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 agents/opendcai/dataflow-webui/setupgit 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 | $0.00000 | $0.01653 |
| Opus 5 | $0.00000 | $0.00826 |
| Sonnet 5 | $0.00000 | $0.00331 |
| Haiku 4.5 | $0.00000 | $0.00165 |
Grade C, and why
SETUP scanned grade C with 3 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 yesterday.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- **Codex is the exception:** it reads only `~/.codex/config.toml` and has no flag Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
| `skills` | `ls .claude/skills/generating-dataflow-pipeline/SKILL.md` succeeds (or `~/.claude/skills/...` if you used `--scope user`) | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| `harness` | `curl -sf http://localhost:8000/api/v1/operators/categories` returns categories | How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent setup instructions
You are an AI agent asked to set up DataFlow-Harness. This document is the authoritative procedure. It states what you may do without asking, what you must ask about first, and how to tell whether you succeeded.
A human can read this too, but it is written for you.
Skill content is not duplicated here. Once setup is done, the installed skills tell you how to build pipelines.
1. Pick the profile before installing anything
Do not default to the largest install. Ask the user which they want if it is not already clear from the conversation:
| Profile | Choose when | Cost |
|---|---|---|
skills |
They want you to write DataFlow code; no server needed | seconds, installs no packages |
harness |
They want you to query the live operator registry and run pipelines via MCP, no browser | ~1 min, pip only |
webui |
They want a visual DAG canvas in the browser | minutes, pip + npm |
If the user says only "set up DataFlow" and gives no other signal, ask. The three differ by orders of magnitude in install cost and in what they change.
2. Inspect the plan before running it
./install.sh --list
./install.sh --profile <id> --check # prerequisites; installs nothing
./install.sh --profile <id> --dry-run # every step, verbatim; changes nothing
--dry-run output is the contract. If a step looks wrong, stop and tell the user
rather than running it.
3. Install
./install.sh --profile <id>
You are authorized to run this without further confirmation. It:
- installs Python/Node dependencies for this project only (per profile)
- writes inside this repo only, because
--scope projectis the default. With--scope userit also writes~/.claude/skills - writes no agent MCP configuration, in either scope
- fingerprints every path the profile declared off-limits before and after, and fails if any of them changed
If a prerequisite is missing, the installer names it. Report exactly what the user needs to install; do not install system packages or language runtimes yourself.
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.
- yesterday First seen · 163 lines · 0 tokens per session scan C 84159750ea50
SETUP is an agent published in the GitHub repository OpenDCAI/DataFlow-WebUI (220 stars, last pushed 6d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,653 tokens. A static security scan graded it C with 3 findings (reads agent configuration directories, enumerates other installed skills, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
audit-geo
Evaluates AI crawler access, llms.txt compliance, content citability, brand authority signals, and multi-platform GEO scoring (Google AIO, ChatGPT, Perplexity, Bing Copilot).
praman-sap-planner-cli
SAP UI5 test planner via Playwright CLI. Token-efficient alternative to MCP planner. Generates test plan + gold-standard spec using CLI commands.
FAI Browser Agent
Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".