specter-competitions

specter-competitions is a skill for Claude Code, Codex from dirtcubeinteractive/specter-skills. It costs 95 tokens per session (932 once invoked), scanned A, original, MIT.

A service for running game competitions, including leaderboards, tournaments, and quick battles. It can handle rankings, entry fees, attempts, prize pools, prize distribution, and scheduled live events.

In plain words
What is it for?
Use it to show player rankings, run time-limited tournaments, accept scores, manage paid competitions, and display schedules and results.
Why use it?
It provides the competition rules and result handling that a game would otherwise need to build itself. Rankings and prizes may be finalised asynchronously after a competition window ends.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to show player rankings, run time-limited tournaments, accept scores, manage paid competitions, and display schedules and results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dirtcubeinteractive/specter-skills/specter-competitions
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 dirtcubeinteractive/specter-skills --skill specter-competitions
Clone the repo
git clone --depth 1 https://github.com/dirtcubeinteractive/specter-skills

Made for: Claude Code, Codex.

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 specter-competitions

README.md
[![agentmods](https://agentmods.dev/badge/skills/dirtcubeinteractive/specter-skills/specter-competitions/github.svg)](https://agentmods.dev/skills/dirtcubeinteractive/specter-skills/specter-competitions)
Your own site
<a href="https://agentmods.dev/skills/dirtcubeinteractive/specter-skills/specter-competitions"><img src="https://agentmods.dev/badge/skills/dirtcubeinteractive/specter-skills/specter-competitions/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.

agentmods 80×15 button for specter-competitions

Your own site · 80×15
<a href="https://agentmods.dev/skills/dirtcubeinteractive/specter-skills/specter-competitions"><img src="https://agentmods.dev/badge/skills/dirtcubeinteractive/specter-skills/specter-competitions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 932 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00095 $0.00932
Opus 5 $0.00048 $0.00466
Sonnet 5 $0.00019 $0.00186
Haiku 4.5 $0.00010 $0.00093

Measured 9d ago against content hash a1823fabe439, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

specter-competitions 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 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.

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.

skills/specter-competitions/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Specter Competitions — leaderboards, tournaments, instant battles

Base URL and headers: see the specter skill. Leaderboards/competitions are configured and scheduled in the dashboard; the game enters players, posts scores, and reads results.

Leaderboards

Configured with a source (what ranks players), an interval (daily / weekly / monthly / custom schedule — each run is an instance), and optional prize distribution rules.

Endpoint Auth Purpose
get-leaderboards api-key Catalog + config (interval, prizes)
leaderboards/get-rankings Bearer Top-N rankings for an instance (paginated)
leaderboards/get-results Bearer Player-centric results (my rank, around-me)
liveops/get-leaderboard-schedule-history api-key Past instances/windows

Scores typically flow in from match results or events per the leaderboard's source config. When an interval ends, a background job computes final rankings and distributes prizes asynchronously — results and wallet credits land minutes after the window closes, not instantly. Build "season ended, rewards incoming" UI states.

Tournaments

Time-boxed competitions with entry control and prize pools:

get-tournaments / app/get-tournaments        → discover (api-key)
competitions/check-attempts                  → can this player (still) enter?
competitions/enter                           → join (Bearer); RMG: competitions/enter-rmg-competition
                                               (debits entry fee from real-money wallet)
competitions/get-current-prize-pool          → live prize pool (RMG/pooled prizes)
competitions/post-score-to-tournament        → submit score after each attempt/run
competitions/get-tournament-rankings         → live standings
competitions/get-tournament-results          → final results + prizes after close
player/me/get-tournament-history             → player's past tournaments

Entry may be limited by attempts (check-attempts before showing the "Play" button), entry fees (virtual or real currency), and schedule windows. Prize distribution after close is async — same guidance as leaderboards.

Read the full file on GitHub · 87 lines

Files

What ships with it

60 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.

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. 9d ago First seen · 87 lines · 95 tokens per session scan A a1823fabe439

Subscribe to this mod's changes

specter-competitions is a skill published in the GitHub repository dirtcubeinteractive/specter-skills (0 stars, last pushed 2mo ago), licensed MIT. It adds 95 tokens to every session and 932 once invoked, about $0.0005 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.