Borrowing it
Nothing to install: this file belongs to unvus/neosql-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/unvus/neosql-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/unvus/neosql-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/unvus/neosql-mcp/agents-md)<a href="https://agentmods.dev/instructions/unvus/neosql-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/unvus/neosql-mcp/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 5.1 | $0.03406 | $0.03406 |
| Opus 5 | $0.01703 | $0.01703 |
| Sonnet 5 | $0.00681 | $0.00681 |
| Haiku 4.5 | $0.00341 | $0.00341 |
Grade A, and why
neosql-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 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
프로젝트 맥락
이 저장소는 neosql-mcp의 TypeScript ESM 패키지다. stdio MCP 클라이언트가
npx neosql-mcp로 실행하는 로컬 MCP 중계 서버를 구현한다.
목표 아키텍처:
[mcp-client] -- stdio MCP --> [neosql-mcp Node]
-- JSON-RPC over HTTP on UDS/Named Pipe --> [electron-main]
-- IPC --> [electron-renderer]
중요한 경계:
- 클라이언트 ↔ Node 구간은 표준 MCP JSON-RPC over stdio를 사용한다.
- Node ↔ electron-main 구간은 neosql 자체 JSON-RPC over HTTP endpoint를 사용한다.
- upstream transport는 POSIX에서는 Unix Domain Socket, Windows에서는 Named Pipe다. 아키텍처 문서가 명시적으로 바뀌기 전까지 TCP port를 도입하지 않는다.
- Tool catalog와 MCP handler는 이 Node 패키지에 둔다. handler는 하나 이상의 upstream HTTP method를 electron-main에 위임할 수 있으며, MCP tool과 upstream method는 1:1 매핑을 보장하지 않는다.
- electron-main, renderer, embedded-server 변경은 이 저장소 범위 밖이다. 단, 작업이 neosql main app 변경을 명시적으로 포함하면 예외다.
현재 상태와 로드맵:
- Phase 0 완료: package scaffold, MCP server,
pingtool, logger, build, unit test, spawn integration test. - Phase 1 완료: endpoint resolution은 config file, environment variable, process discovery가 아니라 deterministic socket path 규칙을 사용한다.
- Phase 2: embedded-server MCP tool을 이 Node 패키지로 이관한다. 순서는 Phase 2-1
channel infrastructure + 9개 tool signature + mock UDS round-trip, Phase 2-2
contract analysis, Phase 2-3 Node handler, Phase 2-4
ContextToolsreal Electron pilot이다. - Phase 3+는 Phase 2-4 pilot 결과를 확인한 뒤 범위와 우선순위를 다시 정한다.
문서 기준:
README.md: npm/GitHub에 노출되는 end-user 문서. 공개 설정 예시와 사용자-facing 설명은 README에 둔다.PLAN.md: 아키텍처 결정과 phase 전략의 단일 진실의 원천.CHECKLIST.md: 현재 진행 상태의 단일 진실의 원천.docs/project-structure.md: 파일 배치 규칙의 단일 진실의 원천.docs/testing.md: 필수 테스트 워크플로.docs/mcp-client-config.md: 내부 개발자용 CLI option, profile, legacy HTTP header → stdio/npx CLI arg 매핑 참고 문서. end-user용 설정 예시는 README를 우선 갱신한다.
AGENTS.md는 AI coding agent용 repository guide다. 세부 내용이 다르면 더 구체적인
계획 문서(PLAN.md, CHECKLIST.md, docs/project-structure.md)를 우선한다.
neosql main app 참조 규칙
neosql Electron app 설치 감지, 앱 실행, readiness 확인, Node ↔ electron-main RPC 계약, renderer IPC 연결, embedded-server 기존 동작 비교처럼 main app 동작에 의존하는 작업은 문서만 보고 추측하지 않는다. 반드시 sibling clone의 실제 소스코드를 먼저 확인한다.
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 · 246 lines · 3,406 tokens per session scan A cfd86b66b9d8
neosql-mcp AGENTS.md is an instructions file published in the GitHub repository unvus/neosql-mcp (1 stars, last pushed 11d ago), licensed Apache-2.0. It adds 3,406 tokens to every session, about $0.0170 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
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).
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.
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).
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.