agentmods.dev

corpus-ingest

corpus-ingest is a skill for Claude Code from moliver28/corpus-kb. It costs 66 tokens per session (380 once invoked), scanned A, original, MIT.

A document-loading tool for adding files, folders, transcripts, and web pages to a searchable collection called a corpus.

In plain words
What is it for?
Use it to add PDFs, office files, text, meeting notes, subtitles, or websites to a research collection.
Why use it?
It puts source material in one place so other tools can search it or answer questions from it instead of relying on memory.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the corpus-rag plugin — 3 skills, 2 commands, 2 hooks shipped together

not rated 1repo yesterday A scan 66 tokens original MIT

Good fit Use it to add PDFs, office files, text, meeting notes, subtitles, or websites to a research collection.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/moliver28/corpus-kb/corpus-ingest
View source ↗ moliver28/corpus-kb
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.

Any agent
npx skills add moliver28/corpus-kb --skill corpus-ingest
Clone the repo
git clone --depth 1 https://github.com/moliver28/corpus-kb

Made for: Claude Code.

Or install corpus-rag, the plugin that ships this one along with the rest of its 3 skills, 2 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 corpus-ingest

README.md
[![agentmods](https://agentmods.dev/badge/skills/moliver28/corpus-kb/corpus-ingest/github.svg)](https://agentmods.dev/skills/moliver28/corpus-kb/corpus-ingest)
Your own site
<a href="https://agentmods.dev/skills/moliver28/corpus-kb/corpus-ingest"><img src="https://agentmods.dev/badge/skills/moliver28/corpus-kb/corpus-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 corpus-ingest

Your own site · 80×15
<a href="https://agentmods.dev/skills/moliver28/corpus-kb/corpus-ingest"><img src="https://agentmods.dev/badge/skills/moliver28/corpus-kb/corpus-ingest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 380 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 $0.00066 $0.00380
Opus 5.5 $0.00026 $0.00152
Sonnet 5.5 $0.00013 $0.00076
Haiku 4.5 $0.00007 $0.00038

Measured yesterday against content hash b175fbcf3f8f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

corpus-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 yesterday.

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.

plugins/corpus-rag/skills/corpus-ingest/SKILL.md · 59 lines

What it actually says

Corpus Ingest

Load documents into the corpus so corpus-kb ask and corpus-kb search can find them.

Steps

  1. One file:

    corpus-kb ingest "<path to file>"

  2. A folder of files:

    corpus-kb ingest "<path to folder>"

  3. A web page:

    corpus-kb ingest-url "<url>"

    Add --crawl to follow same-site links.

  4. Check the result:

    corpus-kb ingest-status

File notes

  • PDF, DOCX, PPTX, HTML, and text files work out of the box.
  • Transcripts: .vtt and .srt files ingest as text. Keep their names clear (date and speaker help).
  • Google Slides: export the deck to .pptx first, then ingest the file.
  • Large folders: start with one folder, then check ingest-status before adding more.

Register the study

The session hint stops once a study is registered. After your first successful ingest, create the marker:

mkdir -p ~/.corpus-kb/plugin
touch ~/.corpus-kb/plugin/study-registered

On Windows use %USERPROFILE%\.corpus-kb\plugin in place of ~/.corpus-kb/plugin.

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. yesterday First seen · 59 lines · 66 tokens per session scan A b175fbcf3f8f

Subscribe to this mod's changes

corpus-ingest is a skill published in the GitHub repository moliver28/corpus-kb (1 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 380 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-11-07.

DocumentsPDFResearch
Related

corpus-ingest compared with skills from other repositories

corpus-ingest next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
corpus-ingestmoliver28/corpus-kbSkill1yesterdayMITA66Claude Code
apify-youtube-transcript-scrapersickn33/agentic-awesome-skillsSkill49k2d agoMITA48Claude Code
foundry-hosted-agent-validationmicrosoft/agent-frameworkSkill15ktodayMITA82Claude Code, Codex
report-to-pdfasgeirtj/system_prompts_leaksSkill71ktodayCC0-1.0A17Claude Code, Codex
pdf-extract-create-workflowHKUDS/OpenSpaceSkill7.9k2d agoMITA22Claude Code, Codex
document-direct-pythonHKUDS/OpenSpaceSkill7.9k2d agoMITA20Claude Code, Codex
pdf-verification-cliHKUDS/OpenSpaceSkill7.9k2d agoMITA19Claude Code, Codex