Borrowing it
Nothing to install: this file belongs to coreline-ai/antigravity_glm_mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/coreline-ai/antigravity_glm_mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/coreline-ai/antigravity_glm_mcpWrote 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/coreline-ai/antigravity_glm_mcp/agents-md)<a href="https://agentmods.dev/instructions/coreline-ai/antigravity_glm_mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/coreline-ai/antigravity_glm_mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/coreline-ai/antigravity_glm_mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/coreline-ai/antigravity_glm_mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00926 | $0.00926 |
| Opus 5 | $0.00463 | $0.00463 |
| Sonnet 5 | $0.00185 | $0.00185 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
antigravity_glm_mcp 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 8d 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
프로젝트 구조 및 모듈 구성
src/server.py가 MCP 도구를 등록하고 호출합니다. 새 도구는src/tools/에 Pydantic 파라미터 모델과ToolResponse를 함께 정의하세요.- 공통 인프라(
config.py,sandbox.py,backup.py,glm_client.py)는src/core/에 있습니다. 경로 검증·백업·HTTP 로직을 재사용해 보안 일관성을 유지합니다. - 문서는
docs/, 단위 테스트는tests/core/와tests/tools/, 통합 스모크는tests/local_tools_test.py,tests/simple_test.py에 있습니다. 런타임 데이터는data/와.glm_backups/(git ignore)에 남습니다.
환경 및 설정
- Python 3.11+ 필요. 기본 설치:
python -m pip install -r requirements.txt. 린트/테스트 추가 패키지:python -m pip install -e .[dev]. - MCP 빠른 설정:
python scripts/install.py실행 후ZHIPU_API_KEY,PROJECT_ROOT, 선택적 모델/베이스 URL을 입력합니다. 이미 설치했다면--skip-deps로 건너뜁니다. - 비밀 값은
.env또는 로컬 MCP 설정에만 보관하고 저장소에 커밋하지 마세요.
빌드·실행·개발 명령
- 서버 수동 실행:
python src/server.py(MCP 클라이언트와 함께 사용). - 린트:
ruff check src tests(ruff는dev익스트라에 포함). - 패키징은 hatchling 기반이며 로컬 개발 시 추가 빌드 단계가 없습니다.
코딩 스타일 및 네이밍
- Python, 4-스페이스 인덴트, 타입 힌트 권장. 도구 입력은 Pydantic
BaseModel+검증자를 사용하고 이름은glm_*패턴을 유지합니다. ToolResponse에 명확한code/message/data를 채우고, 블로킹 대신 비동기 I/O(asyncio.to_thread,httpx.AsyncClient)를 선호합니다.config.PROJECT_ROOT와SandboxValidator를 준수하며 하드코딩된 경로·비밀을 피합니다. 새 파라미터와 핸들러는 동일한*_ops.py에 배치합니다.
테스트 가이드
- 빠른 단위 테스트:
python -m pytest tests/core tests/tools(오프라인). - 네트워크/API 확인:
python tests/local_tools_test.py(웹 검색/HTTP),python tests/simple_test.py(GLM). 실행 전PROJECT_ROOT,ZHIPU_API_KEY를 export 합니다. - 비동기 테스트는
@pytest.mark.asyncio로 표시하고 HTTP·파일 I/O는 가급적 모킹해 결정성을 유지하세요.
커밋 및 PR 가이드
- 커밋은 짧은 명령형 제목, 이모지 선택 사항(예:
feat: tighten sandbox rollback,🚀 improve glm_cmd errors). 한 커밋에 한 가지 변경만 담습니다. - PR에는 동작 변화 요약, 연관 이슈, 실행한 테스트 명령, 설정/환경 영향 여부를 적습니다. 출력 형식/UI가 변할 때만 스크린샷을 첨부합니다.
.env,data/,.glm_backups/, 생성 로그, API 키는 절대 커밋하지 마세요. 샌드박스·쉘·보안 변경 시 위험과 완화책을 설명합니다.
보안 및 데이터 처리
- 파일 작업은 반드시
PROJECT_ROOT내에서 수행하고 원시Path대신SandboxValidator와BackupManager를 거칩니다. glm_http_request,glm_shell_exec의 SSRF/IP 차단과 화이트리스트를 유지하세요. 검토 없이 필터를 완화하지 않습니다.- 수정/삭제 전에 자동 백업이 동작합니다. 복구는 수동 복사보다
glm_file_rollback으로 검증하세요.
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.
- 8d ago First seen · 37 lines · 926 tokens per session scan A 304724239c6b
antigravity_glm_mcp AGENTS.md is an instructions file published in the GitHub repository coreline-ai/antigravity_glm_mcp (1 stars, last pushed 4mo ago), licensed MIT. It adds 926 tokens to every session, about $0.0046 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.
Other instructions, from other repositories
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 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).
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.
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.