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 Immersive-commons/ic-skills --skill ic-leaderboardgit clone --depth 1 https://github.com/Immersive-commons/ic-skillsWrote 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/immersive-commons/ic-skills/ic-leaderboard)<a href="https://agentmods.dev/skills/immersive-commons/ic-skills/ic-leaderboard"><img src="https://agentmods.dev/badge/skills/immersive-commons/ic-skills/ic-leaderboard/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/immersive-commons/ic-skills/ic-leaderboard"><img src="https://agentmods.dev/badge/skills/immersive-commons/ic-skills/ic-leaderboard.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 | $0.00112 | $0.03283 |
| Opus 5 | $0.00056 | $0.01641 |
| Sonnet 5 | $0.00022 | $0.00657 |
| Haiku 4.5 | $0.00011 | $0.00328 |
Grade A, and why
ic-leaderboard 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 9d 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 -H "Authorization: Bearer $FLOOR10_AGENT_TOKEN" \ How it starts
The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You help an agent's human join the IC commits leaderboard at https://www.immersivecommons.com/floor10/commits. The leaderboard counts weekly commits across the linked GitHub account and renders on the FT10 kiosk TV. Three steps: confirm the user can grant the scopes, link their GitHub, opt them in.
AI-assisted onboarding (end-to-end, what to do AND what to say)
This is the whole arc an agent runs on its human's behalf. Each step lists the tool call AND the one thing to communicate to the human — the detailed request/response handling lives in the sections below.
-
Link GitHub. Call
ic_leaderboard_connect_githubwith a PAT the human pastes (discarded after username verification), OR have the human link via the Clerk OAuth browser flow. Both end at the same linked-username state. → Say: "I linked your GitHub as<login>. I only stored your username — the token is discarded and IC never gets write access to your account." -
Opt in. Call
ic_leaderboard_set_optinwithoptIn: true. Requires a linked GitHub identity (step 1). → Say: "You're opted in. Your row shows up on the next leaderboard refresh (~20 min)." -
(Optional) Count private work. By default only PUBLIC commits count. To fold in private/restricted contributions, the human enables one GitHub setting — web-only, one click, no API, no deep-link: open their GitHub profile → click "Contribution settings" above the contribution graph → enable "Private contributions". IC reads only the COUNT, never repo names or content. → Say: "If you want your private work counted too, flip one GitHub toggle: profile → 'Contribution settings' above your contribution graph → enable 'Private contributions'. IC only ever sees the number, never your repos. I can't flip it for you — there's no API for it — so it's a quick click on your end."
-
Verify. Call
ic_leaderboard_get_status. ConfirmoptIn: true, the linkedgithub_username, and (if they did step 3)private_counting: "on". → Say: "Confirmed: you're on the board as<username>, rank<rank>" — and if they enabled private: "and your private contributions are now counted (private_counting: on)." Ifprivate_countingstill reads"off"right after they toggled, tell them the cron just needs a refresh cycle.
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.
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.
- 9d ago First seen · 255 lines · 112 tokens per session scan A 3ae50ac50d26
ic-leaderboard is a skill published in the GitHub repository Immersive-commons/ic-skills (0 stars, last pushed 2d ago), licensed MIT. It adds 112 tokens to every session and 3,283 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
git-wrapup
Land working-tree changes as logical commits — the work grouped by concern, topped by a release commit (version bump, changelog, regenerated artifacts). Verify, commit. Stops at "committed locally on main" — or, when the project releases through a release PR, at "release branch pushed, PR open". No tag, no push to…
commit-and-push
Stage, commit, and push changes without opening a PR. Use when the user says "commit and push", "commit these to a new branch", "push this branch", or wants a branch + commit summary but does not want PR creation. Distinct from yeet, which owns the commit + push + PR flow.
pr
Create a pull request using the Dedalus PR template. Injects git state, commit history, and diff stats automatically.
git-workflow
Trunk-based git workflow with worktrees, switch/restore over checkout, Conventional Commits, force-with-lease. Use whenever the user asks me to commit, push, branch, or rebase.
french-commit-message
Génère un message de commit git en français au format Conventional Commits à partir des changements stagés. Récupère automatiquement le diff via git diff --staged. À utiliser quand l'utilisateur demande un commit message, message de commit, ou résumé de diff en français.
git-wrapup
Review verified mcp-reporter changes, prepare versioned changelog entries, create logical commits and an annotated local tag. No push or publish.