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/agents-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/agents-md)<a href="https://agentmods.dev/instructions/dryrainent/greeum/agents-md"><img src="https://agentmods.dev/badge/instructions/dryrainent/greeum/agents-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 | $0.01012 | $0.01012 |
| Opus 5 | $0.00506 | $0.00506 |
| Sonnet 5 | $0.00202 | $0.00202 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade A, and why
Greeum AGENTS.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 4d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
사용자가 별도로 지시하기 전까지는 모든 답변은 한국어로 답변합니다.
Project Structure & Module Organization
The core package lives in greeum/, providing the STM/LTM memory managers, graph index logic, and shared utilities. Command-line tooling is under cli/, while api/ exposes the REST/MCP layers used by Claude and other integrations. Reusable examples and smoke assets live in examples/ and data/. Automated documentation, migration notes, and design briefs live under docs/ and the top-level *.md reports. Tests are grouped in tests/ for pytest suites, with scenario-specific regression harnesses in the test_*/ directories that mirror production incidents.
Agent Operational Workflow
- 아래의
greeumMCP 도구 사용은 선택이 아닌 필수임을 명심해야 한다. 하기 조건마다 반드시 사용하여 맥락의 휘발을 상시 방지할 수 있어야 한다. - Codex·Claude 환경에서는 로컬 STDIO MCP 경로를 기본으로 사용한다. CLI 명령 대신
greeumMCP 툴(add_memory, search_memory, get_memory_stats, usage_analytics, analyze 등)을 우선 호출해 작업을 기록·조회한다. - 세션 컨텍스트가 비어 있거나 축약돼 있을 때는
get_memory_stats와usage_analytics로 맥락을 빠르게 복원한다. - 새 작업 요청이 들어오면
search_memory로 최신 기록을 우선 탐색하고, 이어서 팔로우업을 진행한다. - 작업 중간에 새로운 추론이 나오거나 완료 직후에는
add_memory로 즉시 경과를 남긴다(액탄트 패턴 유지). - 필요할 때마다 에이전트는 greeum 도구를 자율적으로 호출할 수 있으며, 사용자는 이 권한을 상시 보증한다.
- SentenceTransformer가 필요한 경우
greeum mcp warmup으로 모델을 미리 로드하고, 응답 지연 시/tmp/greeum_codex_stdio.log에서 원인을 확인한다. - CLI, REST 호출은 MCP 도구로 해결할 수 없을 때만 사용한다.
Build, Test, and Development Commands
pip install -e .[dev]: set up an editable checkout with linting and testing extras.pytest: run the fast unit and integration suite intests/.python run_all_tests.py: execute the curated end-to-end suites used before releases.tox -e py311: run pytest in the supported interpreter matrix (py310–py312).greeum mcp serve: start the STDIO MCP server (Claude Desktop).greeum mcp serve -t http --host 0.0.0.0 --port 8800: launch the HTTP MCP endpoint for Codex/OpenAI agents.
Coding Style & Naming Conventions
Target Python 3.10+ with 4-space indentation, type hints on public APIs, and descriptive snake_case identifiers. The repo favors single-purpose modules and keeps CLI entry points in cli/*_commands.py. Run ruff check . (line length 120, selected ignores in pyproject.toml) before submitting. Use black . to normalize formatting and isort . to order imports if you touch modules that mix CLI and service layers.
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.
- 4d ago First seen · 37 lines · 1,012 tokens per session scan A bb63be047c22
Greeum AGENTS.md is an instructions file published in the GitHub repository DryRainEnt/Greeum (24 stars, last pushed 1mo ago), licensed MIT. It adds 1,012 tokens to every session, about $0.0051 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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.