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 rondorkerin/gamestack --skill difficulty-and-balancinggit clone --depth 1 https://github.com/rondorkerin/gamestackWrote 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/rondorkerin/gamestack/difficulty-and-balancing)<a href="https://agentmods.dev/skills/rondorkerin/gamestack/difficulty-and-balancing"><img src="https://agentmods.dev/badge/skills/rondorkerin/gamestack/difficulty-and-balancing/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/rondorkerin/gamestack/difficulty-and-balancing"><img src="https://agentmods.dev/badge/skills/rondorkerin/gamestack/difficulty-and-balancing.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 | $0.00173 | $0.00820 |
| Opus 5 | $0.00086 | $0.00410 |
| Sonnet 5 | $0.00035 | $0.00164 |
| Haiku 4.5 | $0.00017 | $0.00082 |
Grade A, and why
difficulty-and-balancing 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 9d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Difficulty & Balancing
The discipline of ensuring no single option dominates and every player stays in the flow channel — made rigorous by encoding balance as testable invariants and verifying them through simulation, not intuition alone.
Tier: universal craft (→
gamestack-core). Applies across all genres and multiplayer contexts. The encounter-difficulty application lives incombat-design; economy and loot power-budget live inrpg-systems.
When to use this
- Auditing a system for dominant strategies (God-tier lock-in, degenerate meta, solved builds)
- Verifying cost-curve balance across a weapon, card, or unit roster
- Designing or tuning a difficulty curve — encounter sequence, wave rhythm, spike detection
- Specifying or auditing a DDA system (target metric, adjustment range, visibility decision)
- Designing difficulty settings and per-axis accessibility assists
- Building a pre-ship balance spreadsheet or instrumenting post-ship telemetry
Scope
This skill owns the balance and difficulty of game systems — option viability, cost curves, difficulty curves, DDA, and accessibility. Adjacent concerns live in sibling skills:
- The "interesting decision / no dominant option" principle as a design foundation →
game-design-fundamentals(this skill operationalizes that invariant) - Encounter difficulty, enemy telegraphing, and encounter feel →
combat-design - Economy tuning, loot tables, and power-budget math →
rpg-systems - Macro difficulty pacing across a session arc →
pacing-and-the-player-journey - Procedural content gating and generation constraints →
procgen-review - Fairness and player expectations under permanent death →
permadeath-and-lethality
How the pieces fit
GUIDE.md— the cited why, in five sub-domains: dominant strategies & degenerate cases; balance structures (symmetric/asymmetric/intransitive + cost-curve/power-budget); difficulty curves & DDA / hidden directors; difficulty settings & accessibility; metrics-driven balance (spreadsheets, simulation, telemetry). Each rule carries an exemplar + source, a test-for criterion, the named failure mode, and the procedural/headless implication.CHECKLIST.md— Do/Don't + machine-checkable Test-for criteria, grouped by sub-domain. Written to be enforced as automated validators in a generation or build-gate loop.
What ships with it
2 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.
- 9d ago First seen · 41 lines · 173 tokens per session scan A 9c5f3c7aef3d
difficulty-and-balancing is a skill published in the GitHub repository rondorkerin/gamestack (27 stars, last pushed 2mo ago), licensed MIT. It adds 173 tokens to every session and 820 once invoked, about $0.0009 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 2026-08-30.
Other skills, from other repositories
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.
consistency-check
Scan all GDDs against the entity registry to detect cross-document inconsistencies: same entity with different stats, same item with different values, same formula with different variables. Grep-first approach — reads registry then targets only conflicting GDD sections rather than full document reads.
ux-review
Validates a UX spec, HUD design, or interaction pattern library for completeness, accessibility compliance, GDD alignment, and implementation readiness. Produces APPROVED / NEEDS REVISION / MAJOR REVISION NEEDED verdict with specific gaps.
swallowtail
Use the complete Godot development loop from the swallowtail CLI: discover the live engine API, build and edit in the open editor, run and play the game, observe state, debug failures, fix them in place, and verify the result. Use when the task involves creating or modifying a Godot project, testing game behavior…
debug-issue
Systematic Godot debugging decision trees for physics, signals, rendering, navigation, and input issues.
asset-audit
Audits game assets for compliance with naming conventions, file size budgets, format standards, and pipeline requirements. Identifies orphaned assets, missing references, and standard violations.