memex-plugin CLAUDE.md

Instructions for Memex, a personal knowledge base that stores notes and conversation transcripts in an Obsidian vault. They describe searching, indexing, and organizing project knowledge.

In plain words
What is it for?
Use them to check vault status, search notes—including recent notes—rebuild the search index, maintain project summaries, and manage linked notes.
Why use it?
They help an agent find relevant past work and keep the knowledge base connected and organized instead of relying only on the current conversation.

Instructions file

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/linxule/memex-plugin/claude-md
Clone the repo
git clone --depth 1 https://github.com/linxule/memex-plugin
Per session 2,575 This file is loaded in full into every session.
When invoked 2,575 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.

ModelPer sessionOnce invoked
Fable 5 $0.02575 $0.02575
Opus 5 $0.01288 $0.01288
Sonnet 5 $0.00515 $0.00515
Haiku 4.5 $0.00258 $0.00258

Measured 2d ago against content hash a72005a08ee0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memex-plugin 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 · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memex - Personal Knowledge Base

Centralized knowledge base storing memos and transcripts from all Claude Code sessions.

Quick Start

The memex CLI works from any directory. For Obsidian CLI and dreamer, cd to vault is still needed.

# Check vault status
memex status

# Search for something (RRF scoring is default)
memex search "authentication"

# Search recent docs only (7d, 2w, 3m)
memex search "plugin" --since=7d

# Rebuild index after changes
memex index rebuild --incremental

Semantic search requires Gemini API: export GEMINI_API_KEY="your-key". Falls back to FTS-only without it.

Your Role

You are the memex curator. Condense project knowledge into _project.md overviews, maintain [[wikilinks]], and cultivate the vault's knowledge topology. Search the vault when you need context — don't rely on pre-loaded summaries.

Folder Structure

memex/
├── projects/<name>/memos/       # Session memos per project
├── projects/<name>/auto-memory/ # Synced Claude Code auto-memory files
├── projects/<name>/transcripts/ # Full conversation logs
├── topics/                      # Cross-project concept notes + trails (type: trail)
├── src/memex/scripts/           # Core scripts (search, embeddings, etc.)
├── scripts/                     # Backward-compat shims → src/memex/scripts/
├── hooks/                       # Claude Code hooks (SessionStart, PreCompact, etc.)
├── commands/                    # Slash commands (/memex:*)
├── skills/                      # Intent-based skills
├── _meta/                       # Curator infrastructure (dashboard, log, tag taxonomy)
├── _views/                      # Obsidian Base views (.base)
├── _templates/                  # Note templates
└── .claude-plugin/              # Plugin manifest

The FTS5 + vector search + observation_topics index is not in the vault: it lives at ~/.memex/_index.sqlite by default (memex path --index resolves it; index_path in ~/.memex/config.json or MEMEX_INDEX_PATH overrides it). An index left at <vault>/_index.sqlite by a pre-0.17.0 install is still used from there.

Read the full file on GitHub · 152 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.

  1. 2d ago First seen · 152 lines · 2,575 tokens per session scan A a72005a08ee0

Subscribe to this mod's changes

memex-plugin CLAUDE.md is an instructions file published in the GitHub repository linxule/memex-plugin (7 stars, last pushed 5d ago), licensed MIT. It adds 2,575 tokens to every session, about $0.0129 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.