Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/dirtcubeinteractive/specter-skillsnpx agentmods add skills/dirtcubeinteractive/specter-skills/specterWrote 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/dirtcubeinteractive/specter-skills/specter)<a href="https://agentmods.dev/skills/dirtcubeinteractive/specter-skills/specter"><img src="https://agentmods.dev/badge/skills/dirtcubeinteractive/specter-skills/specter.svg" alt="Measured on agentmods" 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 | $0.00103 | $0.01664 |
| Opus 5 | $0.00051 | $0.00832 |
| Sonnet 5 | $0.00021 | $0.00333 |
| Haiku 4.5 | $0.00010 | $0.00166 |
Grade A, and why
specter 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 -X POST $BASE/app/welcome -H "api-key: $API_KEY" How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Specter — Game Backend as a Service
Specter is a backend platform for games. Instead of building your own backend, your game calls Specter's REST APIs (and WebSocket server for multiplayer) for accounts, virtual economy, missions/achievements, leaderboards, tournaments and matchmaking. Game content (currencies, items, tasks, leaderboards…) is configured in the Specter dashboard at https://console.specterapp.xyz; your game then reads and acts on that content via the client API.
Base URLs
| Environment | Client REST API | Multiplayer (Socket.io) |
|---|---|---|
| Production | https://api.specterapp.xyz/v2/client |
https://multiplayer.specterapp.xyz |
| Staging | https://client.staging.specterapp.xyz/v2/client |
https://staging.multiplayer.specterapp.xyz |
Quick connectivity check: POST {base}/app/welcome.
Always use the v2 client API. v1 exists but is legacy — do not build new integrations on it.
The two credentials (read this first)
api-keyheader — required on every request. Issued per project + environment in the dashboard (dev / qa / production keys are different). Identifies which game/project the call is for.Authorization: Bearer <accessToken>header — required for player-scoped endpoints (anythingplayer/me/*, purchases, inventory changes, score posts…). Obtained from anyauth/login-*orauth/signup-*endpoint. The JWT embedsuserId+projectIdand expires in ~1 hour — refresh withauth/refresh-token.
Endpoints listed as "API Key" auth in the references work without a user token (app-level catalog reads, plus server-to-server lookups of other players' data).
All client endpoints use POST with a JSON body — even reads. Filters, pagination
(offset/limit) and the attributes array (opt-in response fields) go in the body.
Response envelope
Every endpoint returns the same shape — branch on status/code, read payload from data:
{
"status": "success",
"code": 200,
"message": "Items list",
"data": { ... },
"errors": []
}
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.
- references/api/app-get-battlepasses.md 1001 B
- references/api/app-get-bundles.md 966 B
- references/api/app-get-currencies.md 296 B
- references/api/app-get-document-content.md 441 B
- references/api/app-get-documents.md 583 B
- references/api/app-get-gacha-bundle-config.md 589 B
- references/api/app-get-games.md 1.3 KB
- references/api/app-get-info.md 430 B
- references/api/app-get-instant-battles.md 320 B
- references/api/app-get-items.md 964 B
- references/api/app-get-leaderboards.md 304 B
- references/api/app-get-markers.md 840 B
- references/api/app-get-master-data.md 274 B
- references/api/app-get-matches.md 284 B
- references/api/app-get-missions.md 313 B
- references/api/app-get-players.md 831 B
- references/api/app-get-progression-systems.md 330 B
- references/api/app-get-step-series.md 324 B
- references/api/app-get-store-categories.md 733 B
- references/api/app-get-store-category-contents.md 767 B
- references/api/app-get-stores.md 818 B
- references/api/app-get-tasks.md 301 B
- references/api/app-get-time-series.md 324 B
- references/api/app-get-tournaments.md 305 B
- references/api/app-welcome.md 254 B
- references/authentication.md 3.6 KB
- references/client-api-index.md 3.0 KB
- references/curated-client-api.md 20 KB
- references/endpoints-index.md 1.2 KB
- references/endpoints/app-get-document-content-v2.md 1.6 KB
- references/endpoints/app-get-documents-v2.md 2.3 KB
- references/endpoints/app-get-master-data-v2.md 9.5 KB
- references/endpoints/app-welcome-v2.md 1.0 KB
- references/endpoints/get-games-v2.md 7.7 KB
- references/endpoints/get-info-v2.md 4.2 KB
- references/endpoints/liveops-get-server-time-v2.md 1.3 KB
- references/environments.md 954 B
- references/errors.md 2.8 KB
- references/manual-index.md 2.1 KB
- references/manual/additional-resources__feedback-and-support.md 775 B
- references/manual/additional-resources__product-versioning.md 2.0 KB
- references/manual/additional-resources__specter-api-reference.md 2.0 KB
- references/manual/additional-resources__specter-manual-versioning.md 724 B
- references/manual/additional-resources__specter-unity-sdk.md 2.5 KB
- references/manual/additional-resources__terms-of-service-and-privacy-policy.md 564 B
- references/manual/analyze__overview.md 989 B
- references/manual/build__games__game-configuration.md 1.5 KB
- references/manual/build__games__understanding-apps-and-games-on-specter.md 716 B
- references/manual/build__games.md 1021 B
- references/manual/build__overview.md 1.9 KB
- references/manual/community-and-growth__overview.md 1.4 KB
- references/manual/getting-started__dashboard.md 3.7 KB
- references/manual/getting-started__introducing-specter.md 5.6 KB
- references/manual/getting-started__onboarding.md 2.4 KB
- references/manual/product-roadmap__detailed-feature-pipeline-descriptions.md 11 KB
- references/manual/product-roadmap__feature-pipeline.md 6.7 KB
- references/manual/product-roadmap__overview.md 2.8 KB
- references/manual/unity-sdk__getting-started__configuration-and-initialization.md 3.9 KB
- references/manual/unity-sdk__getting-started__installation.md 2.8 KB
- references/manual/unity-sdk__getting-started__make-your-first-api-call.md 1.1 KB
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.
- 7d ago First seen · 139 lines · 103 tokens per session scan A 1e159e796ef4
specter is a skill published in the GitHub repository dirtcubeinteractive/specter-skills (0 stars, last pushed 2mo ago), licensed MIT. It adds 103 tokens to every session and 1,664 once invoked, about $0.0005 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
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.
csharp-godot
Use when working with C# in Godot — conventions, GodotSharp API differences from GDScript, project setup, and interop.
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.
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…
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…
roblox-cloud
Use for Roblox Open Cloud APIs, API keys, OAuth 2.0, webhooks, scopes, token lifecycle, or in-experience HttpService calls.