querytree AGENTS.md

Repository-wide instructions for contributors and AI coding assistants working on querytree. They define the project's rules for truthfulness, human decision authority, documentation, branches, commits, and checks.

In plain words
What is it for?
Use them before modifying the repository to understand the required reading, workflow branches, merge rules, commit format, source of decision state, and final validation command.
Why use it?
They prevent unverified claims and premature implementation while making changes traceable to the project's source documents and decisions.

Instructions file for CodexOpenCode

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/sp-daewoon/querytree/agents-md
Clone the repo
git clone --depth 1 https://github.com/sp-daewoon/querytree

Made for: Codex, OpenCode.

Per session 555 This file is loaded in full into every session.
When invoked 555 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 $0.00555 $0.00555
Opus 5 $0.00278 $0.00278
Sonnet 5 $0.00111 $0.00111
Haiku 4.5 $0.00056 $0.00056

Measured yesterday against content hash b6abd81f5322, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

querytree 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 yesterday.

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.

AGENTS.md · 39 lines

What it actually says

Querytree 헌법

이 문서는 Querytree 저장소에서 Codex, Claude Code, 사람 기여자가 함께 작업할 때의 최우선 규칙이다. 하위 문서는 이 규칙을 약화하거나 충돌하는 지시를 추가할 수 없다.

진실성과 결정 권한

  • 확인하지 않은 사실은 사실처럼 쓰지 않는다. 가설에는 가설임을 표시한다.
  • 불가능하거나 권한·정보가 부족한 작업은 추정으로 진행하지 않고 사용자에게 필요한 정보를 질문한다.
  • 에이전트는 선택지, 근거, 반론을 만들 수 있지만 사람의 선택·확정·재개방을 대신하지 않는다.
  • 확정 전 결정에 따른 구현은 사용자가 명시적으로 요청한 되돌릴 수 있는 탐색 작업으로 제한한다.

문서와 코드

  • 한국어 문서를 원본으로 유지한다. 공개 사용자층을 위한 영어 문서는 한국어 원본과 의미가 어긋나지 않게 별도 제공할 수 있다.
  • 코드 주석은 꼭 필요한 경우에만 한글 한 줄로 쓴다. 변경 이력식 주석은 남기지 않는다.
  • 결정 원본은 .querytree/state.json 서버 상태다. UI의 임시 상태나 대화 기록을 원본으로 취급하지 않는다.

작업 흐름과 추적성

  • 모든 비자명한 변경은 workflow/wNN-<topic> 브랜치에서 수행한다. main에 직접 커밋하지 않는다.
  • 검증을 통과한 뒤에만 main으로 --no-ff merge하고, main만 원격에 push한다.
  • 커밋 제목은 [agent:<role>] <type>: <요약> 형식을 사용한다. 예: [agent:codex-architect] feat: MCP 결정 초안 POC.
  • 작업 시작 전 이 문서와 관련 docs/ 문서를 읽고, 완료 전 npm run check를 실행한다.

문서 우선순위

  1. AGENTS.md - 공통 헌법과 안전·작업 흐름
  2. docs/architecture.md - 제품 경계와 기술 설계
  3. skills/querytree/SKILL.md - 에이전트의 결정 처리 절차
  4. README.md - 설치와 사용자 안내

같은 주제에서 문서가 충돌하면 더 높은 순위의 문서를 따르고, 모호하면 구현 전에 사용자에게 질문한다.

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. yesterday First seen · 39 lines · 555 tokens per session scan A b6abd81f5322

Subscribe to this mod's changes

querytree AGENTS.md is an instructions file published in the GitHub repository sp-daewoon/querytree (0 stars, last pushed 23d ago), licensed MIT. It adds 555 tokens to every session, about $0.0028 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.

Related

Other instructions, from other repositories

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.

github/spec-kit · 7,104 tokens

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).

microsoft/vscode · 6,785 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

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.

vercel/next.js · 7,296 tokens