ingest

ingest is a skill for Claude Code, Codex from superhero-tech/super-brain. It costs 52 tokens per session (1,276 once invoked), scanned A, original, MIT.

A workflow for turning a source from an inbox folder into linked wiki pages, then archiving the source. A source can be an article, discussion thread, tutorial, transcript, or note.

In plain words
What is it for?
Use it to process one source or the whole inbox, update existing knowledge pages, and create pages for important new concepts or entities.
Why use it?
It prevents useful ideas from staying as isolated clippings or being reduced to one summary page when they belong in several parts of the wiki.

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/superhero-tech/super-brain/ingest
Any agent
npx skills add superhero-tech/super-brain --skill ingest
Clone the repo
git clone --depth 1 https://github.com/superhero-tech/super-brain

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/superhero-tech/super-brain/ingest.svg)](https://agentmods.dev/skills/superhero-tech/super-brain/ingest)
Your own site
<a href="https://agentmods.dev/skills/superhero-tech/super-brain/ingest"><img src="https://agentmods.dev/badge/skills/superhero-tech/super-brain/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 1,276 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 $0.00052 $0.01276
Opus 5 $0.00026 $0.00638
Sonnet 5 $0.00010 $0.00255
Haiku 4.5 $0.00005 $0.00128

Measured 4d ago against content hash 0a12bf92431a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 4d 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.

.agents/skills/ingest/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ingest

Turn a source into wiki. Not one summary page per file - one page per concept, plus every existing page this source has something to say about.

Write wiki pages in the language the human writes in. One language per page.

How to invoke

  • "Process this", "run an ingest", "I dropped something in Inbox"
  • "Process the whole inbox" for batch mode
  • /ingest

Sources live in 2-Inbox/. If the human clips with Obsidian Web Clipper on its default settings, check Clippings/ too.

How it works

1. Read the source

End to end, before forming a view of it. Note what it is - article, thread, tutorial, transcript, note - and who wrote it.

2. Map it against the wiki

Read 4-Knowledge/index.md. Then list everything the source touches and mark each item twice.

By kind:

  • concept - an idea, framework, method or pattern
  • entity - a person, company, tool or product

By state:

  • primary - the source's main concept, gets the new or heavily updated page
  • existing - has a page already, needs an update from this source
  • new - worth its own page, does not have one yet

An entity earns a page when it appears in two or more sources, or is central to this one. A name mentioned once in passing gets a citation, not a page.

Also check 5-Raw/ - if this source has been processed before, you are updating pages, not creating them.

This list is the actual work. Everything after it is execution.

3. Check in before writing

Show the human what you found, in three or four lines: what the source argues, which pages you are about to touch, and anything in it that contradicts what the wiki already says. Then wait.

A wrong page written now is a wrong answer in every query for the next month, and nobody will notice until it has been built on. This is the cheapest place to catch it. Batch mode is the only exemption.

4. Write the pages

Load references/page-templates.md now - it has the frontmatter and the shape for both concept and entity pages.

Read the full file on GitHub · 112 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 112 lines · 52 tokens per session scan A 0a12bf92431a

Subscribe to this mod's changes

ingest is a skill published in the GitHub repository superhero-tech/super-brain (114 stars, last pushed 9d ago), licensed MIT. It adds 52 tokens to every session and 1,276 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