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 Illuminated2020/agentic-wiki --skill wikigit clone --depth 1 https://github.com/Illuminated2020/agentic-wikiWrote 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/illuminated2020/agentic-wiki/wiki)<a href="https://agentmods.dev/skills/illuminated2020/agentic-wiki/wiki"><img src="https://agentmods.dev/badge/skills/illuminated2020/agentic-wiki/wiki/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/illuminated2020/agentic-wiki/wiki"><img src="https://agentmods.dev/badge/skills/illuminated2020/agentic-wiki/wiki.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 | $0.00072 | $0.01354 |
| Opus 5.5 | $0.00029 | $0.00542 |
| Sonnet 5.5 | $0.00014 | $0.00271 |
| Haiku 4.5 | $0.00007 | $0.00135 |
Grade A, and why
wiki 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 1mo 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wiki Skill
操作用户的多域个人 Obsidian LLM Wiki。负责定位仓库、选择操作分支、加载权威协议并执行工作流。
Contract
按以下边界维护单一事实源：
- 本 skill：意图路由、操作编排、Lint 执行方式和硬防线。
<WIKI_ROOT>/CLAUDE.md：项目边界、工作流、通用页面契约和全局维护规则。<WIKI_ROOT>/sources/CLAUDE.md与<WIKI_ROOT>/<知识域>/CLAUDE.md：局部页面类型、字段、正文结构和专属 workflow。
skill 与协议冲突时，以协议为准。不要在 skill 里维护第二份页面契约。
Wiki Root
按以下优先级定位 WIKI_ROOT：
- 如果环境变量
WIKI_ROOT已设置，使用其指向的绝对路径。 - 否则解析 skill 软链得到 canonical 实文件路径，并从其所在目录运行
git rev-parse --show-toplevel。 - 如果仍失败，向上查找同时含
CLAUDE.md、purpose.md与index.md的目录。
定位后必须验证根目录同时存在 CLAUDE.md、purpose.md 与 index.md。如果用户显式设置的 WIKI_ROOT 无效，立即说明配置错误并停止，不得静默回退到其他目录。不得在入 git 文件中硬编码某台机器的 vault 绝对路径。
Activation
- 读取
<WIKI_ROOT>/purpose.md、CLAUDE.md和index.md。 - Query：读取
references/wiki-query.md、相关知识域index.md，再读取最相关页面。 - Ingest / Update：读取
sources/CLAUDE.md（涉及来源时）、相关知识域CLAUDE.md和index.md。 - Lint：根据被检查页面的路径读取对应域
CLAUDE.md，再按当前 vault 的实际结构执行检查。 - Restructure：再读取
references/wiki-structure.md。
渐进式加载限制内容阅读，不限制命令式结构检查。
Intent Routing
| 用户信号 | 分支 |
|---|---|
| 分享文章/链接并要求处理、入库、ingest | Ingest |
| 查 wiki、询问 wiki 里有什么 | Query |
| lint、检查 wiki、健康检查 | Lint |
| 更新或修正已有页面 | Update |
| 新增、删除、重命名知识域或调整目录 | Restructure |
| wiki todo / wiki idea | 读取对应文件和域规则；写入前取得用户确认 |
| 生成公开文章、对外总结、导出材料 | Query + 分享边界检查 |
Operation Execution
- Ingest / Query / Update：按根
CLAUDE.md的对应工作流执行；页面表示以所属域或sources/CLAUDE.md为准。 - Restructure：额外读取
references/wiki-structure.md。只把可路由内容目录当作知识域；sources/与logs/是基础设施层。 - Lint：根据当前 vault 实际结构选择
rg、find等只读命令，检查结构、frontmatter、索引覆盖、日志格式、Wikilink、来源追溯、overview 和跨域一致性。不得依赖固定脚本或假定目录一定非空。默认只报告；只有用户明确要求修复时才修改文件。
Non-Negotiables
sources/raw/只允许新建，不修改已有文件。ideas/writing.md、ideas/products.md、todo.md只有用户确认后才可写入。- 新增、删除、移动或重命名页面时更新对应 index；仅修改既有页面正文或 frontmatter 时只验证索引覆盖。
- 所有写操作追加
logs/YYYY-MM.md；月度日志本身严格追加，不回改顶部元数据。 - 对外输出检查
share_scope：sensitive默认不外发，private需用户确认。 - Query 不得绕过已有 wiki 页面直接凭模型常识回答。
- Ingest 必须基于完整 raw 原文；对不确定事实联网查证。
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.
- 1mo ago First seen · 98 lines · 72 tokens per session scan A 021277a36731
wiki is a skill published in the GitHub repository Illuminated2020/agentic-wiki (11 stars, last pushed 3mo ago), licensed MIT. It adds 72 tokens to every session and 1,354 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.