agentmods.dev

wiki-ingest

wiki-ingest is a skill for Claude Code, Codex from tboome33/obsidian-mcp-router. It costs 121 tokens per session (9,858 once invoked), scanned A, original, Apache-2.0.

A tool that reads a file, web page, or pasted text and turns its important ideas and named things into linked wiki pages. It also updates the wiki's catalogue, activity log, and recent-information list.

In plain words
What is it for?
Use it to add articles, URLs, local files, or pasted text to an existing wiki without creating duplicate entries when the same source is processed again.
Why use it?
Adding research to a wiki by hand is slow and can leave pages disconnected from the rest of the knowledge base. This provides a repeatable way to file and cross-reference new material.

Skill for Claude CodeCodex

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

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/me/Obsidian/my-vault.

Part of the obsidian-router plugin — 49 skills, 54 commands, 2 agents, 3 hooks, 1 MCP server shipped together

not rated 1repo today A scan 121 tokens original Apache-2.0

Good fit Use it to add articles, URLs, local files, or pasted text to an existing wiki without creating duplicate entries when the same source is processed again.

Compare 6 skills from other repositories ↓
View source ↗ tboome33/obsidian-mcp-router
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add tboome33/obsidian-mcp-router
Claude Code
/plugin install obsidian-router

Made for: Claude Code, Codex.

Or install obsidian-router, the plugin that ships this one along with the rest of its 49 skills, 54 commands, 2 agents, 3 hooks, 1 MCP server.

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-ingest

README.md
[![agentmods](https://agentmods.dev/badge/skills/tboome33/obsidian-mcp-router/wiki-ingest/github.svg)](https://agentmods.dev/skills/tboome33/obsidian-mcp-router/wiki-ingest)
Your own site
<a href="https://agentmods.dev/skills/tboome33/obsidian-mcp-router/wiki-ingest"><img src="https://agentmods.dev/badge/skills/tboome33/obsidian-mcp-router/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.

agentmods 80×15 button for wiki-ingest

Your own site · 80×15
<a href="https://agentmods.dev/skills/tboome33/obsidian-mcp-router/wiki-ingest"><img src="https://agentmods.dev/badge/skills/tboome33/obsidian-mcp-router/wiki-ingest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,858 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 $0.00121 $0.09858
Opus 5 $0.00060 $0.04929
Sonnet 5 $0.00024 $0.01972
Haiku 4.5 $0.00012 $0.00986

Measured 8d ago against content hash af5091a656af, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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 8d 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.

skills/wiki-ingest/SKILL.md · 466 lines

How it starts

The opening of the file, as written. The whole thing — 466 lines — stays where its author put it; the contents beside it link to each section on GitHub.

wiki-ingest

Take a source (URL, local file path, or pasted text) and do the structured work of: pulling it in, identifying what's worth keeping, writing wiki pages for the new entities/concepts, and updating the relevant cross-references — all idempotently so re-ingesting the same source doesn't duplicate.

Pre-conditions

  1. The target vault has a wiki/ folder with catalog.md, journal.md, hot.md. If not, run the wiki skill first.
  2. The vault is online (call list_vaults).
  3. You have one of: a URL, a file path on disk, or text the user pasted.

When to use

  • "ingest this URL" / "absorb this article"
  • The user pastes a long block of text and says "file this"
  • Batch mode: "ingest all of these" with multiple sources → fan out via the wiki-ingest sub-agent (in agents/wiki-ingest.md).

When NOT to use

  • The user wants a quick answer without filing → just answer, don't ingest.
  • The source is already filed (check wiki-meta/catalog.md for the title or URL) → tell them; offer to refresh instead.
  • The "source" is the current conversation → use the save skill instead.

Steps

1. Acquire the source content

  • URL: use the defuddle skill (v0.13.2+) — it returns {markdown, metadata} with deterministic title/author/published/image/site/lang/description/wordCount/readingMinutes from Schema.org/OG/meta tags. If you bypass defuddle for some reason (e.g. URL is already clean markdown), call mcp__obsidian-router__extract_page_metadata({url}) directly to get the metadata block — it's the input to step 4's deterministic frontmatter.
  • Local file: prefer mcp__obsidian-router__get_file if the file is inside a vault; else Read. No metadata block in this case — fall back to inference.
  • Pasted text: use what the user gave you. No metadata block — fall back to inference.

If acquisition fails, surface the error and stop. Don't ingest a partial source.

1.5 Hash-based freshness check (v0.15.0+, roadmap item #4)

Before processing the acquired content further, check whether this source has been ingested before with the exact same content. This is a fast no-op detector that saves a fetch+parse+LLM round-trip when the user re-runs wiki-ingest <url> on a source that hasn't evolved.

Read the full file on GitHub · 466 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. 8d ago First seen · 466 lines · 121 tokens per session scan A af5091a656af

Subscribe to this mod's changes

wiki-ingest is a skill published in the GitHub repository tboome33/obsidian-mcp-router (1 stars, last pushed today), licensed Apache-2.0. It adds 121 tokens to every session and 9,858 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 2026-09-03.

Claude CodeMemory and contextResearchanthropicclaude-desktopkarpathyknowledge-managementllm-wiki
Related

Other skills, from other repositories

librarian

Orchestrate vault knowledge workflows using the Librarian MCP server. Ingest solutions, search prior art, explore the knowledge graph, log daily learnings.

ngmeyer/librarian-mcp · 35 tokens

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).

zosmaai/pi-llm-wiki · 52 tokens

llm-wiki

Build and maintain an LLM-curated personal knowledge base — the "LLM Wiki" pattern from Andrej Karpathy's April 2026 gist. Use this skill whenever the user wants to ingest a source (paper, article, transcript, PDF, notes) into a persistent compounding knowledge base, ask a question against accumulated notes, lint or…

praneybehl/llm-wiki-plugin · 221 tokens

mindbase

Maintain a persistent AI-tended research wiki. Activates when the user wants to ingest a source (PDF, URL, article, paste), capture a thought, build the wiki context, query what's already known, lint for orphans/contradictions, or maintain page conventions. Phrases include "add this to my wiki", "today I decided…"…

frankchu91/mindbase-llm-wiki · 105 tokens

bastra-recall

Persistent external brain for ChatGPT, Codex, Claude, and other MCP clients — documents (PDFs, contracts, scans with OCR), personal facts (appointments, decisions, items, amounts), AND code lessons / preferences / project topology. USE PROACTIVELY in three modes. (1) RECALL — whenever the user asks about anything from…

n0mad-ai/bastra-recall · 0 tokens

bastra-recall

Proactive private local memory for ChatGPT and Codex — recall before acting, save durable rules, lessons and decisions without being asked. Requires the local bastra-recall MCP server installed by bastra install codex.

n0mad-ai/bastra-recall · 50 tokens