agentmods.dev

wiki-audit

wiki-audit is a skill for Claude Code, Codex from GYF0311/lorekit. It costs 29 tokens per session (844 once invoked), scanned A, original, MIT.

A wiki-maintenance workflow for reviewing human feedback files, correcting the pages they refer to, and filing the resolved feedback. A wiki is a collection of linked documentation pages.

In plain words
What is it for?
Use it to list open feedback, inspect the affected page, make factual or structural corrections, record the resolution, and run a quick check.
Why use it?
It turns scattered correction requests into a traceable review process and keeps the documentation aligned with what people report.

Skill for Claude CodeCodex

not rated 5 1mo ago A scan 29 tokens original MIT
View the source file GYF0311/lorekit
Install

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.

agentmods
npx agentmods add skills/gyf0311/lorekit/wiki-audit
Any agent
npx skills add GYF0311/lorekit --skill wiki-audit
Clone the repo
git clone --depth 1 https://github.com/GYF0311/lorekit

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for wiki-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/gyf0311/lorekit/wiki-audit.svg)](https://agentmods.dev/skills/gyf0311/lorekit/wiki-audit)
Your own site
<a href="https://agentmods.dev/skills/gyf0311/lorekit/wiki-audit"><img src="https://agentmods.dev/badge/skills/gyf0311/lorekit/wiki-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 844 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00029 $0.00844
Opus 5 $0.00015 $0.00422
Sonnet 5 $0.00006 $0.00169
Haiku 4.5 $0.00003 $0.00084

Measured 4d ago against content hash fe8a03617cdf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wiki-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 4d 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.

skills/wiki-audit/SKILL.md · 94 lines

What it actually says

wiki-audit

处理 corpus 中的人类反馈条目（反馈/待处理/*.md），逐条审阅、修正目标页面、归档已处理反馈。

When to trigger

  • 用户说"处理反馈"、"review audit"、"check feedback"
  • lorekit audit --list --open 显示有待处理条目
  • 用户说"看看有什么需要改的"、"审阅知识库"

不要触发：

  • 用户只是提一个新反馈 → 直接 lorekit audit --create ...
  • 查询已有内容 → wiki-query

Tools to use

  • lorekit audit --list --open — 列出待处理反馈
  • lorekit audit --list --resolved — 列出已处理反馈
  • lorekit audit --create --target <file> --severity <info|suggest|warn|error> --text "..." — 新建反馈
  • lorekit lint --quick — 修改后自检
  • 底层：Read / Edit / mv

Workflow

列出待处理

  1. 运行 lorekit audit --list --open
  2. 展示给用户，按 severity 排序（error → warn → suggest → info）
  3. 问用户要处理哪条，或逐条处理

处理单条反馈

  1. 读 audit 文件：Read 反馈/待处理/xxx.md，理解反馈内容
  2. 读 target 文件：Read audit frontmatter 里 target 指向的 wiki 页面
  3. 理解反馈意图：对照反馈文本和 target 内容，确定修改方案
  4. 修改 target：
    • 事实性修正 → 改 ## Compiled Truth
    • 补充信息 → 追加 ## Timeline 条目
    • 结构调整 → 按 filing-rules 重组
  5. 刷新 target 的 updated 字段：frontmatter 中 updated: YYYY-MM-DD
  6. 移动 audit 文件：mv 反馈/待处理/xxx.md 反馈/已处理/xxx.md
  7. 追加 resolution：在 audit 文件末尾追加： 
    ---
## Resolution
- 处理时间：YYYY-MM-DD HH:mm
- 操作：修改了 xxx
- 结果：已修正/已驳回/部分采纳
  8. 自检：lorekit lint --quick
  9. 汇报（见 Output format）

批量处理

  1. lorekit audit --list --open 获取全部待处理
  2. 逐条按上述流程处理
  3. 每条处理完展示差异让用户确认，再进行下一条
  4. 全部完成后汇总报告

驳回反馈

如果反馈不合理或已过时：

  1. 移动到 反馈/已处理/
  2. Resolution 中标注"已驳回"并说明原因
  3. 不修改 target 文件

Output format

审阅反馈：反馈/待处理/20260416-100000-xxx.md
  severity: error
  target:   知识库/实体/xxx.md
  反馈内容：xxx
  处理方式：修正了 Compiled Truth 中的 xxx
  结果：已修正
  lint：PASS

批量处理完后汇总：

本轮处理 N 条反馈：
  - 已修正：X 条
  - 已驳回：Y 条
  - 部分采纳：Z 条
Changes

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.

  1. 4d ago First seen · 94 lines · 29 tokens per session scan A fe8a03617cdf

Subscribe to this mod's changes

wiki-audit is a skill published in the GitHub repository GYF0311/lorekit (5 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 844 once invoked, about $0.0001 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.

LLMWriting and docsai-agentclaude-codeembeddingkarpathyknowledge-base
Related

Other skills, from other repositories

mindbase

Maintain a persistent AI-tended research wiki. Activates when the user wants to ingest a source (PDF, URL, article, paste), capture a thought, build the wiki context, query what's already known, lint for orphans/contradictions, or maintain page conventions. Phrases include "add this to my wiki", "today I decided…"…

frankchu91/mindbase-llm-wiki · 105 tokens

wiki-ingest

Ingest exactly one research paper or source document into an open-llm-wiki vault. Use when the user explicitly asks to add, ingest, process, or publish a paper into the wiki. The workflow parses the source, drafts a source page, runs independent QA, publishes only after the quality gate passes, extracts and normalizes…

AIwork4me/open-llm-wiki · 116 tokens

query-writeback

Answer cross-source questions about an open-llm-wiki vault and optionally write reusable synthesis back into concept pages. Use when the user asks a wiki question that requires comparing, connecting, or tracing multiple source/concept pages. By default answer first and propose writeback; modify files only when the…

AIwork4me/open-llm-wiki · 82 tokens

wiki-lint

Run a health check for an open-llm-wiki vault. Use when the user asks to lint, audit, validate, or periodically check wiki quality. The default mode is report-only: inspect schema compliance, QA coverage, links, stale claims, contradictions, and log health. Modify files only when the user explicitly requests fix mode…

AIwork4me/open-llm-wiki · 84 tokens

zenwiki-ask

Search this local ZenWiki and answer questions about its content with citations. Use this whenever the user asks anything about wiki topics — what / how / why / compare / list / which — that might be answered by pages under wiki/. Always run zenwiki search first; never answer from memory.

ChenXplorer/zenwiki · 63 tokens

openkb-deck-neon

Use when the user asks the openkb chat to make a deck / slide presentation / PPT / slides / 演示稿 / 幻灯片 from their compiled KB content AND wants a dark, high-tech, neon / glow / glassmorphism look (赛博 / 科技风 / 暗色 / 霓虹 / 炫酷). Generates a polished single-file HTML deck in the Aurora Glass visual direction (near-black…

VectifyAI/OpenKB · 173 tokens