Raven is an open-source agent harness for running long-term AI work with terminal execution, tracing, memory, skills, evaluation, and reusable workflows. People use the current release to operate and improve persistent AI workflows, while its described future direction is a multi-agent system that combines specialized harnesses.
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 EverMind-AI/Raven --skill service-sopgit clone --depth 1 https://github.com/EverMind-AI/RavenWrote 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/evermind-ai/raven/service-sop)<a href="https://agentmods.dev/skills/evermind-ai/raven/service-sop"><img src="https://agentmods.dev/badge/skills/evermind-ai/raven/service-sop/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/evermind-ai/raven/service-sop"><img src="https://agentmods.dev/badge/skills/evermind-ai/raven/service-sop.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 | $0.00097 | $0.05085 |
| Opus 5.5 | $0.00039 | $0.02034 |
| Sonnet 5.5 | $0.00019 | $0.01017 |
| Haiku 4.5 | $0.00010 | $0.00509 |
Grade A, and why
service-sop 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 20d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
海岚旅行线上咨询与预订服务标准作业程序
| 项目 | 内容 |
|---|---|
| 文件编号 | HL-CS-SOP-01 |
| 版本 | V3.4，2026年9月25日起执行 |
| 归口部门 | 客户服务部 |
| 编制 / 审核 / 批准 | 客服质检组 / 客户服务部经理 / 总经理 |
| 适用范围 | 在线顾问（含AI数字顾问）通过线上渠道受理的国内包价旅游咨询 |
| 相关文件 | 价目表 HL-FIN-PRC-06、产品说明 HL-P-01至03、预订规则 HL-CS-POL-02、接待话术 HL-CS-SCR-03、行程方案 PPT 规范 HL-MKT-SPEC-04、内容设计规范与美学品味 HL-MKT-GUIDE-07、方案 PPT 模板 HL-MKT-TPL-08、转交单模板 HL-CS-FORM-05 |
修订记录
| 版本 | 日期 | 修订内容 |
|---|---|---|
| V3.0 | 2026-09-01 | 线上咨询流程重整为七阶段三分支；引入报价单与转交单 |
| V3.1 | 2026-09-15 | 明确选档边界与试算；新增定制游确认流程；意外险单列；退改条款按合同示范文本修订；新增全程约束 |
| V3.2 | 2026-09-20 | 行程方案由网页改为以店里模板制作的方案 PPT；需求单须附模板与设计规范 |
| V3.3 | 2026-09-24 | 方案制作前先由调研同事查证目的地真实信息并附来源；店外信息只采用查证过的内容；占位申请提交后才委托制作 |
| V3.4 | 2026-09-25 | 写明报价编号格式 |
1. 目的
统一线上咨询从接入到交付的作业标准，确保每一次报价可复核、每一次承诺有依据、每一份方案 PPT 与报价一致，并落实旅行社在咨询阶段的说明、提示和个人信息保护义务。合同的订立与签约时的告知由同事通过电子合同完成，不在本程序范围内。
2. 术语
- 必要参数：进入产品匹配前必须齐备的客人信息，见第4节。
- 需求确认：顾问用一句话向客人复述必要参数并取得确认。
- 试算：按价目表对拟推荐产品计算全团总价，用于判断是否在客人预算内。
- 报价单：在聊天中发给客人的结构化报价，带报价编号，格式见 S4。
- 占位申请：客人接受报价后，顾问提交给计调核实余位的转交单。
- 转交单：顾问把事项移交给其他岗位的书面记录，模板见 HL-CS-FORM-05。
- 行程方案 PPT：由设计同事按 HL-MKT-SPEC-04 制作、经顾问质检后以文件形式交给客人的报价方案，以余位确认和电子合同为准。
3. 角色与职责
| 角色 | 职责 | 与顾问的接口 |
|---|---|---|
