knowledge-base

knowledge-base is a skill for Claude Code, Codex from JansenAnalytics/claudex. It costs 43 tokens per session (469 once invoked), scanned A, original, MIT.

A local searchable store for information from web pages, files, and PDFs. You can add documents, search their contents later, list them, update them, or remove them.

In plain words
What is it for?
Use it to collect research sources, search technical documents, build a reference library, and retrieve information from saved PDFs or local files.
Why use it?
It keeps useful research material in one place so you do not have to repeatedly open files or revisit web pages. Searching stored documents makes it easier to find supporting context for a task.

Skill for Claude CodeCodex

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 skills/jansenanalytics/claudex/knowledge-base
Any agent
npx skills add JansenAnalytics/claudex --skill knowledge-base
Clone the repo
git clone --depth 1 https://github.com/JansenAnalytics/claudex

Made for: Claude Code, Codex.

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 knowledge-base

README.md
[![agentmods](https://agentmods.dev/badge/skills/jansenanalytics/claudex/knowledge-base.svg)](https://agentmods.dev/skills/jansenanalytics/claudex/knowledge-base)
Your own site
<a href="https://agentmods.dev/skills/jansenanalytics/claudex/knowledge-base"><img src="https://agentmods.dev/badge/skills/jansenanalytics/claudex/knowledge-base.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 469 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00043 $0.00469
Opus 5 $0.00022 $0.00234
Sonnet 5 $0.00009 $0.00094
Haiku 4.5 $0.00004 $0.00047

Measured today against content hash 25cd557473d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

knowledge-base 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 today.

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.

skills/knowledge-base/SKILL.md · 64 lines

What it actually says

Knowledge Base Skill

Use when: ingesting documents, searching stored knowledge, building research context.

Ingest a URL

node ${KNOWLEDGE_BASE_HOME:-$HOME/projects/knowledge-base}/ingest.cjs add <url>

Ingest a local file

node ${KNOWLEDGE_BASE_HOME:-$HOME/projects/knowledge-base}/ingest.cjs add --file <path>

Ingest a PDF

node ${KNOWLEDGE_BASE_HOME:-$HOME/projects/knowledge-base}/ingest.cjs add --pdf <path>
node ${KNOWLEDGE_BASE_HOME:-$HOME/projects/knowledge-base}/search.cjs "query"
node ${KNOWLEDGE_BASE_HOME:-$HOME/projects/knowledge-base}/search.cjs "query" --limit 10
node ${KNOWLEDGE_BASE_HOME:-$HOME/projects/knowledge-base}/search.cjs "query" --context

List all documents

node ${KNOWLEDGE_BASE_HOME:-$HOME/projects/knowledge-base}/ingest.cjs list

Remove a document

node ${KNOWLEDGE_BASE_HOME:-$HOME/projects/knowledge-base}/ingest.cjs remove <id>

Update (re-fetch) a document

node ${KNOWLEDGE_BASE_HOME:-$HOME/projects/knowledge-base}/ingest.cjs update <id>

Notes

  • DB lives at: ${KNOWLEDGE_BASE_HOME:-$HOME/projects/knowledge-base}/kb.sqlite
  • Uses SQLite FTS5 with BM25 ranking
  • Chunks are ~500 words each
  • URL deduplication: re-run with update <id> to refresh
  • Supports: URLs, local text/markdown files, PDFs (if pdftotext installed)
Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. today First seen · 64 lines · 43 tokens per session scan A 25cd557473d9

Subscribe to this mod's changes

knowledge-base is a skill published in the GitHub repository JansenAnalytics/claudex (5 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 469 once invoked, about $0.0002 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 2026-09-03.

Related

Other skills, from other repositories

mixedbread-parsing

Parse documents, extract structured content, and run OCR using the Mixedbread Parsing API. Use when parsing PDFs, Word documents, PowerPoint slides, or images, extracting tables or form fields, running OCR on scanned documents, converting documents to markdown or HTML, or extracting structured chunks with…

mixedbread-ai/skills · 69 tokens

pdf-figure-extract

Extract and return figures from already-downloaded local PDFs with PyMuPDF, optionally reusing PageIndex artifacts for page selection and verifying shortlisted candidates multimodally before delivery.

jimezsa/opencolab · 40 tokens

paper-summary

Deterministic PDF-to-markdown paper summarization for papercli workflows. Given one paper PDF or a directory of paper PDFs, produce schema-conformant markdown summaries and optionally update summarizedids.txt.

jimezsa/opencolab · 43 tokens

latex-paper-writer

Create, edit, Git-version, compile, and deliver scientific LaTeX papers, reports, and research-derived PDF summaries. Use for venue-aware templates such as ICLR, NeurIPS, ICML, CVPR, ACL, ACM, and IEEE; experiment-result tables; architecture figures or diagrams; deep-research/pro-research/fast-research to PDF…

jimezsa/opencolab · 90 tokens

mineru-extract

Use the official MinerU (mineru.net) parsing API to convert a URL (HTML pages like WeChat articles, or direct PDF/Office/image links) into clean Markdown + structured outputs. Use when webfetch/browser can’t access or extracts messy content, and you want higher-fidelity parsing (layout/table/formula/OCR).

blessonism/openclaw-skills · 72 tokens

docsagent

Search and manage private, local document collections (PDF, PPTX, DOCX) offline. Use when you need to find information within your private files, not for web research.

docsagent/docsagent · 39 tokens