agentmods.dev

wiki-capture

wiki-capture is a skill for Claude Code, Codex from pivoshenko/pivoshenko.ai. It costs 125 tokens per session (657 once invoked), scanned A, original, MIT.

A maintenance check for an Obsidian vault, which is a folder of linked Markdown notes. It scans the vault and reports problems such as broken links, missing metadata, orphan notes, and outdated indexes.

In plain words
What is it for?
Use it to check vault health, find notes missing from the index, detect dead links, review stale projects, and identify unprocessed inbox items.
Why use it?
It helps find organizational and formatting issues before they make the vault harder to search or trust. Fixes require approval.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/volodymyr.pivoshenko/Library/Mobile.

not rated 4repo 4d ago A scan 125 tokens original MIT

Good fit Use it to check vault health, find notes missing from the index, detect dead links, review stale projects, and identify unprocessed inbox items.

Compare 6 skills from other repositories ↓
View source ↗ pivoshenko/pivoshenko.ai ai.pivoshenko.dev
Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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-capture

README.md
[![agentmods](https://agentmods.dev/badge/skills/pivoshenko/pivoshenko.ai/wiki-capture/github.svg)](https://agentmods.dev/skills/pivoshenko/pivoshenko.ai/wiki-capture)
Your own site
<a href="https://agentmods.dev/skills/pivoshenko/pivoshenko.ai/wiki-capture"><img src="https://agentmods.dev/badge/skills/pivoshenko/pivoshenko.ai/wiki-capture/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.

agentmods 80×15 button for wiki-capture

Your own site · 80×15
<a href="https://agentmods.dev/skills/pivoshenko/pivoshenko.ai/wiki-capture"><img src="https://agentmods.dev/badge/skills/pivoshenko/pivoshenko.ai/wiki-capture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 125 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 657 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00125 $0.00657
Opus 5 $0.00063 $0.00329
Sonnet 5 $0.00025 $0.00131
Haiku 4.5 $0.00013 $0.00066

Measured 9d ago against content hash 6f5d876b107a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

wiki-capture 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.

archive/skills/wiki-capture/SKILL.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wiki capture

Vault: /Users/volodymyr.pivoshenko/Library/Mobile Documents/iCloud~md~obsidian/Documents/Vault

Workhorse skill. Anything in -> right note out. No confirm for new notes; confirm before rewriting user-authored content.

Flow

  1. Read vault CLAUDE.md (schema) + INDEX.md (catalog). Always. Conventions live there, not here.
  2. Classify the input -> note type -> folder:
    • concept / evergreen idea -> 02 PERMANENT NOTES
    • project info / decision -> 03 PROJECTS (or hand to wiki-project)
    • investigation / open question -> 04 RESEARCH
    • talk/book/article/video -> 05 SOURCES (or hand to wiki-summarize if it needs summarizing)
    • blog/announcement idea -> 06 WRITING (or hand to wiki-write for a full draft)
    • unclear + low effort -> dump to 00 INBOX, done
  3. Check INDEX.md: page already exists -> update it (merge, don't duplicate). Else new note from matching 99 TEMPLATES/ template.
  4. Fill frontmatter per the contract in vault CLAUDE.md. created/updated = today.
  5. Wikilinks: link first mention of known concepts. Worthwhile new concept w/o page -> stub in 02 PERMANENT NOTES (frontmatter + one-line definition).
  6. Duties: INDEX.md entry + LOG.md line + bump updated on touched notes.
  7. Report: what was filed where, stubs created.

Inbox processing

"process my inbox" -> for each file in 00 INBOX/: run flow steps 2–6, then delete the inbox file. Empty inbox = done. Ambiguous item -> ask, don't guess-file. End with a quick lint sanity pass (INDEX drift + dead links only).

Rules

  • One concept per note. Plain descriptive filename, Title Case, no ID/date prefix.
  • Existing page wins over new page. Grep (rg) before creating.
  • Never edit 01 DAILY NOTES retroactively. Never touch 98 ATTACHMENTS.
  • Daily note mentions something durable -> extract to proper note, leave daily note untouched.
  • Vault path missing on disk -> remote session: return a formatted paste-ready block, never recreate vault structure elsewhere.

Read the full file on GitHub · 41 lines

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. 9d ago First seen · 41 lines · 125 tokens per session scan A 6f5d876b107a

Subscribe to this mod's changes

wiki-capture is a skill published in the GitHub repository pivoshenko/pivoshenko.ai (4 stars, last pushed 4d ago), licensed MIT. It adds 125 tokens to every session and 657 once invoked, about $0.0006 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.

Memory and contextWriting and docsagentsaiai-agentsai-skillsmcpobsidianskillswiki
Related

Other skills, from other repositories

wiki-export

Export the Obsidian wiki's knowledge graph to structured formats for use in external tools. Use this skill when the user says "export wiki", "export graph", "export to JSON", "export to Gephi", "export to Neo4j", "export to Postgres", "export to SQL", "graphml", "visualize wiki", "knowledge graph export", "export to…

Ar9av/obsidian-wiki · 172 tokens

wiki-query

Answer questions by searching the compiled Obsidian wiki. Use this skill when the user asks a question about their knowledge base, wants to find information across their wiki, asks "what do I know about X", "find everything related to Y", or wants synthesized answers with citations from their wiki pages. Also use when…

Ar9av/obsidian-wiki · 200 tokens

cross-linker

Scan the Obsidian wiki and automatically discover missing cross-references between pages. Use this skill when the user says "link my pages", "find missing links", "cross-reference", "connect my wiki", "add wikilinks", "what pages should be linked", or after any large ingestion to ensure new pages are woven into the…

Ar9av/obsidian-wiki · 137 tokens

pi-history-ingest

Ingest Pi coding agent session history into the Obsidian wiki. Use this skill when the user wants to mine their past Pi sessions for knowledge, import their /.pi/agent/sessions folder, extract insights from previous coding sessions, or says things like "process my Pi history", "add my Pi sessions to the wiki", "ingest…

Ar9av/obsidian-wiki · 112 tokens

wiki-agent

Query-driven targeted ingest from a specific AI agent's raw history. Use this skill when the user invokes /wiki-claude, /wiki-codex, /wiki-hermes, /wiki-openclaw, /wiki-copilot, /wiki-pi — with or without a search topic. Different from wiki-history-ingest (which bulk-ingests everything new): this skill finds sessions…

Ar9av/obsidian-wiki · 190 tokens

wiki-capture

Save the current conversation as a permanent, structured wiki note. Use this skill when the user says "save this", "/wiki-capture", "capture this", "file this conversation", "preserve this", "add this to my wiki", or wants to turn what was just discussed into lasting knowledge. The skill classifies the content…

Ar9av/obsidian-wiki · 197 tokens