ingest

ingest is a command for coding agents from gf-labs/ramp. It costs 19 tokens per session (2,867 once invoked), scanned A, original, MIT.

A command that creates a knowledge-graph schema from an external source such as a course, API documentation, or technical specification. A knowledge graph organises topics and their relationships so they can be explored systematically.

In plain words
What is it for?
Ingesting a new topic, extracting its structure into the project’s schema format, and adding source-based learning or reference material to the knowledge graph.
Why use it?
It turns source material into a consistent topic structure instead of requiring the schema to be designed manually. It also checks the arguments and existing schemas before proceeding.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the ramp plugin — 11 commands, 2 hooks shipped together

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/gf-labs/ramp/ingest
Clone the repo
git clone --depth 1 https://github.com/gf-labs/ramp

Or install ramp, the plugin that ships this one along with the rest of its 11 commands, 2 hooks.

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/gf-labs/ramp/ingest.svg)](https://agentmods.dev/commands/gf-labs/ramp/ingest)
Your own site
<a href="https://agentmods.dev/commands/gf-labs/ramp/ingest"><img src="https://agentmods.dev/badge/commands/gf-labs/ramp/ingest.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,867 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 $0.00019 $0.02867
Opus 5 $0.00010 $0.01434
Sonnet 5 $0.00004 $0.00573
Haiku 4.5 $0.00002 $0.00287

Measured 4d ago against content hash 2f9e2adcab6d, 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.

commands/ingest.md · 355 lines

How it starts

The opening of the file, as written. The whole thing — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auto-collected context

Arguments: $ARGUMENTS

Today's date: !date +%Y-%m-%d

Existing topic schemas: !ls ~/.claude/ramp/schemas/ 2>/dev/null || ls "${CLAUDE_PLUGIN_ROOT}/topics/"*.md 2>/dev/null | xargs -I{} basename {} .md | sort || echo "none found"

Current plugin version: !python3 -c "import json,os; root=os.environ.get('CLAUDE_PLUGIN_ROOT',''); d=json.load(open(os.path.join(root,'.claude-plugin','plugin.json'))); print(d['version'])" 2>/dev/null || echo "unknown"


Your role

You are the /ramp:ingest command. Your job is to generate a complete, high-quality knowledge-graph schema for a new topic by reading external source material and applying ramp's v3 schema format.

Work through the 7 phases below sequentially. Do not write any files until Phase 3 approval. After Phase 3, proceed autonomously through Phases 4–7.


Phase 0 — Parse arguments and detect source type

Parse $ARGUMENTS: first word = topic-name, remainder = source.

Argument checks:

  • If no topic-name: ask "What topic name should I use? (e.g., aws-solutions-architect)" and wait.
  • If no source: ask "What source material should I read? Provide a file path or URL." and wait.
  • If topic-name already appears in Existing topic schemas above: warn — "Topic [name] already exists. Extend it, or abort?" Wait for user reply. If extend: proceed with a gap-fill focus in Phase 2. If abort: stop.

Source type detection:

  • Path ending .pdf → use Read tool (paginated; up to 20 pages per call — read in chunks)
  • URL (http:// or https://) → use WebFetch
  • Path ending .md, .txt, or any local file → use Read tool

Proceed to Phase 1 once arguments are validated.


Phase 1 — Read and internalize source material

Read the full source using the appropriate tool. For long PDFs, read pages 1–20, then continue in 20-page chunks until you have covered the full document.

Extract and display:

  • Title of the source
  • High-level structure: sections, domains, chapters — with page numbers if available
  • Key concepts per section: what topics and skills each section covers
  • Any explicit learning objectives, task statements, or assessment criteria

Read the full file on GitHub · 355 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. 4d ago First seen · 355 lines · 19 tokens per session scan A 2f9e2adcab6d

Subscribe to this mod's changes

ingest is a command published in the GitHub repository gf-labs/ramp (2 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 2,867 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.