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/opendcai/dataflow-webui/dataflow-operator-buildernpx skills add OpenDCAI/DataFlow-WebUI --skill dataflow-operator-buildergit clone --depth 1 https://github.com/OpenDCAI/DataFlow-WebUIWhat 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 | $0.00066 | $0.02078 |
| Opus 5 | $0.00033 | $0.01039 |
| Sonnet 5 | $0.00013 | $0.00416 |
| Haiku 4.5 | $0.00007 | $0.00208 |
Grade A, and why
dataflow-operator-builder 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 2d 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 — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DataFlow Operator Builder
Build production-ready DataFlow operator artifacts with either interactive interview mode or direct spec mode.
ZH: 通过“交互采访模式”或“直接 spec 模式”快速生成生产可用的 DataFlow Operator。
Usage
/dataflow-operator-builder
/dataflow-operator-builder --spec path/to/spec.json --output-root path/to/repo
/dataflow-operator-builder --dry-run --spec path/to/spec.json --output-root path/to/repo
Script Directory
Agent execution instructions:
- Resolve this
SKILL.mddirectory asSKILL_DIR. - Use
${SKILL_DIR}/scripts/build_operator_artifacts.py.
ZH:
- 将当前
SKILL.md所在目录作为SKILL_DIR。 - 使用
${SKILL_DIR}/scripts/build_operator_artifacts.py。
| Script | Purpose |
|---|---|
scripts/build_operator_artifacts.py |
Generate operator + CLI + tests from spec |
scripts/example_spec.json |
Example input spec with defaults |
Scope
This skill targets:
- DataFlow-style operator implementation (
DataFlowStorage+ dataframe flow) @OPERATOR_REGISTRY.register()registration- Separate CLI wrapper under
cli/ - Minimal but production-grade tests (
unit/registry/smoke)
ZH:
- 面向 DataFlow 风格的 operator 实现（
DataFlowStorage+ dataframe 流程） - 自动包含
@OPERATOR_REGISTRY.register()注册 - CLI 与 operator 逻辑分离
- 生成最小但可用的测试骨架（
unit/registry/smoke）
Default families:
generatefilterrefineeval
Two Working Modes
Mode A: Interactive Interview Mode
Use AskUserQuestion in batch mode with exactly two rounds:
Use structured questioning in batch mode with exactly two rounds:
- Round 1: structure fields
- Round 2: implementation fields
Important:
- In each question block, include recommended option + short reason.
- Ask follow-up questions only when high-impact fields are missing or contradictory.
- Do not ask one-by-one when the same round can be asked in one batch.
- Present all questions of one round in a single message to the user, grouped by round.
What ships with it
21 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.
- assets/templates/cli/operator_cli.py.tmpl 2.9 KB
- assets/templates/operators/eval_operator.py.tmpl 2.4 KB
- assets/templates/operators/filter_operator.py.tmpl 1.5 KB
- assets/templates/operators/generate_operator.py.tmpl 2.3 KB
- assets/templates/operators/refine_operator.py.tmpl 2.3 KB
- assets/templates/package/cli_init.py.tmpl 46 B
- assets/templates/package/operator_pkg_init.py.tmpl 140 B
- assets/templates/package/operators_root_init.py.tmpl 49 B
- assets/templates/package/package_init.py.tmpl 476 B
- assets/templates/tests/test_operator_registry.py.tmpl 417 B
- assets/templates/tests/test_operator_smoke.py.tmpl 1.8 KB
- assets/templates/tests/test_operator_unit.py.tmpl 2.1 KB
- references/acceptance-checklist.md 1.2 KB
- references/askuserquestion-rounds.md 2.8 KB
- references/cli-shell-guidelines.md 1.2 KB
- references/gotchas.md 3.2 KB
- references/operator-contract.md 1.4 KB
- references/output-checklist.md 733 B
- references/registration-rules.md 991 B
- scripts/build_operator_artifacts.py 26 KB runs code
- scripts/example_spec.json 428 B
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.
- 2d ago First seen · 267 lines · 66 tokens per session scan A 602980a26897
dataflow-operator-builder is a skill published in the GitHub repository OpenDCAI/DataFlow-WebUI (224 stars, last pushed 6d ago), licensed Apache-2.0. It adds 66 tokens to every session and 2,078 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…