graph-open

A command that explains how to open the graph-engineering web interface when access requires a human-only token. The token is shown in the graph server’s startup message.

In plain words
What is it for?
It is for telling a person where to find the interface address and token needed to unlock runs, answer questions, approve commands, or stop a run.
Why use it?
It prevents agents from wasting time looking for a token they cannot access or use themselves.

Command

Install

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.

agentmods
npx agentmods add commands/sciencemj/graph-engineering/graph-open
Clone the repo
git clone --depth 1 https://github.com/sciencemj/graph-engineering
Per session 5 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 135 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00005 $0.00135
Opus 5 $0.00003 $0.00068
Sonnet 5 $0.00001 $0.00027
Haiku 4.5 $0.00001 $0.00014

Measured yesterday against content hash ee4fc9fc0a44, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

graph-open 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 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.

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.

commands/graph-open.md · 17 lines

What it actually says

The web UI requires the human-only full-authority token (ui_token). It is stored in no file, so you cannot know it and must not try to find it.

The MCP server printed one line like this to stderr on startup:

[graph-engineering] UI: http://localhost:<port>/#t=<ui_token>

Tell the user to find that line and paste it into a browser. If they cannot find it, restarting Claude Code prints it again. Unlocking, human answers, command approvals, and aborting a run all happen only in that UI.

Changes

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.

  1. yesterday First seen · 17 lines · 5 tokens per session scan A ee4fc9fc0a44

Subscribe to this mod's changes

graph-open is a command published in the GitHub repository sciencemj/graph-engineering (0 stars, last pushed 1mo ago), licensed MIT. It adds 5 tokens to every session and 135 once invoked, about $0.0000 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 2026-08-31.