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 skills add Haili321/haili-auto-mkt --skill luma-event-promogit clone --depth 1 https://github.com/Haili321/haili-auto-mktWrote 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.
[](https://agentmods.dev/skills/haili321/haili-auto-mkt/luma-event-promo)<a href="https://agentmods.dev/skills/haili321/haili-auto-mkt/luma-event-promo"><img src="https://agentmods.dev/badge/skills/haili321/haili-auto-mkt/luma-event-promo/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/haili321/haili-auto-mkt/luma-event-promo"><img src="https://agentmods.dev/badge/skills/haili321/haili-auto-mkt/luma-event-promo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00111 | $0.04700 |
| Opus 5 | $0.00056 | $0.02350 |
| Sonnet 5 | $0.00022 | $0.00940 |
| Haiku 4.5 | $0.00011 | $0.00470 |
Grade A, and why
luma-event-promo scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
import urllib.request, json How it starts
The opening of the file, as written. The whole thing — 456 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Luma Event Promo
What this skill is for
Launching a Luma event end-to-end without stepping on the half-dozen sharp edges Luma's interface and API hide. The standard path:
- Research 2-3 comparable events in the same city or scene
- Draft conversational copy that sounds human
- Create the event as Private (unlisted) so you can preview before sharing
- Fix the things Luma's default Create flow gets wrong (time, duration, capacity)
- Polish description structure, theme, font, cover photo
This skill captures the working recipes for each phase plus the surprises you only learn by doing it.
Mental model
Luma has two surfaces:
- The browser UI (
luma.com/create, manage pages). Good for: creating events from scratch, picking date from the calendar, uploading images. Bad for: bulk edits, setting fields the UI does not expose (duration_interval,tint_color,font_title), retries after errors. - The admin API at
https://api.lu.ma/event/admin/*. Authenticated by cookies (luma.did+luma.auth-session-key). Excellent for: editing every field after the event exists, updating the description as ProseMirror JSON, fixing time bugs, swappingcover_urlbetween existing Luma CDN images.
Cardinal rule: use the browser UI to create the event and upload images,
then use the API for everything else. Do not try to set start_at /
end_at through JS on the create form (it silently fails). Do not try
to upload images through Chrome MCP file_upload (it is blocked).
Setup
The admin API authenticates with two cookies pulled from a signed-in browser. The browser stays the source of truth; this skill borrows its session.
- Sign in to luma.com in any browser as the user who owns the event.
- Open DevTools (Cmd+Option+I on macOS), go to Application -> Cookies
->
https://luma.com. Copy these two:luma.did(random device id)luma.auth-session-key(looks likeusr-<user-id>.<session-secret>)
- Combine them into one cookie string and either export it or write it
to
~/.luma_cookie(gitignored):export LUMA_COOKIE='luma.did=...; luma.auth-session-key=usr-XXX.YYY' # or: printf 'luma.did=...; luma.auth-session-key=usr-XXX.YYY\n' > ~/.luma_cookie - Find the event api id. After creating an event, the manage URL is
https://luma.com/event/manage/evt-XXXXXXXXXXXXX. Copy theevt-XXXXXXXXXXXXXpart.export LUMA_EVENT_ID=evt-XXXXXXXXXXXXX # or: printf 'evt-XXXXXXXXXXXXX\n' > ~/.luma_event_id - Sanity-check by fetching the current event state:
python3 skills/luma-event-promo/scripts/update_event.py --get
What ships with it
6 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.
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.
- 12d ago First seen · 456 lines · 111 tokens per session scan A 2a58644aeddf
luma-event-promo is a skill published in the GitHub repository Haili321/haili-auto-mkt (2 stars, last pushed 3mo ago), licensed MIT. It adds 111 tokens to every session and 4,700 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
lark-task
A Feishu task-management tool for handling to-do items, task lists, assignments, subtasks, attachments, and task-focused agents. Feishu Tasks is Feishu's workspace for tracking work and responsibilities.
lark-approval
Instructions for using Lark’s approval tools, where Lark is a workplace platform with forms and approval workflows. They explain how to recognise approval requests and which tool references to read before acting.
lark-okr
A Feishu/Lark skill for managing OKRs, or objectives and measurable key results, across planning cycles.
calendar
Manage Lark calendar - view schedule, create/update/delete events, check availability, find meeting slots, RSVP to invitations. Use when user asks about meetings, schedule, availability, or calendar.
recipe-project-tracker
Sync project data between Lark and Notion.
daily-standup
An automated weekday stand-up process for a laboratory. It gathers yesterday's progress, today's plans, and blockers, then posts a summary to the lab's group chat at 09:30.