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.
npx agentmods add instructions/dryrainent/greeum/claude-mdgit clone --depth 1 https://github.com/DryRainEnt/GreeumWrote 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.
[](https://agentmods.dev/instructions/dryrainent/greeum/claude-md)<a href="https://agentmods.dev/instructions/dryrainent/greeum/claude-md"><img src="https://agentmods.dev/badge/instructions/dryrainent/greeum/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 5.1 | $0.03673 | $0.03673 |
| Opus 5 | $0.01836 | $0.01836 |
| Sonnet 5 | $0.00735 | $0.00735 |
| Haiku 4.5 | $0.00367 | $0.00367 |
Grade A, and why
Greeum 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 408 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
⚠️ CRITICAL REQUIREMENTS (v5.4 트랙)
Semantic Embedding Requirement
MANDATORY: The system requires proper semantic embeddings for core functionality. v5.4부터 hash-fallback은 시끄러운 경고와 함께만 동작하며, 두 가지 의미 임베딩 경로를 자동 선택한다:
| 경로 | extra | 특징 | 권장 사용 |
|---|---|---|---|
sentence-transformers |
greeum[full] |
torch 기반, 최고 recall@5/10 | GPU 있거나 deep recall 필요 |
model2vec (정적, no-torch) |
greeum[lite] |
numpy만, CPU 즉시, 27× 빠름 | 드롭인 기본·라이트 환경 |
| hash fallback | (없음) | 사실상 랜덤 — 절대 production 금지 | 테스트 한정 |
자동 선택 우선순위 (EmbeddingRegistry._auto_init):
SentenceTransformer → Model2Vec → 시끄러운 hash 폴백.
Install:
pip install greeum[full] # ST + faiss + 풀 의존성 (recall 우선)
pip install greeum[lite] # model2vec만 (드롭인 가벼움)
환경변수 (v5.4):
GREEUM_HYBRID_VEC_WEIGHT/GREEUM_HYBRID_BM25_WEIGHT— 하이브리드 가중치 (기본 0.9/0.1, 2026-06-14 sweep 결과로 0.7/0.3에서 상향). 라이브 DB·MIRACL-Korean 양쪽 데이터에서 0.9/0.1이 0.7/0.3을 strictly dominate. 짧은 텍스트/태그 위주 코퍼스만 BM25 비중을 높이는 게 의미 있음. 가이드는docs/eval/tuning_guide.md.GREEUM_DISABLE_ST/GREEUM_DISABLE_M2V— 특정 경로 비활성화.GREEUM_SILENT_HASH_FALLBACK=1— 테스트/CI에서만 hash 배너 억제.GREEUM_INSIGHT_REQUIRE_LLM=1— InsightJudge LLM 실패 시 엄격 모드(500 반환). 기본은 fail-soft.GREEUM_DB_THREAD_LOCAL=1— DatabaseManager per-thread 연결 (FastAPI/MCP-HTTP 권장).
Version History:
- v3.1.0: FAILED — hash embeddings 발견
- v3.1.1a1: ST 도입
- v5.0: Hybrid Graph Search + 3단계 파이프라인
- v5.3.0: Consolidator + Association 검색
- v5.4 (작업 중): Model2Vec 통합, 하이브리드 가중치 재튜닝, fail-soft, thread-local 옵션
Project Overview
Greeum (pronounced "그리음") is a universal memory module for Large Language Models (LLMs) that provides human-like memory capabilities. It's designed to be LLM-agnostic and supports multiple languages, particularly Korean and English.
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.
- 6d ago First seen · 408 lines · 3,673 tokens per session scan A 9f3d699411a5
Greeum CLAUDE.md is an instructions file published in the GitHub repository DryRainEnt/Greeum (24 stars, last pushed 1mo ago), licensed MIT. It adds 3,673 tokens to every session, about $0.0184 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.
Other instructions, from other repositories
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).
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.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.