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 instructions/opendcai/dataflow-webui/claude-mdgit 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 | $0.00556 | $0.00556 |
| Opus 5 | $0.00278 | $0.00278 |
| Sonnet 5 | $0.00111 | $0.00111 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
DataFlow-WebUI CLAUDE.md 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 3d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DataFlow WebUI — Project Rules
Deployment assumption: this project is a single-user, local-first tool. Each developer/user runs both backend and frontend on their own machine. There is no authentication, no registration, no multi-tenant concern. Do NOT add login pages, JWT/session infrastructure, or per-user ACL.
WebUI Change Policy
The previous strict allow-list (only operator-rendering fixes / existing-endpoint patches) has been relaxed. New routes, new sidebar items, new backend endpoints, and new services are all permitted when they serve the goal of "completing DataFlow-WebUI as a usable local tool".
Encouraged work areas
- Agent chat experience — tool-call progress indicators, session persistence, multi-session switching, reconnect logic, robust error surfacing.
- Prompt management — both read-only browsing of the built-in
PROMPT_REGISTRYAND first-class support for user-defined prompt templates (file-based persistence underbackend/data/prompts/, CRUD endpoints, editor UI, reference from operator config). - JSON Schema management — container-based service injection, schema validation (ajv), monaco/codemirror editor, deep integration with operator parameter panels so saved schemas can be chosen for structured LLM outputs.
- Operator rendering — still a priority: new/fixed node components in
components/manage/mainFlow/nodes/, parameter editors, correct display of operators that already exist inOPERATOR_REGISTRY. - Repo hygiene — consolidating/deleting duplicate markdown, removing
stray
* copyskill directories, fixing obvious code smells (same-name route handlers, hard-coded URLs, services bypassing the DI container).
Still prohibited
- Authentication / registration / multi-user features. Single-user local tool only.
- External telemetry / analytics uploads. No outbound reporting.
- Breaking changes to
OPERATOR_REGISTRY/PROMPT_REGISTRYsemantics — always extend, never redefine, so upstream DataFlow stays compatible.
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.
- 3d ago First seen · 50 lines · 556 tokens per session scan A c37ef42fd25d
DataFlow-WebUI CLAUDE.md is an instructions file published in the GitHub repository OpenDCAI/DataFlow-WebUI (224 stars, last pushed 7d ago), licensed Apache-2.0. It adds 556 tokens to every session, about $0.0028 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.