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.
npx agentmods add commands/gf-labs/ramp/ingestgit clone --depth 1 https://github.com/gf-labs/rampWrote 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.
[](https://agentmods.dev/commands/gf-labs/ramp/ingest)<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>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.
| Model | Per session | Once 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 |
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.
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-namealready 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://orhttps://) → 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
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.
- 4d ago First seen · 355 lines · 19 tokens per session scan A 2f9e2adcab6d
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.
Other commands, from other repositories
design-tutorial
Interactive guided tour of Naksha — learn commands through real exercises, discover workflows, and get oriented in under 10 minutes.
coding-drill
Rapid-fire reps — pattern recognition, complexity-of-this-snippet, template recall — flashcard cadence; prioritizes your weak patterns.
coding-import
Import a LeetCode problem into your local library via WebFetch — no MCP, no login. Becomes a normal markdown problem you can practice or mock.
practice-coding
Untimed guided coding practice: you write code in a seeded solution file in your own editor; a warm interviewer hints via a ladder, runs your code, and teaches inline. Summarized, not scored.
alt
Import an Exam Radar (OPTIMETA Alt plugin) export and fold its lecture-emphasis exam signal into the course index — radar.md, a lecture-emphasis column on coverage.md, and a gold-zone weakmap.
blind
Strategy-level blind drill on a known HW or example problem. User describes approach in prose (no math typing); Claude verifies against solution then saves clean reference to derivations/.