning+数据标注+训练+评估+部署 | 30-50人天 | 含数据标注30-50%工时，全流程覆盖 |
高复杂项目特别提示：
- 30-40人天：基础微调（有现成标注数据、标准模型）
- 40-50人天：深度定制（需数据准备、多轮迭代优化、领域适配）
- 数据标注已含在智能体开发人天内：微调项目按总工时30-50%估算，该费用包含在智能体人天中；独立的批量数据标注项目（如专用的训练数据集构建）可单独评估
- 建议采用"基础开发费 + 效果优化服务费"模式，避免一口价锁死风险
人天估算原则：
- 上述人天为"有效开发人天"，不含需求变更、客户等待等时间
- 复杂/高复杂项目建议预留15-20%缓冲人天应对调试风险
- 多智能体项目需额外考虑智能体间联调成本（通常+20%）
智能体合并原则
- 功能相似合并：如"计划编制+初审"可合并为一个智能体
- 流程连续合并：如"需求征集+计划编制"如逻辑紧密可合并
- 避免过度拆分：不要为了凑数量而拆分，以实际技术实现复杂度为准
二、传统信息化模块（优化版）
| 模块 | 子项 | 人天 |
|---|---|---|
| 数据采集层 | 系统接口对接（8-12人天/系统）、定时任务（5-8人天） | 按接口数量×复杂度 |
| 数据工程层 | 数据清洗（10-20人天）、数据标注（按数据量估算）、ETL流程 | 数据质量决定AI效果，需充分评估 |
| 管理后台 | 用户权限、配置管理、内容管理 | 15-25人天 |
| 可视化层 | 图表组件、仪表盘、报表导出 | 10-18人天 |
| 基础架构 | 部署运维、监控告警、安全防护 | 10-15人天 |
数据工程重要提示：政企客户数据通常质量较差（扫描件、非结构化、格式混乱），数据清洗与标注是影响AI效果的关键投入，5-8人天通常仅够处理极少量数据。建议根据实际数据量和质量评估，必要时单独列项。
三、项目闭环环节（政企刚需，优化版）
| 环节 | 内容 | 人天 |
|---|---|---|
| 需求调研 | 业务调研、需求梳理、方案设计 | 8-12人天 |
| 合规适配 | 等保测评、数据合规、国产化适配 | 10-18人天 |
| 培训交付 | 用户培训、操作手册、运维交接 | 5-8人天 |
四、角色单价参考（政企AI项目，优化版）
| 角色 | 单价（元/人天） | 说明 |
|---|---|---|
| AI算法工程师（应用级） | 3,000-4,000 | Prompt工程、RAG、Agent编排、标准模型调用 |
| AI算法工程师（专家级） | 5,000-8,000 | 模型微调、领域定制、复杂推理架构设计 |
| 数据工程师 | 2,200-2,800 | 数据接入、ETL、基础数据治理 |
| 后端开发工程师 | 2,000-2,500 | 业务系统、API开发、数据库设计 |
| 前端开发工程师 | 1,800-2,200 | 管理后台、可视化界面 |
| 产品经理 | 1,600-2,000 | 需求分析、原型设计、项目管理 |
| 测试工程师 | 1,600-1,800 | 功能测试、性能测试、安全测试 |
| 项目经理 | 2,000-2,500 | 进度管控、客户对接、风险管理 |
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 · 492 lines · 89 tokens per session scan A 5eb2fef6dde9
ai-project-quote is a skill published in the GitHub repository AgenticAIPlan/AgenticAISkills (11 stars, last pushed 3mo ago), licensed MIT. It adds 89 tokens to every session and 6,807 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 2026-08-30.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.
reading-receipt
An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.