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/wackygem/fleur/fleur-dagster-http-sourcenpx skills add WackyGem/Fleur --skill fleur-dagster-http-sourcegit clone --depth 1 https://github.com/WackyGem/FleurWrote 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/wackygem/fleur/fleur-dagster-http-source)<a href="https://agentmods.dev/skills/wackygem/fleur/fleur-dagster-http-source"><img src="https://agentmods.dev/badge/skills/wackygem/fleur/fleur-dagster-http-source.svg" alt="Measured on agentmods" 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 | $0.00099 | $0.02461 |
| Opus 5 | $0.00049 | $0.01230 |
| Sonnet 5 | $0.00020 | $0.00492 |
| Haiku 4.5 | $0.00010 | $0.00246 |
Grade A, and why
fleur-dagster-http-source scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
3. 用 `curl` 或现有 HTTP client 探测 URL。公开接口可以直接取小样本;需要鉴权或大量数据时只记录阻塞原因。 How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dagster HTTP Source Asset
当用户只提供一个远端 HTTP 链接,并希望生成 HTTP -> S3 Parquet -> ClickHouse raw
链路代码时,使用本 skill。
目标不是生成孤立 asset,而是把新数据集纳入 fleur 的长期边界:
- 远端接口事实记录在
docs/references/remote_endpoint/。 - 字段事实源记录在
pipeline/contracts/datasets/*.yml。 - Dagster source asset 写入 contract 精确匹配的 S3 Parquet。
- ClickHouse raw asset 由
pipeline/contracts中的clickhouse_raw自动生成。
配合使用
- 先使用
dagster-expert,并按需读取 asset metadata、dependency 和dg checkreference。 - 涉及 contract、Parquet schema、ClickHouse raw 字段时使用
fleur-contract-data-dictionary。 - 写 Python 代码或测试时使用
dignified-python。 - 需要实际 materialize、回填或重跑时使用
fleur-dagster-backfill-runbook。 - 涉及 Dagster、ClickHouse client、PyArrow、dbt 等库/CLI 的 API 细节时,按
AGENTS.md使用 Context7。
输入归一化
最小输入可以只有一个 URL。先把它归一化成下面事实,不足时自己探测;只有鉴权、 业务口径或目标数据集命名无法安全推断时才问用户。
source:供应商或站点名,作为 source bundle 名和 asset tag。dataset:形如<source>__<entity>,作为 source asset 尾段、contract 文件名和 raw table 名。endpoint:HTTP method、URL、query params、headers、referer、分页和速率限制。payload_format:JSON、CSV、TXT、ZIP 等。grain:一行代表什么。storage_mode:latest_snapshot或partitioned。partition_key_name:仅partitioned需要,如year、trade_date。raw_sync:是否同步到 ClickHouse raw;不能确定时默认做 source-only,并在最终说明原因。
如果 URL 需要 token、cookie、账号密码或私有 header,不能把密钥写进代码、文档或最终回答;
应使用现有 .env/resource/config 模式,缺少变量时向用户要变量名或鉴权方式。
Endpoint Profiling
- 先读入口文档:
AGENTS.md、docs/architecture/scheduler-architecture.md、docs/architecture/scheduler-module-boundaries.md。 - 查已有事实:
docs/references/remote_endpoint/<dataset>.md、pipeline/contracts/datasets/<dataset>.yml、同源pipeline/scheduler/src/scheduler/defs/sources/<source>/。 - 用
curl或现有 HTTP client 探测 URL。公开接口可以直接取小样本;需要鉴权或大量数据时只记录阻塞原因。 - 记录或更新
docs/references/remote_endpoint/<dataset>.md,至少包含: endpoint、请求示例、参数表、响应结构、分页/游标、错误码、保留期限、headers、速率限制和样例字段。 - 不从字段名凭空编业务含义。中文描述无法确认时按 contract skill 使用“待核实”格式。
Contract First
新增或修改 source asset 前,先维护 pipeline/contracts/datasets/<dataset>.yml。
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.
- 6d ago First seen · 193 lines · 99 tokens per session scan A b8073f61084e
fleur-dagster-http-source is a skill published in the GitHub repository WackyGem/Fleur (114 stars, last pushed 1mo ago), licensed MIT. It adds 99 tokens to every session and 2,461 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pinecone
Managed vector DB for production RAG and search.
embeddings
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.
cognee-community
Use when the user needs something that ships outside cognee core — community database adapters (Qdrant, Milvus, Weaviate, Redis, Pinecone, FalkorDB, Memgraph, DuckDB, NetworkX, …), data-source connectors (Slack, Gmail, Notion, Confluence, Google Drive), custom tasks/pipelines/retrievers (Exa, ScrapeGraph, codify)…
data-engineer
Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms.
similarity-search-patterns
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.
ingesting-into-data-lake
Import data into the AWS data lake from S3 files, local uploads, JDBC databases (Oracle, SQL Server, PostgreSQL, MySQL, RDS, Aurora), Amazon Redshift, Snowflake, BigQuery, DynamoDB, or existing Glue catalog tables (migration). Default target is S3 Tables; standard Iceberg on a general purpose bucket is supported where…