What is llm-knowledge-base CLAUDE.md?

Repository instructions for maintaining a Swedish-language knowledge base with raw material, research, wiki articles, and a change log.

Organizing incoming material, updating related knowledge articles, maintaining the wiki index, and recording changes chronologically.

They define where different kinds of information belong and how articles, links, indexes, and history should be maintained.

llm-knowledge-base CLAUDE.md — Instructions file by Pluggentipsar

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 instructions/pluggentipsar/llm-knowledge-base/claude-md

Clone the repo

git clone --depth 1 https://github.com/Pluggentipsar/llm-knowledge-base

Per session 657 This file is loaded in full into every session.

When invoked 657 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5	$0.00657	$0.00657
Opus 5	$0.00329	$0.00329
Sonnet 5	$0.00131	$0.00131
Haiku 4.5	$0.00066	$0.00066

Measured 2d ago against content hash 3340cacbf4d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

llm-knowledge-base CLAUDE.md 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 2d 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.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kunskapsbas: [DITT PROJEKT]

Om projektet

Beskriv ditt projekt har. Vad handlar det om? Vad ar syftet?

Amnesomraden

Amne 1 - Kort beskrivning
Amne 2 - Kort beskrivning
Amne 3 - Kort beskrivning

Mappstruktur

raw/           # Obearbetat kallmaterial (ror ej dessa filer)
  inbox/       # Snabbfangat material (YouTube, LinkedIn, tankar)
  artiklar/    # Nedladdade artiklar
  forskning/   # Vetenskapliga papers
  rapporter/   # Rapporter
  inspiration/ # Ideer, videos, poddar

wiki/          # AI-kompilerad kunskapsbas (AI underhaller)
  INDEX.md     # Huvudindex
  log.md       # Kronologisk logg
  begrepp/     # Begreppsartiklar
  forskning/   # Forskningssammanfattningar
  personer/    # Relevanta personer

outputs/       # Genererade analyser och material

Wiki-regler

Varje amne far en egen .md-fil
Varje wiki-fil borjar med en sammanfattning (1-2 stycken)
Relaterade amnen lankas med [[amnesnamn]]
INDEX.md listar alla artiklar med en enrads-beskrivning
Nar nytt raw-material laggs till, uppdateras relevant wiki-artikel
log.md ar en append-only kronologisk logg - alla andringar loggas
Varje loggrad: [DATUM] [TYP] Beskrivning
Typer: INGEST, COMPILE, RESEARCH, UPDATE, LINK, LINT, NOTE, QUESTION
Kor LINT (halsokontroll) regelbundet for att hitta inkonsekvenser och luckor

Vetenskapliga databaser (oppna API:er)

OpenAlex:          https://api.openalex.org/works?search={query}
arXiv:             https://export.arxiv.org/api/query?search_query={query}
Semantic Scholar:  https://api.semanticscholar.org/graph/v1/paper/search?query={query}
CrossRef:          https://api.crossref.org/works?query={query}
DIVA Portal:       https://diva-portal.org/smash/export.jsf?format=csv&searchType=RESEARCH&query={query}

Soktermer

"term 1", "term 2", "term 3"

Read the full file on GitHub · 65 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.

2d ago First seen · 65 lines · 657 tokens per session scan A 3340cacbf4d8

Subscribe to this mod's changes

llm-knowledge-base CLAUDE.md is an instructions file published in the GitHub repository Pluggentipsar/llm-knowledge-base (11 stars, last pushed 4mo ago), licensed MIT. It adds 657 tokens to every session, about $0.0033 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 2026-08-30.

Data and AI Memory and context Research

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

llm-knowledge-base CLAUDE.md