floor10-submit

floor10-submit is a skill for Claude Code from Immersive-commons/ic-skills. It costs 128 tokens per session (2,620 once invoked), scanned A, original, MIT.

A guided submission workflow for sending a member's story and photos to the Immersive Commons moderation queue. A moderation queue is a review list where an administrator checks submissions before publishing them.

In plain words
What is it for?
Preparing and submitting HighlightStories about events or moments at Immersive Commons.
Why use it?
It organizes the required event link, role, photos, and description into a clean submission. It also helps members choose from events they attended and does not publish the story directly.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: names the AskUserQuestion tool.

Good fit Preparing and submitting HighlightStories about events or moments at Immersive Commons.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/immersive-commons/ic-skills/floor10-submit
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.

Any agent
npx skills add Immersive-commons/ic-skills --skill floor10-submit
Clone the repo
git clone --depth 1 https://github.com/Immersive-commons/ic-skills

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.

agentmods badge for floor10-submit

README.md
[![agentmods](https://agentmods.dev/badge/skills/immersive-commons/ic-skills/floor10-submit.svg)](https://agentmods.dev/skills/immersive-commons/ic-skills/floor10-submit)
Your own site
<a href="https://agentmods.dev/skills/immersive-commons/ic-skills/floor10-submit"><img src="https://agentmods.dev/badge/skills/immersive-commons/ic-skills/floor10-submit.svg" alt="Measured on agentmods" height="20"></a>
Per session 128 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,620 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00128 $0.02620
Opus 5 $0.00064 $0.01310
Sonnet 5 $0.00026 $0.00524
Haiku 4.5 $0.00013 $0.00262

Measured 7d ago against content hash 9128360ea4d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

floor10-submit 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 7d 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.

curl -s -H "Authorization: Bearer $FLOOR10_AGENT_TOKEN" \
.claude/skills/floor10-submit/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a floor member's submission helper. Your one job: take what the human gives you (a Luma URL, photos, a one-liner about what they did) and ship a clean HighlightStory to the IC moderation queue. An admin reviews and publishes. You do NOT publish.

Pre-flight (always)

Before doing anything, confirm two things:

  1. Token is set. The member must have FLOOR10_AGENT_TOKEN in their environment, OR they paste it inline. The token starts with agt_.
  2. Member identity. You don't need to ask — the token attributes the submission. But mention it in the preview so they catch a wrong-token paste.

The pipeline (always this order)

1. Gather inputs

Try the discovery feed first. Before asking the human to paste a URL, fetch their recent attended events and let them pick:

curl -s -H "Authorization: Bearer $FLOOR10_AGENT_TOKEN" \
  "https://www.immersivecommons.com/api/floor10/claimable-events?limit=15"

The response is { ok, member_id, count, events: [{ event_api_id, title, date, status, url, program, episode, ... }] }. Show the human the list (formatted as [date] title — status) and ask which event they want to write about. Use AskUserQuestion if you can; otherwise number-pick. The chosen event gives you the URL + title + date for free; skip ahead to step 3 (extract any extra metadata you still need).

If the feed returns count: 0 (member is brand new, attendance hasn't ingested yet, or the data is stale), fall back to asking for the URL manually as below.

Ask the human (use AskUserQuestion when several knobs are open at once; otherwise plain prompts):

  • Event URL — Luma is the canonical case (e.g. https://luma.com/abc1234). LinkedIn post URLs and X tweet URLs also valid. Ask them to paste it.
  • Their action — verb-clause that completes " <event_title>". Default suggestions: spoke at, hosted, paneled at, demoed at, moderated, keynoted, co-organized. Pick the one that fits the role.
  • Photos — get them to URLs. Acceptable sources:
    • Luma cover URL (auto-extractable from the event page — you'll grab this in step 2)
    • LinkedIn post images (right-click → copy image address)
    • Their own hosted images (Cloudinary, Drive shared link)
    • Local photos — use the upload helper, don't punt to imgur:
      # multipart upload (any client):
      curl -X POST -H "Authorization: Bearer $FLOOR10_AGENT_TOKEN" \
        -F "file=@/path/to/photo.jpg" \
        https://www.immersivecommons.com/api/ingest/highlights/image
      # → { url: "https://...vercel-blob.../floor10/highlights/<member>/<sha256>.jpg", ... }
      
      Or via MCP: call the floor10_upload_image tool with { url: "<source>" } (server fetches + re-hosts) or { data_url: "data:image/jpeg;base64,..." } for inline. Max 8 MB per upload, 30 uploads / token / UTC day, separate from the 3-submissions/day budget. Same bytes always return the same URL (content-addressed dedup).
  • Stats — optional but recommended. Convention: RSVPS / ORGANIZATION / ROLE. Ask if they know the RSVP count; otherwise leave stats off.

Read the full file on GitHub · 189 lines

Files

What ships with it

1 file 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.

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. 7d ago First seen · 189 lines · 128 tokens per session scan A 9128360ea4d0

Subscribe to this mod's changes

floor10-submit is a skill published in the GitHub repository Immersive-commons/ic-skills (0 stars, last pushed 1mo ago), licensed MIT. It adds 128 tokens to every session and 2,620 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.

Related

Other skills, from other repositories

ray

Generate code screenshots via ray.tinte.dev API. Use when user asks for code screenshots, code images, code snippets as images, or says "ray". Calls POST https://ray.tinte.dev/api/v1/screenshot and saves the PNG result.

Railly/tinte · 52 tokens

youtube-cli

Searches YouTube and fetches video transcripts via the cli-web-youtube command-line tool — video search, video details (views, duration, description, keywords), trending by category, channel info, and timestamped transcripts/captions with language selection and translation. Use when the user asks about YouTube…

ItamarZand88/CLI-Anything-WEB · 105 tokens

maya-render

Pipeline stage — render globals, final-frame rendering, and viewport capture: configure render settings, query them, render frames, capture playblasts. Use for producing final or preview imagery. Not for modeling (maya-mesh-ops), animation editing (maya-animation), generic file import/export (maya-geometry), or render…

dcc-mcp/dcc-mcp-maya · 77 tokens

maya-scripting

Bootstrap stage — escape hatch for Maya work that has no packaged skill yet. Agents should prefer searchskills / dcccapabilitymanifest → loadskill → typed tools (inputSchema + annotations) from domain skills; use executepython or executemel only when no skill matches, for bulk in-process loops, or for API…

dcc-mcp/dcc-mcp-maya · 100 tokens

dcc-mcp-maya-setup

Set up dcc-mcp-maya for an agent or operator: install Maya Python dependencies with mayapy, generate MCP host configuration, guide the user through loading the Maya plugin, and run a first live-tool smoke prompt.

dcc-mcp/dcc-mcp-maya · 55 tokens

gigachat-image

An image-generation workflow for GigaChat, an AI service that creates pictures from text descriptions. It also supports checking the remaining usage allowance and adding an uploaded reference image.

theYahia/WWmcp · 20 tokens