What is specter-admin?

An administration interface for configuring a game backend through an API. It covers game content and systems such as currencies, items, tasks, battle passes, rankings, competitions, events, and matches.

Use it to create and manage game projects, keys, stores, rewards, missions, progression systems, leaderboards, tournaments, live events, and matches.

It removes the need to configure these game systems manually in a dashboard or write the underlying administration requests yourself.

specter-admin — Skill for Claude Code and Codex by dirtcubeinteractive

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-admin

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dirtcubeinteractive/specter-skills/specter-admin.svg)](https://agentmods.dev/skills/dirtcubeinteractive/specter-skills/specter-admin)

Your own site

<a href="https://agentmods.dev/skills/dirtcubeinteractive/specter-skills/specter-admin"><img src="https://agentmods.dev/badge/skills/dirtcubeinteractive/specter-skills/specter-admin.svg" alt="Measured on agentmods" height="20"></a>

Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,873 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.

Model	Per session	Once invoked
Fable 5.1	$0.00099	$0.02873
Opus 5	$0.00049	$0.01437
Sonnet 5	$0.00020	$0.00575
Haiku 4.5	$0.00010	$0.00287

Measured 6d ago against content hash ccfcdf0f5b65, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

specter-admin 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 6d 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-admin/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.

Specter Admin — configure your game via API

⚡ First: use the Specter MCP server if it's connected

If the specter MCP server is available (tools named specter_create_currency, specter_create_item, specter_list_*, specter_login, etc.), use those tools to configure the backend — do NOT hand-roll the raw admin HTTP calls below. The MCP server handles authentication for you (a one-time browser sign-in), auto-detects the project, and clears the gateway. The raw API reference below is for when the MCP server is not connected, or for generating standalone scripts.

Never ask the user for their dashboard email/password. Member auth happens through a browser sign-in, not a pasted password. If a create/configure action needs auth:

With the MCP server: just call a create tool — it triggers specter_login (browser) when needed, or tell the user to run npx -p specter-skills specter-mcp login once.
Without the MCP server: tell the user to set up the specter MCP server (see the package README) and sign in — then ask again. Do not collect a password to call member/sign-in.

Everything the dashboard (https://console.specterapp.xyz) does, the admin API can do — useful for bulk content import, IaC-style game config, and CI pipelines.

This API mutates live game configuration. Two standing rules when generating admin integrations:

Always show the user what will be created/changed and get confirmation before calling mutating endpoints — especially */delete (destructive, archive/soft-delete).
Run against a dev/staging project first; admin changes are immediately visible to clients using that project's api-key.

Achievements — the four types (task / mission / step-series / time-series)

When a user asks to "configure an achievement / quest / mission / challenge / streak", first pick the right type. There are four, split across two endpoints:

Type	Endpoint	Discriminator	MCP tool	Use when…
Single task	`task/create`	—	`specter_create_task`	one objective → one reward ("win 10 matches", "log in today")
Mission	`task-group/create`	`typeId: 1`	`specter_create_mission`	a pool of tasks; player sees/does a subset per cycle ("daily missions", "rotating challenges", `noOfMissionsPerCycle`)
Step series	`task-group/create`	`typeId: 2`	`specter_create_step_series`	sequential — finish step 1 to unlock step 2 ("quest line", "tutorial chain")
Time series	`task-group/create`	`typeId: 3`	`specter_create_time_series`	per-window streak ("login 7 days in a row", "weekly, resets on miss"; `stageLength` + `interval`)

Read the full file on GitHub · 189 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.

6d ago First seen · 189 lines · 99 tokens per session scan A ccfcdf0f5b65

Subscribe to this mod's changes

specter-admin is a skill published in the GitHub repository dirtcubeinteractive/specter-skills (0 stars, last pushed 2mo ago), licensed MIT. It adds 99 tokens to every session and 2,873 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.

Backend and APIs Game development

league-akari-sgp-data-source

Use when implementing or reviewing League Akari SGP/LCU data-source selection, SGP API clients, League Servers remote config, Tencent cross-region queries, token handling, or per-feature SGP interoperability.

LeagueAkari/LeagueAkari · 50 tokens

csharp-godot

Use when working with C# in Godot — conventions, GodotSharp API differences from GDScript, project setup, and interop.

jame581/GodotPrompter · 34 tokens

cloudflare-durable-objects

Cloudflare Durable Objects for stateful coordination and real-time apps. Use for chat, multiplayer games, WebSocket hibernation, or encountering class export, migration, alarm errors.

secondsky/claude-skills · 43 tokens

gamedev-multiplayer

Use when adding multiplayer or netcode to a game — client-server vs P2P, server authority and anti-cheat, state replication vs RPCs, prediction and reconciliation, lag compensation, plus Godot 4 / Unity NGO / Unreal wiring. NOT single-player gameplay (that is godot, unity, unreal), NOT matchmaking or server hosting…

ericrisco/rsc-harness · 86 tokens

cloudflare-do-turn-based-multiplayer

Design, implement, debug, or verify a remote turn-based multiplayer game whose rooms run on Cloudflare Durable Objects. Use for room and invite identity, reconnectable seats, WebSocket hibernation, concurrent turns, action idempotency, revision conflicts, or cross-browser game-state agreement. Do not trigger for…

swyxio/skills · 80 tokens

roblox-cloud

Use for Roblox Open Cloud APIs, API keys, OAuth 2.0, webhooks, scopes, token lifecycle, or in-experience HttpService calls.

TabooHarmony/roblox-brain · 36 tokens