A skill that prints the local web address for The Luminarium, a dashboard for the moflo background service running on the current project.

Opening the moflo daemon dashboard, or getting the start command when the daemon is not running.

It finds the project's actual dashboard port so you do not need to inspect daemon files or guess the URL.

luminarium — Skill for Claude Code by eric-cielo: A skill that prints the local web address for…

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 skills/eric-cielo/moflo/luminarium

Any agent

npx skills add eric-cielo/moflo --skill luminarium

Clone the repo

git clone --depth 1 https://github.com/eric-cielo/moflo

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/eric-cielo/moflo/luminarium.svg)](https://agentmods.dev/skills/eric-cielo/moflo/luminarium)

Your own site

<a href="https://agentmods.dev/skills/eric-cielo/moflo/luminarium"><img src="https://agentmods.dev/badge/skills/eric-cielo/moflo/luminarium.svg" alt="Measured on agentmods" height="20"></a>

Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 760 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.

Model	Per session	Once invoked
Fable 5.1	$0.00081	$0.00760
Opus 5	$0.00041	$0.00380
Sonnet 5	$0.00016	$0.00152
Haiku 4.5	$0.00008	$0.00076

Measured 5d ago against content hash dd41d99cab46, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

luminarium 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 5d 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.

.claude/skills/luminarium/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/luminarium — Project Dashboard Link

Surface the URL for The Luminarium (the moflo daemon's localhost UI) for the project that this session is running in. No prompts, no confirmations — print the link and stop.

Procedure

Find the project root. Walk up from process.cwd() looking for a .moflo/ directory. The session's cwd is almost always the project root, so check there first.
Read .moflo/daemon.lock. It's a JSON file written by the daemon at bind time. The dashboard port is the port field:
```
{ "pid": 12345, "port": 33421, "startedAt": "...", ... }
```
- If the file exists and port is a valid number → the daemon is running and bound. Use that port.
- If the file is missing or port is absent/invalid → the daemon is not running. See step 4.
Print the link in a single line, with the path verbatim — Claude Code renders it as clickable:
```
The Luminarium: http://localhost:<port>
```
Nothing else. No banner, no follow-up question, no "what would you like to do?".
If the daemon isn't running (no lock file, or unparseable), say so in one line and offer the start command — don't run it:
```
The moflo daemon isn't running for this project. Start it with: npx flo daemon start
```

Why read the lock, not compute the port

The port is project-deterministic (sha256(projectRoot) mapped into 33000–33999), but if the deterministic port was already taken at bind time the daemon scans forward and binds an alternate. The lock file is the only source of truth for what's actually bound. Do not compute the hash yourself — read the file.

Don't

Don't fall back to any hardcoded port — there is no project-agnostic dashboard port; a literal would route to a foreign daemon on a multi-project machine. If the lock is missing, report "not running".
Don't compute the deterministic port and report it as the link when the lock is missing — the daemon may be down, or bound to an alternate port. Report "not running" instead.
Don't run flo daemon start automatically — the user asked for a link, not for daemon management. Leave starting to /healer or the user.
Don't open a browser. Print the URL; let the user click.

Read the full file on GitHub · 67 lines

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.

5d ago First seen · 67 lines · 81 tokens per session scan A dd41d99cab46

Subscribe to this mod's changes

luminarium is a skill published in the GitHub repository eric-cielo/moflo (18 stars, last pushed 2d ago), licensed MIT. It adds 81 tokens to every session and 760 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.

agent-orchestration ai-agents anthropic claude claude-code developer-tools

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

interview

Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.

Hmbown/CodeWhale · 40 tokens

local-frontend-check

Smoke-test or verify UI behaviour on the local Jarvis Registry frontend running at http://localhost/gateway. Use for manual regression checks, bug-fix verification, and end-to-end confirmation of specific flows without running the automated test suite.

ascending-llc/jarvis-registry · 52 tokens

luminarium