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 johnfkoo951/cmdspace-plugins --skill citation-managergit clone --depth 1 https://github.com/johnfkoo951/cmdspace-pluginsWrote 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/johnfkoo951/cmdspace-plugins/citation-manager)<a href="https://agentmods.dev/skills/johnfkoo951/cmdspace-plugins/citation-manager"><img src="https://agentmods.dev/badge/skills/johnfkoo951/cmdspace-plugins/citation-manager/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/johnfkoo951/cmdspace-plugins/citation-manager"><img src="https://agentmods.dev/badge/skills/johnfkoo951/cmdspace-plugins/citation-manager.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 | $0.00103 | $0.01263 |
| Opus 5.5 | $0.00041 | $0.00505 |
| Sonnet 5.5 | $0.00021 | $0.00253 |
| Haiku 4.5 | $0.00010 | $0.00126 |
Grade A, and why
citation-manager 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Citation Manager (독립 스킬)
원고의 인용과 참고문헌을 관리하는 독립 스킬입니다.
기능
- 인용 포맷 변환: 인라인 인용 + 참고문헌 목록을 지정 스타일로 변환
- 인용 감사 (Audit): 본문 인용과 참고문헌 목록의 일치 여부 검증
- DOI 검증: DOI 링크 존재 확인 (Firecrawl 스크래핑)
- Zotero 교차 검증: 볼트의 Zotero 레퍼런스와 대조
워크플로우
1. 입력 확인
사용자가 제공하는 입력:
- 원고 파일 경로 (필수)
- 인용 스타일 (기본: APA 7th)
2. 옵션 확인
AskUserQuestion으로 확인:
{
"questions": [
{
"header": "인용 스타일",
"question": "어떤 인용 스타일을 적용할까요?",
"options": [
{"label": "APA 7th (Recommended)", "description": "사회과학 표준. (Author, Year) 형식"},
{"label": "Chicago 17th", "description": "인문학. 각주 + 참고문헌"},
{"label": "IEEE", "description": "공학/CS. [1] 번호 형식"},
{"label": "기타", "description": "직접 스타일 지정"}
],
"multiSelect": false
},
{
"header": "작업 범위",
"question": "어떤 작업을 수행할까요?",
"options": [
{"label": "전체 (Recommended)", "description": "포맷 변환 + 감사 + DOI 검증"},
{"label": "감사만", "description": "인용-참고문헌 일치 여부만 검증"},
{"label": "포맷만", "description": "인용 스타일 변환만 수행"}
],
"multiSelect": false
}
]
}
3. 인용 감사 (Citation Audit)
원고 파일을 읽어:
A. 본문 인용 추출:
- 패턴:
(Author, Year),Author (Year),(Author1 & Author2, Year),(Author et al., Year) - 모든 인라인 인용을 목록으로 수집
B. 참고문헌 목록 추출:
- References 섹션에서 모든 항목 파싱
- Author, Year, Title, Journal, DOI 추출
C. 교차 검증:
| 상태 | 설명 |
|---|---|
| OK | 본문에 인용되고 참고문헌에도 있음 |
| Missing Reference | 본문에 인용되었으나 참고문헌 누락 |
| Orphaned Reference | 참고문헌에 있으나 본문에 인용 안 됨 |
| Year Mismatch | 본문과 참고문헌의 연도 불일치 |
| Author Mismatch | 본문과 참고문헌의 저자명 불일치 |
D. Zotero 교차 검증:
80. References/84. References (Zotero)/디렉토리 스캔@citekey.md파일과 매칭- 볼트에 있는 레퍼런스는 "Verified" 표시
4. DOI 검증 (선택)
각 DOI에 대해:
mcp__firecrawl-mcp__firecrawl_scrape으로https://doi.org/{DOI}접근- 응답 확인 → 존재하면 "Valid", 404면 "Invalid"
- Invalid DOI는
[INVALID DOI]플래그
5. 포맷 변환
APA 7th 포맷 규칙 (참조: references/apa7-guide.md):
본문 인용:
- 1-2 저자: (Kim & Lee, 2024)
- 3+ 저자: (Kim et al., 2024)
- 직접 인용: (Kim, 2024, p. 15)
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 · 129 lines · 103 tokens per session scan A e470b5097d42
citation-manager is a skill published in the GitHub repository johnfkoo951/cmdspace-plugins (7 stars, last pushed today), licensed MIT. It adds 103 tokens to every session and 1,263 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
obsidian-bases
Explain, draft, and validate Obsidian Bases .base files with filters, formulas, properties, summaries, and table, card, list, or version-gated kanban views. Use for Obsidian Bases, database-like vault views, dynamic tables, reading lists, task trackers, filters, formulas, summaries, and .base file edits.
wiki-ingest
Ingest supplied source material into an Obsidian vault with provenance and claim tracking: pasted text, files staged in the selected vault's inbox or .raw archive, or explicitly approved URLs. Use for a single source or bounded batch, not for saving an assistant answer. Triggers: ingest, ingest this file, ingest this…
autoresearch
Run a bounded, source-grounded research loop, draft a cited dossier, and optionally propose a separately reviewed canonical vault merge. Use when the user wants autonomous or deep research that may access the public web. Triggers: /autoresearch, autoresearch, research this topic, deep dive into, investigate, find…
wiki-retrieve
Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta…
ariadne:workspace-instructions
Create or update workspace-level instruction files for code repositories or ordinary project folders, including AGENTS.md, CLAUDE.md, GEMINI.md, local override files, and Ariadne vault-link blocks. Use when a user wants to initialize, repair, or refresh workspace instructions, connect a workspace to a registered…
ariadne:global-discovery
Register existing Markdown knowledge vaults for machine-level discovery so cold agents can find long-term knowledge from any workspace. Use when checking, adding, updating, repairing, or removing global vault discovery.