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 Cooperzheng/ue-dev-playbook --skill doc-consistency-auditgit clone --depth 1 https://github.com/Cooperzheng/ue-dev-playbookWrote 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/cooperzheng/ue-dev-playbook/doc-consistency-audit)<a href="https://agentmods.dev/skills/cooperzheng/ue-dev-playbook/doc-consistency-audit"><img src="https://agentmods.dev/badge/skills/cooperzheng/ue-dev-playbook/doc-consistency-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/cooperzheng/ue-dev-playbook/doc-consistency-audit"><img src="https://agentmods.dev/badge/skills/cooperzheng/ue-dev-playbook/doc-consistency-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 | $0.00084 | $0.01693 |
| Opus 5 | $0.00042 | $0.00847 |
| Sonnet 5 | $0.00017 | $0.00339 |
| Haiku 4.5 | $0.00008 | $0.00169 |
Grade A, and why
doc-consistency-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 10d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
文档一致性审计 & 上下文优化
本 Skill 分两个阶段执行:一致性审计(代码 vs 文档)和上下文优化(裁剪冗余 / 超长内容)。
代码永远是 Source of Truth。文档描述与代码不符时,以代码为准更新文档。
阶段一:一致性审计
1.1 执行方式
为每个需要审计的模块并发启动独立 subagent:
subagent_type: generalPurpose
readonly: false ← 需要写入文档
model: fast
每个 subagent 的任务 Prompt 模板:
你是 <模块名> 模块的文档一致性审查员,以代码为最终权威。
请完成以下任务:
**第一步 — 读取源码接口**
读取 <源码路径> 下的 .h 文件,提取:
- 所有 public 函数签名(UFUNCTION 和普通 public)
- 所有 UPROPERTY(EditAnywhere/BlueprintReadWrite/SaveGame 等)
- 关键枚举和结构体定义
**第二步 — 与 spec.md 对比**
读取 AI_Docs/<模块>/spec.md,逐项检查:
- 接口速查表中的函数/属性是否与源码一致(名称、参数、类型)
- 已删除的类/函数是否还在文档里
- 新增的接口是否遗漏
**第三步 — 检查 design.md 描述的流程**
读取 AI_Docs/<模块>/design.md,检查:
- "核心流程走读"中的类名、函数名是否与源码一致
- 数据流图中的组件关系是否准确
**第四步 — 修复**
以代码为准,更新 spec.md 和 design.md 中所有不一致之处。
- spec.md:更新接口表格、参数类型、函数名
- design.md:更新类名引用、流程步骤(保持叙述风格,只改不准确的部分)
- 保留 design.md 第一行的 <!-- AI NOTE --> 注释
**输出格式:**
发现的不一致:<逐条列出>
已修复:<逐条列出>
无需修改:<哪些部分已准确>
1.2 重点检查项
| 检查类型 | 具体验证 |
|---|---|
| 函数签名 | 参数名/类型/返回值是否与 .h 文件一致 |
| 资产路径 | /Game/Content/... 路径是否实际存在(用 MCP 或 Glob 验证) |
| 已删除内容 | 文档里提到但代码中已不存在的类/函数 |
| 枚举值 | enum 的枚举项名称和数量 |
| 委托签名 | DECLARE_DYNAMIC_MULTICAST_DELEGATE 参数是否准确 |
阶段二:上下文优化审计
2.1 执行方式
启动一个 readonly subagent 扫描所有文档,生成优化报告:
subagent_type: explore
readonly: true
model: fast
Prompt:
你是项目文档的上下文优化审查员,目标是减少 AI 不必要的 Token 消耗。
请扫描 AI_Docs/ 和 .cursor/rules/ 下的所有文件,报告以下问题:
**检查项 A:spec.md 超长(>200 行)**
对每个超过 200 行的 spec.md,分析:
- 哪些章节内容在 design.md 中已重复描述?(可以从 spec.md 中移除或缩减)
- 接口速查表是否有大量已弃用/未实现的接口(标注 ⬜ 的)占用空间?
- 是否有大段代码示例可以移到 design.md?
**检查项 B:主文档索引冗余**
读取主文档(CLAUDE.md 或等效文件),检查:
- "文档索引"中是否有条目 AI 从未需要查询(低频、仅人类关心)
- "快速问答索引"是否有重复问题指向同一文档
**检查项C:alwaysApply Rules 负担**
读取所有 alwaysApply: true 的 Rule 文件,评估:
- 每次对话都加载是否真的必要?
- 哪些可以改为 trigger-based(alwaysApply: false)?
- 每个 always-apply Rule 的大致行数
**检查项 D:changelog.md 需要归档**
对每个 changelog.md,检查是否超过 300 行(需要归档)
报告格式:
## A. 超长 spec.md
[文件] [行数] [建议操作]
## B. 主文档冗余
[具体条目] [建议]
## C. alwaysApply 负担
[Rule 文件] [行数] [是否可改为触发式] [理由]
## D. 需归档 changelog
[文件] [行数]
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.
- 10d ago First seen · 191 lines · 84 tokens per session scan A 3ff2e2294dc1
doc-consistency-audit is a skill published in the GitHub repository Cooperzheng/ue-dev-playbook (5 stars, last pushed 5mo ago), licensed MIT. It adds 84 tokens to every session and 1,693 once invoked, about $0.0004 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.