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 mike007jd/game-superpowers --skill gsp-backend-selectorgit clone --depth 1 https://github.com/mike007jd/game-superpowersWrote 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/mike007jd/game-superpowers/gsp-backend-selector)<a href="https://agentmods.dev/skills/mike007jd/game-superpowers/gsp-backend-selector"><img src="https://agentmods.dev/badge/skills/mike007jd/game-superpowers/gsp-backend-selector/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/mike007jd/game-superpowers/gsp-backend-selector"><img src="https://agentmods.dev/badge/skills/mike007jd/game-superpowers/gsp-backend-selector.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 | $0.00026 | $0.00319 |
| Opus 5 | $0.00013 | $0.00160 |
| Sonnet 5 | $0.00005 | $0.00064 |
| Haiku 4.5 | $0.00003 | $0.00032 |
Grade A, and why
gsp-backend-selector 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 10d 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.
What it actually says
Game Backend Selector
Goal
Select the backend profile that best serves the requested outcome.
Use ./shared/reference/backend-profiles.md.
Outputs
Follow the gsp-orchestrator output strategy:
- inline (default): present backend decisions in conversation.
- minimal or full: write
docs/game-studio/backend-decision.md.
Rules
- Prefer capabilities over brand or fandom.
- If the project already has a workable backend, bias toward it unless it is the blocker.
- Optimize for the chosen quality target, not just the fastest toy result.
- Respect project state: live iteration and greenfield do not deserve the same backend decision policy.
Compare mode
Use compare mode only when:
- the backend choice is genuinely uncertain,
- or the user explicitly requests comparison.
When compare mode is used:
- warn that it will usually cost more tokens and time,
- keep the comparison narrow,
- define the winner criteria before exploring.
Specialist follow-through
After choosing a backend profile, route to a concrete specialist when needed:
gsp-web-2d-specialistforweb-2d-ui-firstorweb-2d-world-firstgsp-web-3d-specialistforweb-3d-preview
Top-level planning remains stack-neutral. Implementation guidance should still become concrete once a backend family is chosen.
What ships with it
6 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.
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.
- 10d ago First seen · 41 lines · 26 tokens per session scan A 180ed381f7b4
gsp-backend-selector is a skill published in the GitHub repository mike007jd/game-superpowers (12 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 319 once invoked, about $0.0001 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.
Other skills, from other repositories
pacing-and-the-player-journey
Use when designing, auditing, or generating the macro arc of an experience — how engagement rises and falls across an encounter, a session, a level, and an entire playthrough. Covers the interest curve and fractal pacing, tension/rest rhythm, novelty cadence and mid-game sag, nested engagement loops and retention…
game-design-fundamentals
The foundational design discipline — the spine the rest of the pack cross-links to. Use when judging whether a mechanic is fun, auditing a system for balance, designing difficulty/flow, setting reward schedules, checking player motivation, or diagnosing "my choices don't matter" / "this is grindy" / "this difficulty…
creating-squadjs-plugins
Use when creating, writing, or scaffolding a new SquadJS plugin, adding a server-side feature to a Squad server via SquadJS, or deciding whether SquadJS can support a desired behaviour ("can SquadJS detect X / do Y on a Squad server?"). Covers the plugin lifecycle, the full event/RCON capability surface, and the hard…
python-sdk
Implement or modify Python SDK behavior under python/composio, including tools, toolkits, sessions, auth configs, connected accounts, client integration, and shared Python models. Use for Python core runtime/API work; pair with python-testing and cross-sdk-parity when TypeScript must match.
potpie-infra-architecture
Use for project infra and architecture context: environments, adapters, runtime configuration, deployments, service dependencies, datastores, API contracts, ownership, incidents, and dependency blast radius.
ux-design
Guided, section-by-section UX spec authoring for a screen, flow, or HUD. Reads game concept, player journey, and relevant GDDs to provide context-aware design guidance. Produces ux-spec.md (per screen/flow) or hud-design.md using the studio templates.