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 OpenDCAI/DataFlow-WebUI --skill chunked-prompted-generatorgit clone --depth 1 https://github.com/OpenDCAI/DataFlow-WebUIWrote 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/opendcai/dataflow-webui/chunked-prompted-generator)<a href="https://agentmods.dev/skills/opendcai/dataflow-webui/chunked-prompted-generator"><img src="https://agentmods.dev/badge/skills/opendcai/dataflow-webui/chunked-prompted-generator.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00072 | $0.01122 |
| Opus 5 | $0.00036 | $0.00561 |
| Sonnet 5 | $0.00014 | $0.00224 |
| Haiku 4.5 | $0.00007 | $0.00112 |
Grade A, and why
chunked-prompted-generator 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 8d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChunkedPromptedGenerator Operator Reference
ChunkedPromptedGenerator reads file paths from a dataframe column, loads each
file from disk, recursively splits long content into chunks, calls the LLM on
all chunks, joins the generated outputs with a separator, writes the joined
result into a new text file, and stores that output file path back into the
dataframe.
1. Import
from dataflow.operators.core_text import ChunkedPromptedGenerator
2. Constructor
ChunkedPromptedGenerator(
llm_serving=llm,
system_prompt="You are a helpful agent.",
json_schema=None,
max_chunk_len=128000,
enc=tiktoken.get_encoding("cl100k_base"),
separator="\n",
)
| Parameter | Required | Default | Description |
|---|---|---|---|
llm_serving |
Yes | None | LLM service object implementing generate_from_input(...) |
system_prompt |
No | "You are a helpful agent." |
Prepended to each chunk as plain text before the chunk content |
json_schema |
No | None |
Optional schema forwarded to generate_from_input(...) |
max_chunk_len |
No | 128000 |
Maximum token count per chunk |
enc |
No | tiktoken.get_encoding("cl100k_base") |
Encoder used for token counting through len(enc.encode(text)) |
separator |
No | "\n" |
Join separator for chunk outputs |
3. run() Signature
op.run(
storage=self.storage.step(),
input_path_key="file_path",
output_path_key="output_path",
)
# returns: output_path_key
| Parameter | Required | Default | Description |
|---|---|---|---|
storage |
Yes | None | Current operator-step storage object |
input_path_key |
Yes | None | Column containing input file paths |
output_path_key |
Yes | None | Column used to store generated output file paths |
4. Actual Execution Logic
The current implementation behaves as follows:
- Read the dataframe from
storage. - For each row, read the file content from
Path(row[input_path_key]).read_text(encoding="utf-8"). - Count tokens with
len(enc.encode(text)). - If the text exceeds
max_chunk_len, recursively split it into two halves by character position, not by sentence or token boundary. - For each chunk, build one LLM input as:
What ships with it
3 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.
- 8d ago First seen · 136 lines · 72 tokens per session scan A b7cf7b0eaf6e
chunked-prompted-generator is a skill published in the GitHub repository OpenDCAI/DataFlow-WebUI (234 stars, last pushed 12d ago), licensed Apache-2.0. It adds 72 tokens to every session and 1,122 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
markitdown
Convert heterogeneous documents and selected URIs to Markdown with Microsoft MarkItDown for text analysis, search, and LLM/RAG ingestion. Covers safe local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server.
llamaindex
Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines. Best for data-centric LLM…
azure-ai
Use for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcribe, OCR, convert text to speech.
kb-retriever
A retrieval and question-answering assistant for a local folder of documents, including Markdown, text, PDFs, and spreadsheets.
bailian-kb
A command-line manager for Alibaba Cloud Bailian knowledge bases, which are collections of documents prepared for search and question answering. It handles the stored documents, search services, text chunks, and data-centre files rather than everyday searches.
rag-deep-dive
Three-step multi-tool workflow — search the corpus, fetch the most relevant document in full, then find similar documents. Use when a single searchknowledge hit is not enough because the user asked a "how does X work end to end" or "explain the pattern" or "give me the full picture" question. Prevents shallow answers…