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 PracticalSwan/agent-skills --skill scale-gamegit clone --depth 1 https://github.com/PracticalSwan/agent-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/practicalswan/agent-skills/scale-game)<a href="https://agentmods.dev/skills/practicalswan/agent-skills/scale-game"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/scale-game/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/practicalswan/agent-skills/scale-game"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/scale-game.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 | $0.00027 | $0.01025 |
| Opus 5 | $0.00014 | $0.00513 |
| Sonnet 5 | $0.00005 | $0.00205 |
| Haiku 4.5 | $0.00003 | $0.00103 |
Grade A, and why
scale-game 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scale Game
Overview
Test your approach at extreme scales to find what breaks and what surprisingly survives.
Core principle: Extremes expose fundamental truths hidden at normal scales.
Quick Reference
| Scale Dimension | Test At Extremes | What It Reveals |
|---|---|---|
| Volume | 1 item vs 1B items | Algorithmic complexity limits |
| Speed | Instant vs 1 year | Async requirements, caching needs |
| Users | 1 user vs 1B users | Concurrency issues, resource limits |
| Duration | Milliseconds vs years | Memory leaks, state growth |
| Failure rate | Never fails vs always fails | Error handling adequacy |
Process
- Pick dimension - What could vary extremely?
- Test minimum - What if this was 1000x smaller/faster/fewer?
- Test maximum - What if this was 1000x bigger/slower/more?
- Note what breaks - Where do limits appear?
- Note what survives - What's fundamentally sound?
Examples
Example 1: Error Handling
Normal scale: "Handle errors when they occur" works fine At 1B scale: Error volume overwhelms logging, crashes system Reveals: Need to make errors impossible (type systems) or expect them (chaos engineering)
Example 2: Synchronous APIs
Normal scale: Direct function calls work At global scale: Network latency makes synchronous calls unusable Reveals: Async/messaging becomes survival requirement, not optimization
Example 3: In-Memory State
Normal duration: Works for hours/days At years: Memory grows unbounded, eventual crash Reveals: Need persistence or periodic cleanup, can't rely on memory
Red Flags You Need This
- "It works in dev" (but will it work in production?)
- No idea where limits are
- "Should scale fine" (without testing)
- Surprised by production behavior
Remember
- Extremes reveal fundamentals
- What works at one scale fails at another
- Test both directions (bigger AND smaller)
- Use insights to validate architecture early
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.
- 4d ago Changed fe41ddf9fb65
- 6d ago Changed 6e0ed61a735b
- 8d ago First seen · 112 lines · 27 tokens per session scan A ed02f0b6338e
scale-game is a skill published in the GitHub repository PracticalSwan/agent-skills (14 stars, last pushed 4d ago), licensed MIT. It adds 27 tokens to every session and 1,025 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 2026-09-03.
Other skills, from other repositories
dma-attack-techniques
Classify hardware DMA threats, host-driver memory acquisition and network or USB transport in game-security research. Use for PCIe/FPGA, IOMMU/VT-d, Thunderbolt/USB4, LeechCore, WinPmem, bridge-cable claims, device identity and acquisition forensics; select repository resources for architecture, remapping concepts and…
anti-cheat-systems
Analyze layered game integrity defenses and select repository resources for process-memory reports, acquired-memory forensics, callback scope, behavioral measurement and driver-policy evidence. Use for DMA versus host-mediated acquisition, input provenance, replay fidelity, collector health, detector rollout/recovery…
game-hacking-techniques
Classify game-cheating threats across client memory, code injection, rendering, input, engines, kernels, DMA and remote transports. Use for repository-backed attack-surface maps, attacker prerequisites, state exposure, legitimate comparison baselines, and observable artifacts. Select engine source, capture or…
graphics-api-hooking
Analyze Direct3D/DXGI, OpenGL, and Vulkan rendering, presentation, composition, and capture evidence. Use to distinguish API samples, PresentMon event metrics, Tracy instrumentation, compatibility translation, frame images, and validation diagnostics; review swap chains, overlays, resource lifetime, and…
reverse-engineering-tools
Investigate supplied game binaries, protection components, drivers, dumps, and traces through reproducible binary analysis. Use for repository resource selection, PE/symbol inspection, disassembly and decompilation, control/data-flow reconstruction, build comparison, obfuscation classification, and interface evidence…
awesome-game-security-overview
Find, select and maintain resources in awesome-game-security using its actual README taxonomy, skill catalog, compiled wiki, generated descriptions and source archives. Use for repository-specific discovery, category placement, duplicate or identity review, missing/case-mismatched local paths, and choosing the right…