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 seed-forge/harness-ai-kit --skill infra-ragflow-opsgit clone --depth 1 https://github.com/seed-forge/harness-ai-kitWrote 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/seed-forge/harness-ai-kit/infra-ragflow-ops)<a href="https://agentmods.dev/skills/seed-forge/harness-ai-kit/infra-ragflow-ops"><img src="https://agentmods.dev/badge/skills/seed-forge/harness-ai-kit/infra-ragflow-ops/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/seed-forge/harness-ai-kit/infra-ragflow-ops"><img src="https://agentmods.dev/badge/skills/seed-forge/harness-ai-kit/infra-ragflow-ops.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 | $0.00061 | $0.01357 |
| Opus 5 | $0.00030 | $0.00678 |
| Sonnet 5 | $0.00012 | $0.00271 |
| Haiku 4.5 | $0.00006 | $0.00136 |
Grade A, and why
infra-ragflow-ops 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 9d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
infra-ragflow-ops
用于 RAGFlow 平台 day-2 运维。RAGFlow 是 AI/RAG 平台型应用,本轮作为基础设施纳入治理。
配置上下文
本技能依赖以下配置,AI 在运行时按如下优先级解析:
- 用户对话中明确提供的值(最高优先级)
~/.harness-ai-kit/config.yaml中assets.ragflowctl或global段config.defaults.yaml中的默认值
如用户未提供且无默认值的 required 字段,必须主动询问用户。 禁止从 AGENTS.md 或脚本中读取硬编码配置值。
| 配置项 | 类型 | 必填 | 说明 |
|---|---|---|---|
ragflow_url |
string | ✅ | RAGFlow 服务 URL(默认 http://ragflow.{base_domain}:11281) |
配套 CLI:ragflowctl(配置来源:~/.harness-ai-kit/config.yaml → assets.ragflowctl)
边界
- 本 skill 负责:RAGFlow 服务健康、dataset/知识库 API 探活、模型/向量库/对象存储依赖检查、运行台账。
- 模型消费规则交给
infra-aimodel-ops。 - 数据库/向量库/对象存储连接规则交给
infra-datasource-ops和infra-minio-ops。
推荐输出格式
执行完毕后输出极简回执:状态(✅ 成功 / ⚠️ 部分成功 / ❌ 失败)+ 关键结果(1-2 行,如操作对象、产出位置、下一步)。无需强制套用大表格。
操作顺序
- 运行
ragflowctl doctor --profile 组织内部集群 --json。 - 检查依赖:模型 endpoint、数据库、向量库、对象存储。
- 只读列 dataset/知识库,再评估是否需要变更。
- 变更前输出 dry-run 计划。
模型治理(ragflowctl ≥0.3.0,v0.26 模型体系)
v0.26 起 RAGFlow 模型管理重构为 provider/instance/model 三级(tenant_model_* 表),一律经 ragflowctl llm 命令组操作,不开 UI、不手写 SQL:
llm providers|factories|models|remote-models|default:只读盘点llm add-instance --models <name:type>:创建实例(服务端强制真实探测,--models 至少一项)llm add-model:追加模型(纯登记不探测;--type asr/vision自动映射speech2text/image2text)llm set-default --type chat|embedding|rerank|asr|tts:设租户默认模型(引用格式model@instance@provider)llm remove-provider:连实例/模型整体删除dataset set-embedding:存量库 embedding 引用重绑(同模型换服务后端向量兼容,无需重建索引)
模型选型与消费 token 遵循 infra-aimodel-ops 场景矩阵;组织内部集群 默认统一走 newapi 入口(provider=OpenAI-API-Compatible)。
能力地图(v0.26:不止是知识库 RAG)
v0.26 的 RAGFlow 是 RAG-native 智能体平台:知识库底座 + agent 编排引擎(21 组件 / 25 内置模板,含 deep_research 交叉核实综述、web_search_assistant、ingestion_pipeline 系列)。分工:知识库半径内智能体放 RAGFlow Agent,业务半径编排留 Dify,自研代码 agent(LangGraph 等)经 POST /api/v1/retrieval 把 RAGFlow 当检索后端(hybrid+rerank 一站式),模型统一走 newapi。RAG 算法(GraphRAG/RAPTOR/hybrid/VLM/parent_child)、三级召回方法论、入库纪律、ragflowctl 扩展 backlog 见参考文档。
What ships with it
7 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.
- 9d ago First seen · 92 lines · 61 tokens per session scan A 6ae6643ad6d2
infra-ragflow-ops is a skill published in the GitHub repository seed-forge/harness-ai-kit (22 stars, last pushed 8d ago), licensed Apache-2.0. It adds 61 tokens to every session and 1,357 once invoked, about $0.0003 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
audit-langfuse-llm
Run a PDCA quality audit on LLM/AI features: traces, prompts, costs, evals, grounding, hallucination. Use for "audit LLM quality", "check Langfuse", "audit prompts", "check AI quality", "audit AI costs", "check traces". Jailbreak/OWASP LLM → audit-llm-security. Token caps → plan-llm-cost-guardrails.
RAG Workflow Planner
Designs a complete Retrieval-Augmented Generation (RAG) pipeline for a given use case, including chunking strategy, embedding model selection, and retrieval approach.
Hybrid Search Architect
Designs a hybrid retrieval pipeline combining dense vector search and BM25 sparse search with reciprocal rank fusion, and explains when to use each configuration.
RAG Chunking Strategy Advisor
Given a document type and retrieval goal, recommends the optimal chunking strategy for a RAG pipeline to minimize retrieval failures.
audit-llm-security
Read-only OWASP LLM Top 10 audit of app-facing AI: prompt injection, data leakage, unsafe output/agency, RAG risks, misinformation, and unbounded spend. Use when "audit LLM security", "prompt injection", "jailbreak my chatbot", or "is my AI safe?". General app security → audit-security.
modal
Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs. Use when deploying or serving AI/ML models, running GPU-accelerated workloads (training, fine-tuning, inference), serving web endpoints, scheduling batch jobs, or scaling Python code to cloud containers with the Modal SDK.