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 agentmods add commands/besty0728/unity-skills/skillcheckgit clone --depth 1 https://github.com/Besty0728/Unity-SkillsWhat 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 | $0.00000 | $0.07319 |
| Opus 5 | $0.00000 | $0.03660 |
| Sonnet 5 | $0.00000 | $0.01464 |
| Haiku 4.5 | $0.00000 | $0.00732 |
Grade A, and why
skillcheck 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 3d 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 — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Check — C# 代码与 SKILL.md 一致性审计 + 技能数量同步
你是 UnitySkills 项目的一致性审计助手。扫描所有 [UnitySkill] C# 定义与 skills/*/SKILL.md 文档，报告不一致问题；同时统计实际技能数量，与文档中声称的数字对比并修正（原 /skillcount 已并入本命令）。
目标
检测以下问题（这些是 v1.6.8 修复的那类 bug 的根源——文档声称支持的参数在代码中不存在）：
- 幽灵 Skill：SKILL.md 中记录了但 C# 代码中不存在的 Skill
- 完全无文档的 Skill：C# 中存在
[UnitySkill]但在整个skills/文档树中完全无提及的 Skill（注意：本项目为 schema-first 设计——skill 无需逐个写### skill_name定义，故"无###定义"本身不算缺陷，详见步骤 3a） - 参数不一致：SKILL.md 文档的参数表与 C# 方法签名不匹配（多余参数、缺失参数、类型不匹配）
- 元数据缺失：
[UnitySkill]特性中缺少Category、Operation、Tags、Outputs等关键元数据 - 数量失同步：文档（agent.md / README / README_CN / SKILL.md）中声称的技能总数与模块计数表和实际代码不一致
步骤 1：收集 C# Skill 定义
扫描 SkillsForUnity/Editor/Skills/*Skills.cs 中所有 [UnitySkill(...)] 标记的方法：
-
对每个 Skill 提取：
- Skill 名称（
[UnitySkill("skill_name", ...)]第一个参数） - Description 字符串（
[UnitySkill("name", "description string")]第二个参数，完整保留） - 方法签名（参数名、类型、是否可选、默认值）
- 元数据：Category、Operation、Tags、Outputs、RequiresInput、ReadOnly
- 所在文件和行号
- 条件编译宏：检查 Skill 方法是否位于
#if XXX块内（如PROBUILDER、XRI、UNITY_NETCODE、CINEMACHINE_2、CINEMACHINE_3等），记录对应的宏名称；不在任何#if块内的标记为"无条件" - 返回值字段：解析方法体中
return new { ... }匿名对象的字段名列表（正则提取即可，不需要完美覆盖所有分支）
- Skill 名称（
-
解析纪律（历史假绿源头，必须遵守）：
- 括号配平切分 attribute 块：一个 skill 的元数据只能取它自己
[UnitySkill(...)]块内的标注，严禁把同文件相邻块的元数据算到本 skill 头上 - 先剥
//注释再按逗号切分：带说明注释的 flag 否则会静默读成 false，审计报"零违规"是假绿 - 按技能名去重：
#if/#else分支下的同名 stub（URP 缺包时 Decal/PostProcess/URP/Volume 四个文件以相同技能名注册NoURP()占位实现）会让裸rg -c "\[UnitySkill\("多算 33 个 attribute（如 818 attribute → 785 唯一技能）。一切后续比对和计数都以"按第一个字符串参数去重后的唯一技能名"为准 SkillRouter.cs等非*Skills.cs文件中出现的[UnitySkill(多为注释/文档文字，不计入
- 括号配平切分 attribute 块：一个 skill 的元数据只能取它自己
-
Batch Skill 额外处理：对
*_batch后缀的 Skill，其方法签名通常只有string items，真正的参数定义在同文件的BatchXxxItem内部类中。额外提取该类的所有public属性（属性名、类型、默认值），作为 batch skill 的"实际参数列表"。 -
汇总为 C# Skill 清单
步骤 2：收集 SKILL.md 文档定义
扫描 SkillsForUnity/unity-skills~/skills/*/SKILL.md 中所有记录的 Skill：
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.
- 3d ago First seen · 325 lines · 0 tokens per session scan A 0f498e55ff8c
skillcheck is a command published in the GitHub repository Besty0728/Unity-Skills (1,695 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 7,319 tokens. 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 commands, from other repositories
tokenless-stats
Show Tokenless compression statistics.
diff
Compare two SKILL.md files section-by-section. Parses frontmatter and body sections independently, showing exactly what changed.
ui-flow-review
Review menus, HUD, navigation, and player flow from a UX perspective.
create-pull-request
Auto-generate Pull Request with comprehensive description, test plan, and changelog. Uses gh CLI for creation.
screenshot
Create a design based on screenshot.
play-dashboard
Play in the dashboard — the local viewer becomes your play surface, with a live AI DM beside it.