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 Lagunaswift/GameDevelopmentAudit --skill reward-psychology-auditgit clone --depth 1 https://github.com/Lagunaswift/GameDevelopmentAuditWrote 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/lagunaswift/gamedevelopmentaudit/reward-psychology-audit)<a href="https://agentmods.dev/skills/lagunaswift/gamedevelopmentaudit/reward-psychology-audit"><img src="https://agentmods.dev/badge/skills/lagunaswift/gamedevelopmentaudit/reward-psychology-audit/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/lagunaswift/gamedevelopmentaudit/reward-psychology-audit"><img src="https://agentmods.dev/badge/skills/lagunaswift/gamedevelopmentaudit/reward-psychology-audit.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 | $0.00116 | $0.01141 |
| Opus 5 | $0.00058 | $0.00571 |
| Sonnet 5 | $0.00023 | $0.00228 |
| Haiku 4.5 | $0.00012 | $0.00114 |
Grade A, and why
reward-psychology-audit 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 12d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reward Psychology Audit
Reward systems steer behaviour whether or not the designer intends it. The same machinery that makes progression satisfying can make a game compulsive and joyless, and players feel the difference even when they keep playing. This skill designs reward loops that motivate toward fun and audits existing ones for misalignment and manipulation.
Core concepts
Wanting and liking are different circuits. Anticipation of a reward drives action; the pleasure of receiving it is separate and smaller. Systems can make players want intensely without liking at all. A game that players cannot stop playing but do not enjoy has captured wanting and abandoned liking; treat that as a defect, not a retention win.
Reinforcement schedules shape behaviour predictably. Fixed-ratio rewards (every Nth action) produce bursts of effort then pauses after payout. Variable-ratio rewards (random chance per action) produce steady, persistent, hard-to-extinguish behaviour; this is the slot-machine schedule and the reason loot rolls are so gripping. Real games superimpose several schedules, and schedules also emerge uninvited from mechanics (drop tables, spawn odds). Know which schedules a design is running, including the accidental ones.
Extrinsic rewards can crowd out intrinsic joy. Paying players (XP, badges, currency) for an activity they already enjoy reframes the activity as work; remove the payment later and enjoyment does not return. Reserve extrinsic rewards for bridging players into activities whose intrinsic fun takes time to reach, and keep them light where the activity carries itself.
Alignment is the core test. Rewards should point at play the game is proud of. Misaligned rewards manufacture grind: if the XP-optimal path is repetitive and dull, players will take it and resent it, because reward systems outvote fun in guiding behaviour.
Player's remorse is the tell. The signature of a manipulative loop is a player who, after stopping, regrets the time spent. Compulsion metrics (session length, streaks) cannot distinguish a loved game from a trap; regret can. Design so that a player looking back endorses the time they gave.
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.
- 12d ago First seen · 46 lines · 116 tokens per session scan A 99ab227b4cf1
reward-psychology-audit is a skill published in the GitHub repository Lagunaswift/GameDevelopmentAudit (5 stars, last pushed 2mo ago), licensed MIT. It adds 116 tokens to every session and 1,141 once invoked, about $0.0006 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
gameobject-component-destroy
Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.
unity-version-split
Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).
godot-signals-groups
Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…
motion
How an agent turns a character mesh into a usable animated FBX — and how to judge whether the result is shippable.
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
threejs-exposure-color-grading
Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.