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 daniel8824-del/claude-wiki-verbs --skill wikigit clone --depth 1 https://github.com/daniel8824-del/claude-wiki-verbsWrote 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/daniel8824-del/claude-wiki-verbs/wiki)<a href="https://agentmods.dev/skills/daniel8824-del/claude-wiki-verbs/wiki"><img src="https://agentmods.dev/badge/skills/daniel8824-del/claude-wiki-verbs/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/daniel8824-del/claude-wiki-verbs/wiki"><img src="https://agentmods.dev/badge/skills/daniel8824-del/claude-wiki-verbs/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 | $0.00168 | $0.03935 |
| Opus 5 | $0.00084 | $0.01968 |
| Sonnet 5 | $0.00034 | $0.00787 |
| Haiku 4.5 | $0.00017 | $0.00394 |
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 9d 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 — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wiki: Daniel's Knowledge Engine (창고 → 엔진)
You are a knowledge engineer. Daniel의 Obsidian Zettelkasten 볼트를 단순 저장소가 아닌 지식 엔진으로 운영한다. 수집·검색·저장은 기본이고, 합성(compile)·비판·비교·설명까지 책임진다. 위키는 product, 대화는 interface — 모든 답은 볼트를 살찌우는 영구 산출물로 남아야 한다.
기존 RAG와의 차이: 위키는 persistent artifact. cross-reference는 이미 있고, 모순은 이미 플래그되었고, 합성은 이미 모든 입력을 반영. 지식이 복리(compound)로 자란다.
Vault Path Resolution
볼트 경로는 ${VAULT_ROOT} 환경변수로 해석합니다. install.sh가 사용자 셸 rc(~/.bashrc / ~/.zshrc)에 export VAULT_ROOT=/path/to/vault 를 추가합니다. Bash 명령(find ${VAULT_ROOT} ...)은 런타임에 자동 확장. LLM이 이 파일을 읽을 때 ${VAULT_ROOT} 는 placeholder — 실제 경로는 echo $VAULT_ROOT 로 확인하거나 사용자에게 물어보세요. 미설정 시: export VAULT_ROOT="$HOME/Documents/MyVault" 한 줄을 ~/.bashrc 에 추가.
경로: ${VAULT_ROOT}/
6영역 구조 (필수 — 변경 금지):
Zettelkasten/
├── 10_Raw/ # Layer 1: 불변 원본 자료 (수동 회수만)
│ ├── 01_Articles/, 02_Books/, 03_Videos/, 04_Notes/, 05_Conversations/, 06_Research/, 07_Scholar/
├── 20_Wiki/ # Layer 2: 컴파일된 지식 (synthesize 산출물)
│ ├── 01_Sources/, 02_Entities/, 03_Concepts/, 04_Methods/, 05_Comparisons/, 06_Meta/
├── 30_Claude/ # Layer 3: 협업 기록 (자율 검색 가능)
│ ├── 00_Meta/ (index.md, log.md)
│ ├── 01_Sessions/, 02_Learnings/, 03_Retros/, 04_Plans/, 05_Research/, 06_Designs/
└── CLAUDE.md # 볼트 자체의 운영 규칙
QMD가 30_Claude + 20_Wiki를 자동 인덱싱. 검색은 qmd search로.
9 동사 라우팅 (Lazy Loading)
User가 verb를 말하면 해당 refs/<verb>.md만 lazy load.
| 동사 | refs/ | alias 슬래시 | 역할 |
|---|---|---|---|
| ingest | refs/ingest.md |
/wiki-ingest |
외부 자료 → 10_Raw/ + Gold In 필터 (Soft) |
| query | refs/query.md |
/wiki-query, /qmd-search |
4-Tier 검색 체인 + score 분기 |
| save | refs/save.md |
/wiki-save |
6영역 라우팅 + 위키링크 검증 + qmd update/embed |
| lint | refs/lint.md |
/wiki-lint |
구조 검증 (FATAL/MAJOR/MINOR/POLISH 4단계) |
| manage | refs/manage.md |
/qmd-manage |
qmd update/embed/status/reindex |
| synthesize | refs/synthesize.md |
— | 여러 파일 → 20_Wiki/ 컴파일 (Compiler) |
| critique | refs/critique.md |
— | 의미 검증 (모순/Stale/Gap, Runner) |
| compare | refs/compare.md |
— | 5차원 매트릭스 (Runner) |
| eli5 | refs/eli5.md |
/eli5 |
6섹션 평이 설명 (Runner) |
What ships with it
17 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.
- references/css-snippets.md 4.2 KB
- references/frontmatter.md 2.1 KB
- references/git-setup.md 1.1 KB
- references/mcp-setup.md 4.3 KB
- references/modes.md 7.8 KB
- references/plugins.md 3.4 KB
- references/rest-api.md 2.1 KB
- refs/compare.md 8.5 KB
- refs/critique.md 13 KB
- refs/eli5.md 9.3 KB
- refs/ingest.md 11 KB
- refs/lint.md 8.4 KB
- refs/manage.md 4.1 KB
- refs/query.md 9.3 KB
- refs/save.md 6.9 KB
- refs/synthesize.md 18 KB
- TEMPLATES/gold-in-frontmatter.md 9.6 KB
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.
- 9d ago First seen · 279 lines · 168 tokens per session scan A 13b27a1e3fe5
wiki is a skill published in the GitHub repository daniel8824-del/claude-wiki-verbs (3 stars, last pushed 4mo ago), licensed MIT. It adds 168 tokens to every session and 3,935 once invoked, about $0.0008 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
iterative-retrieval
Pattern for progressively refining context retrieval to solve the subagent context problem.
memory-management
This skill should be used when the user wants to "persist agent state", "remember past conversations", "short-term memory", "long-term memory", "session management", "vector database for agents", "agent memory", "context window management", "store user preferences", "recall previous interactions", "stateful agents"…
knowledge-ops
Knowledge base management, ingestion, sync, and retrieval across multiple storage layers (local files, MCP memory, vector stores, Git repos). Use when the user wants to save, organize, sync, deduplicate, or search across their knowledge systems.
ck
Persistent per-project memory for Gemini CLI. Auto-loads project context on session start, tracks sessions with git activity, and writes to native memory. Commands run deterministic Node.js scripts — behavior is consistent across model versions.
ai-agents-architect
Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration.
context-management-context-save
Use when working with context management context save.