pdf-ingest

pdf-ingest is a command for Claude Code from ngtiendong/Academic-Research-Agent-Skill. It costs 0 tokens per session (195 once invoked), scanned A, original, MIT.

A source-ingestion command for downloading, inspecting, converting, and summarizing research papers before using them as evidence.

In plain words
What is it for?
Use it to build source inventories and extract claims, methods, datasets, metrics, figures, tables, limitations, and usable evidence from PDFs.
Why use it?
It reduces the risk of citing work that was never properly checked or drawing conclusions from only a title or abstract.

Command for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to build source inventories and extract claims, methods, datasets, metrics, figures, tables, limitations, and usable evidence from PDFs.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/ngtiendong/academic-research-agent-skill/pdf-ingest
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.

Clone the repo
git clone --depth 1 https://github.com/ngtiendong/Academic-Research-Agent-Skill

Made for: Claude Code.

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 pdf-ingest

README.md
[![agentmods](https://agentmods.dev/badge/commands/ngtiendong/academic-research-agent-skill/pdf-ingest/github.svg)](https://agentmods.dev/commands/ngtiendong/academic-research-agent-skill/pdf-ingest)
Your own site
<a href="https://agentmods.dev/commands/ngtiendong/academic-research-agent-skill/pdf-ingest"><img src="https://agentmods.dev/badge/commands/ngtiendong/academic-research-agent-skill/pdf-ingest/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for pdf-ingest

Your own site · 80×15
<a href="https://agentmods.dev/commands/ngtiendong/academic-research-agent-skill/pdf-ingest"><img src="https://agentmods.dev/badge/commands/ngtiendong/academic-research-agent-skill/pdf-ingest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 195 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.00195
Opus 5 $0.00000 $0.00097
Sonnet 5 $0.00000 $0.00039
Haiku 4.5 $0.00000 $0.00019

Measured 11d ago against content hash 2dc20b488a24, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

pdf-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 11d 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/commands/pdf-ingest.md · 39 lines

What it actually says

/pdf-ingest

Act as the Strategist for source ingestion.

Language

Follow config/language.yaml when present.

Task

Convert, inspect, and summarize source papers before they are used as evidence.

Use available local tools when possible:

  • paper/PDF downloader,
  • PDF-to-Markdown converter,
  • figure and table extractor,
  • source analysis matrix generator.

Rules

  • Do not cite a source you have not inspected.
  • Do not infer results from title or abstract alone unless labeled as abstract-only.
  • Extract claims, methods, datasets, metrics, limitations, and figures.
  • Inspect figure/table captions and surrounding context.
  • Mark inaccessible or failed sources clearly.

Output

  • Source Inventory
  • Extraction Status
  • Key Claims
  • Methods and Assumptions
  • Datasets and Metrics
  • Figures and Tables
  • Limitations
  • Usable Evidence
  • Open Questions
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. 11d ago First seen · 39 lines · 0 tokens per session scan A 2dc20b488a24

Subscribe to this mod's changes

pdf-ingest is a command published in the GitHub repository ngtiendong/Academic-Research-Agent-Skill (47 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 195 tokens. 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.