ingest-source

A workflow that takes one book, paper, article, or transcript and adds its useful information to a searchable knowledge base. It prepares notes, compares them with existing material, creates links, refreshes search, and records changes.

In plain words
What is it for?
Use it to process sources one at a time, extract and classify insights, find related notes, add high-confidence links, and maintain a change log.
Why use it?
It turns a source into connected knowledge while checking for related information already in the collection instead of treating every source in isolation.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/abilityai/cornelius/ingest-source
Any agent
npx skills add Abilityai/cornelius --skill ingest-source
Clone the repo
git clone --depth 1 https://github.com/Abilityai/cornelius

Made for: Claude Code, Codex.

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,116 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00058 $0.04116
Opus 5 $0.00029 $0.02058
Sonnet 5 $0.00012 $0.00823
Haiku 4.5 $0.00006 $0.00412

Measured 3d ago against content hash 895dc749bb2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ingest-source 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 3d 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.

.claude/skills/ingest-source/SKILL.md · 289 lines

How it starts

The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ingest Source

Fully autonomous pipeline that takes one source from raw file to integrated, connected knowledge. Each invocation handles a single source; drive a whole corpus by invoking once per source (e.g. via /loop or a shell loop over a file list), then run the corpus-level finalize steps once at the end.

ultrathink

Purpose

The unit of work for building a knowledge base from a book corpus. One source in → deduplicated, epistemically-classified notes out, embedded in the graph and linked to existing knowledge, with every auto-action logged for post-hoc review.

The design principle (established in the architecture discussion): insights are extracted against the current KB, not in a vacuum — retrieval-augmented extraction. The index is the KB's queryable state, so it must be refreshed before connection discovery, and refreshed again on the next source so each source builds on the last.

Configuration (safety rails that replace human gates)

Knob Default Purpose
AUTO_LINK_THRESHOLD 0.75 Only auto-write links at or above this cosine similarity. Below → logged as review candidates, not written.
LINKS_PER_NOTE 5 Max auto-links written per new note (top-k). Caps combinatorial blowup.
MUTATE_EXISTING_NOTES false If false, only the NEW notes get edited (links written FROM new → existing). Existing/hub notes are never mutated by auto-linking.
REJECT_ON_TIER rejected If the extractor tiers the source rejected (content-farm / regurgitated), abort and notify.

These are the autonomous substitute for the two approval gates a gated version would have. See Architecture Note for why.

State Dependencies

Source Location Read Write Description
Source file arg path / URL Book, paper, article, transcript, or YouTube URL
Working markdown resources/ingest-workspace/<slug>/ Extracted/prepared markdown + checkpoint
Book scope (books) Brain/Books/<book-slug>/ Per-book scope: notes + _book.md hub land here
Document Insights (non-books) Brain/Document Insights/<session>/ Papers / articles / web extracted notes land here
FAISS index + BDG resources/local-brain-search/, resources/brain-graph/ Refreshed mid-pipeline
Changelogs Brain/05-Meta/Changelogs/ Per-source ingestion report
Ingest ledger resources/ingest-workspace/INGEST-LEDGER.md Corpus progress: which sources done
Checkpoint resources/ingest-workspace/<slug>/.checkpoint Resume marker for the 45-min rule

Read the full file on GitHub · 289 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. 3d ago First seen · 289 lines · 58 tokens per session scan A 895dc749bb2e

Subscribe to this mod's changes

ingest-source is a skill published in the GitHub repository Abilityai/cornelius (104 stars, last pushed 10d ago), licensed MIT. It adds 58 tokens to every session and 4,116 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens