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 Xerolo44/RPG-Maker-MV-MCP --skill rpgmaker-balancinggit clone --depth 1 https://github.com/Xerolo44/RPG-Maker-MV-MCPWrote 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/xerolo44/rpg-maker-mv-mcp/rpgmaker-balancing)<a href="https://agentmods.dev/skills/xerolo44/rpg-maker-mv-mcp/rpgmaker-balancing"><img src="https://agentmods.dev/badge/skills/xerolo44/rpg-maker-mv-mcp/rpgmaker-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/xerolo44/rpg-maker-mv-mcp/rpgmaker-balancing"><img src="https://agentmods.dev/badge/skills/xerolo44/rpg-maker-mv-mcp/rpgmaker-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 | $0.00047 | $0.00764 |
| Opus 5.5 | $0.00019 | $0.00306 |
| Sonnet 5.5 | $0.00009 | $0.00153 |
| Haiku 4.5 | $0.00005 | $0.00076 |
Grade A, and why
rpgmaker-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 13d 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Balancing with numbers, not guesses
Principles
- Decide the target experience first, then measure it: hits-to-kill for normal enemies (2-4), for bosses (10-25), and how many enemy hits a party member survives (3-6).
- Change one lever at a time (class curves, enemy stats, skill formulas, gear) and re-measure.
- Formulas and traits are described in
rpgmaker://reference/damage-formulasandrpgmaker://reference/trait-codes.
Tools
balance_report- class stat curves, damage vs enemy HP (hits to kill) and enemy threat vs your classes. Start here; read thewarnings.simulate_battle {troopId, party}- Monte-Carlo run of a troop against a party (win rate, turns, survivors, who does the damage). Use it for bosses and for spot-checking dungeon progression. It uses the real damage formulas, variance, crits, hit/evasion and turn order; skills with states or special effects are approximated as plain damage.generate_param_curve- writes a class stat curve from a start and end value with a shape (linear,ease-in,ease-out,ease-in-out,exponential,logistic). Dry run by default, shows sample levels.generate_enemy_scaling- spreads stats along a curve over an ordered list of enemies (weakest to strongest) for smooth difficulty progression, includingexpandgold.bulk_update_records- "all weapons +10% attack":changes: [{field: "params.atk", op: "percent", value: 10}]. Filter withidsorwhere. Dry run is the default; show the diff, then repeat withdryRun: false.
Workflow
balance_report-> note the outliers.- Fix the cause: a class curve that falls behind (
generate_param_curve), an enemy tier out of line (generate_enemy_scaling), a skill that is too strong (update_recordon itsdamage.formula). - Preview bulk changes with
bulk_update_recordsbefore applying. simulate_battlethe key fights; aim for the win rate and turn count you decided on.- Repeat until the report has no warnings you do not accept. Tell the user which numbers you changed and why.
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.
- 13d ago First seen · 35 lines · 47 tokens per session scan A b646cecc54c6
rpgmaker-balancing is a skill published in the GitHub repository Xerolo44/RPG-Maker-MV-MCP (8 stars, last pushed 12d ago), licensed MIT. It adds 47 tokens to every session and 764 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-24.
rpgmaker-balancing compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| rpgmaker-balancingXerolo44/RPG-Maker-MV-MCP | Skill | 8 | 12d ago | MIT | A | 47 | Claude Code, Codex |
| playtest-reportDonchitos/Claude-Code-Game-Studios | Skill | 36k | 19d ago | MIT | A | 20 | Claude Code |
| godot-signals-groupsgamedev-skills/awesome-gamedev-agent-skills | Skill | 6.9k | 10d ago | Apache-2.0 | A | 95 | Claude Code |
| scenario-unreal-gameplayscenario-labs/skills | Skill | 3.2k | yesterday | MIT | A | 121 | Claude Code |
| motionOpenDCAI/GameFactory-3A | Skill | 1.0k | 8d ago | Apache-2.0 | A | 0 | Claude Code, Codex |
| unity-addressablesBesty0728/Unity-Skills | Skill | 1.9k | yesterday | MIT | A | 25 | Claude Code, Codex |
| unity-manual-componentBesty0728/Unity-Skills | Skill | 1.9k | yesterday | MIT | A | 36 | Claude Code, Codex |