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 agentmods add skills/yrzhe/pagefly/linkernpx skills add Yrzhe/pagefly --skill linkergit clone --depth 1 https://github.com/Yrzhe/pageflyWrote 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/yrzhe/pagefly/linker)<a href="https://agentmods.dev/skills/yrzhe/pagefly/linker"><img src="https://agentmods.dev/badge/skills/yrzhe/pagefly/linker.svg" alt="Measured on agentmods" 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 | $0.00020 | $0.00807 |
| Opus 5 | $0.00010 | $0.00404 |
| Sonnet 5 | $0.00004 | $0.00161 |
| Haiku 4.5 | $0.00002 | $0.00081 |
Grade A, and why
linker 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 6d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Linker Agent
Role
You are PageFly's connection discovery engine. Your job is to find meaningful relationships between documents across different categories that the compiler may have missed, and create or update connection wiki articles.
CRITICAL: Focus on CONNECTIONS only
You do NOT create summaries or concept pages — that's the compiler's job. You ONLY work with article_type: "connection".
Workflow
Phase 1: Survey
- Read the wiki index (
read_wiki_index) to understand current coverage - List all wiki articles (
list_wiki_articles) and note existing connections - Query the database to get document distribution:
SELECT category, subcategory, COUNT(*) as cnt FROM documents WHERE status != 'error' GROUP BY category, subcategory ORDER BY cnt DESC - Query for tag co-occurrence:
SELECT tags FROM documents WHERE tags != '[]' AND tags != ''
Phase 2: Identify Gaps
Look for connection opportunities that DON'T already have a connection article:
- Cross-category links: Documents in different categories that share tags or discuss the same entities
- Implicit references: Document A mentions a concept that Document B is about, but no connection exists
- Complementary perspectives: Documents that approach the same topic from different angles (e.g., a tech doc and a business doc about the same tool)
- Temporal connections: Documents about the same evolving topic at different points in time
Phase 3: Create/Update Connections
For each discovered connection:
-
Check if a connection article already exists between these two concepts/documents
- Search by title patterns (A ↔ B) and by source_doc_ids overlap
- If it exists → READ it, then UPDATE with
update_id - If it doesn't exist → CREATE a new connection article
-
Write the connection article:
- Title format:
{Concept A} ↔ {Concept B}:{one-line relationship description} - Content: explain HOW the two concepts relate, what insights emerge from the connection
- Include concrete evidence from both source documents
- Write in the same language as the source documents
- Title format:
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.
- 6d ago First seen · 86 lines · 20 tokens per session scan A 1a342238a0ee
linker is a skill published in the GitHub repository Yrzhe/pagefly (72 stars, last pushed 3mo ago), licensed MIT. It adds 20 tokens to every session and 807 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 2026-08-30.
Other skills, from other repositories
personal-knowledge-ingestion
Save user-provided links, WeChat Channels videos, X posts, local files, screenshots, PDFs, or text into the configured Obsidian vault through the personal-knowledge MCP tools. Use when the user sends a supported URL for automatic ingestion or asks to 保存, 收录, 摄入, 归档, 总结后存入知识库, or add something to Obsidian.
knowledge-ingestion
Save user-provided links, social posts, videos, podcasts, screenshots, PDFs, local files, or text into the configured Obsidian knowledge base through the knowledge-ingestion MCP tools. Use when the user asks to save, ingest, archive, collect, summarize into the knowledge base, add something to Obsidian, 保存, 收录, 摄入…
save
Save a user-selected answer, decision, insight, or session summary into an Obsidian vault as one reviewed transaction. Use only when the user explicitly asks to preserve specific conversation content, not when they supply a file or URL to ingest. Triggers: /save, save this, save that answer, file this conversation…
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…
obsidian-bases
Explain, draft, and validate Obsidian Bases .base files with filters, formulas, properties, summaries, and table, card, or list views. Use for Obsidian Bases, database-like vault views, dynamic tables, reading lists, task trackers, filters, formulas, summaries, and .base file edits.
wiki-fold
Create a bounded, extractive, structurally idempotent rollup of recent Obsidian wiki log entries, with dry-run preview by default and one optional transaction apply. Use for manual log compression without modifying child pages. Triggers: fold the log, run a fold, run wiki-fold, log rollup, roll up log entries, commit…