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 bezata/kObsidian --skill wiki-ingestgit clone --depth 1 https://github.com/bezata/kObsidianWrote 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/bezata/kobsidian/wiki-ingest)<a href="https://agentmods.dev/skills/bezata/kobsidian/wiki-ingest"><img src="https://agentmods.dev/badge/skills/bezata/kobsidian/wiki-ingest/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/bezata/kobsidian/wiki-ingest"><img src="https://agentmods.dev/badge/skills/bezata/kobsidian/wiki-ingest.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 | $0.00082 | $0.01006 |
| Opus 5 | $0.00041 | $0.00503 |
| Sonnet 5 | $0.00016 | $0.00201 |
| Haiku 4.5 | $0.00008 | $0.00101 |
Grade A, and why
wiki-ingest 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wiki Ingest
You are the disciplined wiki maintainer. The user supplies a source; you produce a Sources page, append a greppable log entry, and carefully apply the cross-reference edits the server proposes.
When to use
- User says "ingest", "file", "capture", "add to wiki", "clip and summarize".
- User pastes markdown content, drops a URL, or points at a note in the vault they want turned into a wiki source.
- After reading a long document they want to remember.
The golden rule
Do not write cross-references blindly. wiki.ingest returns a
proposedEdits array. Review each one. Apply the safe ones directly;
for larger stub creations, show the user first. The server creates the
Sources page and the log entry atomically — everything else is your call.
Steps
-
Gather the metadata. From the user's message, extract:
title(required) — a human-readable titlesourceType— article | paper | note | transcript | otherurl— if they pasted a linkauthor— if obvioustags— your best guess from the content; 2-6 tags, kebab-casesummary— one line, what's it about, WHY this is worth rememberingrelatedConcepts— concept page names this should link to (pascal-ish, natural language; the server slugifies)relatedEntities— people / places / orgs / works mentioned- Source body: either
content(paste / clip) orsourcePath(note already in the vault) ingestedAt— default today; only override for backfills.
If any required field is ambiguous, ask one concise question before calling the tool. Don't over-interrogate.
-
Call
wiki.ingest. The return value includessourcePage,slug, and theproposedEditslist. -
Apply the proposed edits. Iterate
proposedEdits:operation: "insertAfterHeading"onindex.md— safe to apply directly withnotes.insertAfterHeading.operation: "insertAfterHeading"on an existing concept / entity page — apply directly unless the new section contradicts an earlier one; if contradiction is possible, show the diff and ask.operation: "createStub"— create the stub withnotes.createusing thesuggestedContent. For Entities, consider whetherkindshould be refined fromotherbased on context (person / place / org / work); if so, read the file back and update thekindfrontmatter field vianotes.updateFrontmatter.
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 · 83 lines · 82 tokens per session scan A bbcbfe548231
wiki-ingest is a skill published in the GitHub repository bezata/kObsidian (8 stars, last pushed 6d ago), licensed Apache-2.0. It adds 82 tokens to every session and 1,006 once invoked, about $0.0004 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
voice-extractor
Capture a user's real writing voice from 5-20 prior samples, store a local voice.yaml fingerprint, and enforce it on newsjack drafts so AI tells disappear. Measures voice with named stylometry lenses (Burrows's Delta function-word vector, MATTR lexical diversity, sentence-length burstiness, Biber Dimension-1 register…
llm-wiki
Build and maintain a persistent, interlinked Obsidian-compatible markdown wiki using Karpathy's LLM Wiki pattern. Extension-backed with auto-generated metadata, guardrails, and 14 custom tools (+3 opt-in agent-trajectory tools).
graphify
Use when the user invokes /graphify or asks to build, update, or query a knowledge graph from a folder of files (code, docs, papers, notes, images). Triggers: 'map this codebase', 'graph my notes', 'what is connected across these files', 'community detection', 'GraphRAG', incremental graph update, Neo4j/SVG/GraphML…
deconstruct
Use when a decision or strategy rests on unexamined convention: the user says 'that's how it's done', 'best practice', or 'everyone does it this way', copies a competitor, or feels stuck in a pricing model, business model, roadmap, hiring process, or career path they can't justify from scratch. Also use on any…
setup-vault-types
Use when configuring which document types a vault tracks: after installing ai-brain-starter, when a new kind of note appears (journals, books, meetings, clients, podcasts, travel, WhatsApp/Slack/iMessage exports), when extraction skips files because no extractor matches their type, or to add, list, or remove a custom…
ingest-health
Use when the user says /ingest-health, asks to import, sync, ingest, or load Apple Health / Apple Watch / HealthKit data, has a fresh export.zip from the iPhone Health app, a Simple Health Export CSV folder, or a Health Auto Export TCP live feed, or when health-mcp queries return empty because no data was ever…