ingest

ingest is a skill for Claude Code, Codex from jackwener/llm-wiki. It costs 52 tokens per session (633 once invoked), scanned A, original, Apache-2.0.

A tool for turning documents, notes, chats, or web pages into connected pages in an LLM Wiki vault. The vault is a maintained collection of linked knowledge, while the source files preserve the original evidence.

In plain words
What is it for?
Use it to add or update durable wiki knowledge from source material, preserve original copies, connect related pages, and record what was ingested.
Why use it?
It helps prevent useful information from being lost in scattered source material and avoids creating duplicate or unsupported wiki pages. It also checks existing wiki content and local ingestion rules before editing.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to add or update durable wiki knowledge from source material…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jackwener/llm-wiki/ingest
Install

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.

Any agent
npx skills add jackwener/llm-wiki --skill ingest
Clone the repo
git clone --depth 1 https://github.com/jackwener/llm-wiki

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 ingest

README.md
[![agentmods](https://agentmods.dev/badge/skills/jackwener/llm-wiki/ingest.svg)](https://agentmods.dev/skills/jackwener/llm-wiki/ingest)
Your own site
<a href="https://agentmods.dev/skills/jackwener/llm-wiki/ingest"><img src="https://agentmods.dev/badge/skills/jackwener/llm-wiki/ingest.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 633 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 $0.00052 $0.00633
Opus 5 $0.00026 $0.00316
Sonnet 5 $0.00010 $0.00127
Haiku 4.5 $0.00005 $0.00063

Measured 7d ago against content hash add7f32f0c66, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

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 7d 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/ingest/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ingest an LLM Wiki source

Turn a source into concise, attributable, interconnected wiki pages. The wiki is the maintained knowledge layer; sources/ is the immutable evidence layer.

Before editing

  1. Locate the vault by finding .llm-wiki/config.toml.
  2. Read wiki-purpose.md, wiki-schema.md, and wiki-agent.md when present. The latter defines vault-specific MUST / MAY / NEVER ingest criteria.
  3. Skip material that the agent policy excludes, contains credentials or personal data, or duplicates existing knowledge.
  4. If the vault is empty, agree with the user on language, page layout, directory structure, and filename conventions before creating pages.
  5. If the material would change established scope, page boundaries, naming, or linking strategy, present the proposed structure before editing. Apply straightforward additions directly.

Workflow

  1. Check wiki/, wiki-log.md, and llm-wiki search for prior ingestion of the source or its topics. Re-ingest only changed or newly useful material.

  2. Copy raw input to sources/YYYY-MM-DD/, preserving its original name. Add a version suffix if needed. Once saved, never edit that copy. Split large chat logs or collections by date or topic before saving.

  3. Extract claims, entities, decisions, open questions, and relationships.

  4. Create or merge focused pages in wiki/. Every page needs the fields required by wiki-schema.md; normally this includes:

    ---
    title: Page Title
    description: One-line summary
    aliases: [alternate names]
    tags: [taxonomy tags]
    sources: [YYYY-MM-DD/source.md]
    created: YYYY-MM-DD
    updated: YYYY-MM-DD
    ---
    

    Bug or issue pages also need machine-readable status: open | resolved | wontfix.

  5. Merge rather than overwrite. When sources conflict, preserve both claims, identify their sources, and flag the conflict rather than silently choosing one.

  6. Add [[wikilinks]] for related entities, including useful not-yet-created pages, and finish each page with a ## Related section.

  7. Append a concise ## [YYYY-MM-DD] ingest | … entry to wiki-log.md with pages created or updated.

  8. Run llm-wiki sync after the changes.

Read the full file on GitHub · 64 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. 7d ago First seen · 64 lines · 52 tokens per session scan A add7f32f0c66

Subscribe to this mod's changes

ingest is a skill published in the GitHub repository jackwener/llm-wiki (100 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 52 tokens to every session and 633 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens