ingest

ingest is a command for coding agents from elbalen/skopus. It costs 14 tokens per session (403 once invoked), scanned A, original, MIT.

A command for adding a file or web page to a Markdown knowledge base. It saves a source summary and extracts related topics into linked pages for concepts, entities, decisions, or comparisons.

In plain words
What is it for?
Use it to ingest local files or URLs, create source records, distill important topics, add internal links, update the wiki index, and record the activity in the log.
Why use it?
It reduces the work of reading a source, summarizing it, and connecting its useful ideas to existing notes. Existing pages can be updated instead of creating duplicates.

Command

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 commands/elbalen/skopus/ingest
Clone the repo
git clone --depth 1 https://github.com/elbalen/skopus

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/commands/elbalen/skopus/ingest.svg)](https://agentmods.dev/commands/elbalen/skopus/ingest)
Your own site
<a href="https://agentmods.dev/commands/elbalen/skopus/ingest"><img src="https://agentmods.dev/badge/commands/elbalen/skopus/ingest.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 403 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 $0.00014 $0.00403
Opus 5 $0.00007 $0.00201
Sonnet 5 $0.00003 $0.00081
Haiku 4.5 $0.00001 $0.00040

Measured 4d ago against content hash 8bdd16ab8883, 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.

skopus/templates/commands/ingest.md · 40 lines

What it actually says

/ingest

Ingest a source into the vault. Creates a source summary page and distills knowledge into concept/entity/decision pages with [[wikilinks]] cross-references.

$ARGUMENTS is a file path (relative to the vault's raw/ or absolute) OR a URL.

Steps

  1. Resolve the source.

    • If $ARGUMENTS is a URL → fetch with WebFetch, save cleaned markdown to raw/articles/<slug>.md.
    • If $ARGUMENTS is a path → verify the file exists under raw/ (copy it there if outside). Never modify the original raw file.
  2. Read the source completely.

  3. Identify what to distill: entities (products, tools, services, people), concepts (techniques, patterns, frameworks), decisions (architectural choices with rationale), comparisons (side-by-side analyses).

  4. Create wiki/sources/<slug>.md using the wiki page template. Include type: source, source path, Key Points, Details (~200-500 words), Related section.

  5. For each identified topic: check if a wiki page exists. Update existing pages with new knowledge (preferred) or create new ones. Cross-link everything with [[wikilinks]].

  6. Update wiki/index.md with new pages.

  7. Append to log.md with the ingest operation.

  8. Git commit: ingest: <source title>.

  9. Print a summary of pages created/updated.

Rules

  • Never modify files in raw/.
  • Prefer updating existing pages over creating new ones.
  • Over-link, don't under-link.
  • Cite — every wiki page lists the raw source in frontmatter.
  • Keep summaries concise.
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 · 40 lines · 14 tokens per session scan A 8bdd16ab8883

Subscribe to this mod's changes

ingest is a command published in the GitHub repository elbalen/skopus (4 stars, last pushed 4mo ago), licensed MIT. It adds 14 tokens to every session and 403 once invoked, about $0.0001 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.