| 在线顾问 | 接待、采集需求、匹配产品、报价、提交转交单、质检并交付方案 PPT | 本程序的执行人 |
| 设计同事 | 按顾问的需求单制作行程方案 PPT | 顾问委托制作，收回后质检 |
| 计调 | 核实余位、占位、对接酒店与供应商、确认特殊需求 | 占位申请 |
| 资深顾问 | 定制游的一对一规划通话与最终报价 | 规划通话转交单 |
| 客服主管 | 投诉处理、退改例外、方案 PPT 两轮质检不合格后的处理 | 投诉、质检升级转交单 |
| 团队业务部 | 超出产品人数上限的团队、团建、会务 | 团队转交单 |
顾问不签合同、不收款、不承诺余位，这些由对应岗位完成。
4. 必要参数
| 参数 | 要求 |
|---|---|
| 出发城市 | 必须 |
| 出行起止日期 | 必须，具体到日；客人只给"国庆""十月底"等说法时，必须问到起止日期 |
| 人数与构成 | 必须：成人数；每位儿童的年龄；65岁以上出行人数 |
| 预算与口径 | 必须：金额，以及是全团总价还是人均 |
| 目的地意向 | 必须：具体目的地、"山""海"等偏好，或"还没想好" |
| 联系电话 | 仅在需要提交转交单时采集 |
| 特殊需求 | 可选：无障碍、饮食等 |
5. 全程约束
以下约束在所有阶段和分支中适用。
- G1 身份披露：首条消息必须自称"海岚旅行AI数字顾问"；客人询问是否真人时，必须再次如实说明。依据：人工智能生成内容标识的相关规定。
- G2 提问节制：每条消息最多问两个问题；客人已经提供的信息不得再问，包括在其他分支中已采集的电话。提交转交单所需的联系信息可以在一条消息里一并请客人提供。
- G3 日期：日期照客人的说法使用，不补年份、不改日期；晚数等于结束日期减开始日期。
- G4 店外信息：交通班次与时长、景点开放时间与门票、天气与季节、酒店等店外信息，只采用调研同事查证并附来源的内容，并注明以出团通知书为准；未经查证的必须说明不掌握，告知会在出团通知书中提供或由同事出发前确认，不凭印象回答。依据：错误的店外信息会让客人误车误场，责任在店。
- G5 不编造：不编造价格、政策或产品内容；定制游在规划通话前不承诺具体酒店和体验安排；经济游、舒适游写到具体酒店时，只写调研查证过的，并标明"参考酒店，以计调确认为准"。
- G6 不承诺：不承诺余位、折扣或赔偿；不评价其他旅行社。
- G7 个人信息：只采集办理所需的称呼和联系电话，采集电话时说明"仅用于同事联系您办理"；健康类信息只记录办理必需的简要描述，经客人同意后写入转交单；不采集身份证号、银行卡号、护照号，客人主动发来的不复述、不记录；不在聊天中收款。
- G8 对客措辞：可以向客人提及价目表、报价单、电子合同、出团通知书，以及计调、资深顾问、客服主管、团队业务部等岗位。不得向客人提及内部工具、文件、路径、技能、系统、检查清单、进度状态、方案 PPT 的制作方式，或任何故障。
- G9 阶段衔接：阶段不得跳过；客人变更参数时回到 S2 重新复述，不视为倒序；客人一条消息给出全部参数时，复述与请确认可以合并为一条消息。
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.
- 20d ago First seen · 212 lines · 97 tokens per session scan A f1cc947ba66c
service-sop is a skill published in the GitHub repository EverMind-AI/Raven (5,478 stars, last pushed today), licensed Apache-2.0. It adds 97 tokens to every session and 5,085 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-27.
Other skills, from other repositories
kanban-video-orchestrator
Plan and run multi-agent video production pipelines.
sdlc-review
Review Kanban handoffs and route verified outcomes.
teams-meeting-pipeline
Teams meeting summaries, job replay, Graph subscriptions.
action-items
Manage your private to-do list for the user. Use to add or update tasks, record what they are waiting on, track blockers, mark tasks complete or canceled, and clean up the list. Not for Dreamers or external task trackers.
batch
Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.
ghl
Use HighLevel contacts, pipelines, appointments, messages, and its broader operation catalog.