Borrowing it
Nothing to install: this file belongs to postmelee/hyper-waterfall. 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/postmelee/hyper-waterfall/main/AGENTS.mdgit clone --depth 1 https://github.com/postmelee/hyper-waterfallWrote 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/postmelee/hyper-waterfall/agents-md)<a href="https://agentmods.dev/instructions/postmelee/hyper-waterfall/agents-md"><img src="https://agentmods.dev/badge/instructions/postmelee/hyper-waterfall/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/postmelee/hyper-waterfall/agents-md"><img src="https://agentmods.dev/badge/instructions/postmelee/hyper-waterfall/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 | $0.01380 | $0.01380 |
| Opus 5.5 | $0.00552 | $0.00552 |
| Sonnet 5.5 | $0.00276 | $0.00276 |
| Haiku 4.5 | $0.00138 | $0.00138 |
Grade A, and why
hyper-waterfall 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 1mo 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
본 저장소에서 작업하는 모든 코딩 에이전트(Codex, Claude Code 등)가 따르는 운영 규칙. 매 턴 시스템 프롬프트로 적재되므로 항상 필요한 정책·제약·인덱스만 둔다. 절차 상세는 매뉴얼·SKILL로 분리한다.
프로젝트 개요
본 저장소는 하이퍼-워터폴 방법론을 모듈화한 프레임워크 저장소이며, 자기 자신에게 본 방법론을 적용하는 dogfooding 사례를 운영한다. templates/에는 적용 대상 저장소에 복사할 진실 원천 파일이 있고, 본 저장소 루트의 mydocs/manual과 mydocs/skills는 templates/mydocs/의 동일 폴더로 가는 심볼릭 링크다.
하이퍼-워터폴 핵심 규칙
이 프로젝트는 하이퍼-워터폴 방법론을 적용한다. 에이전트의 기본 동작(빠른 실행, 자율 수정)과 충돌하므로 반드시 숙지한다. 상세: agent_code_hyperfall_rule_conflict.md.
- 소스 수정 전 반드시 작업지시자 승인 요청
- 작업은 GitHub Issue 기준으로 추적
- 새 기능, 버그 수정, 구조 변경은
이슈 -> 브랜치 -> 오늘할일 -> 계획서 -> 구현 -> 검증 -> 최종 보고서 -> PR순서 절대 생략 금지 - 각 단계 완료 후 승인 없이 다음 단계 진행 금지
- 범위가 불명확하거나 기존 작업과 충돌할 가능성이 있으면 먼저 확인
- 사용자나 다른 작업자가 만든 변경은 되돌리지 않음
- 이슈 close는 작업지시자 승인 후 또는 PR merge 확인 후에만 수행
- 문서 수정은 기존 내용을 먼저 읽고 필요한 부분만 수정하며, 불가피할 때만 내용을 추가
- 작업 완료 후 다음 작업에 필요하지 않은 로컬/원격 부산물은 정리
- PR merge와 이슈 close 후에는
main으로 돌아오고, 더 이상 필요 없는local/task{번호}브랜치와 임시 worktree를 정리
승인 간주 조건: 작업지시자가 같은 스레드에서 "계속 진행", "다음 단계 진행"처럼 명시 지시한 경우에만 해당 단계 승인으로 간주한다.
명명 규칙
- 마일스톤:
M{버전}(예: M100=v1.0.0, M05x=v0.5.x). 문서 파일명은m{숫자}소문자 (예:m100) - 브랜치:
local/task{이슈번호}(작업),publish/task{이슈번호}(main대상 PR 게시용) - 커밋 메시지:
- 기본형:
Task #{번호}: 내용 - 단계:
Task #{번호} Stage {N}: 내용 - 하위 단계:
Task #{번호} [Stage {N.M}]: 내용 - 보고서 묶음:
Task #{번호} Stage {N} + 최종 보고서: 내용
- 기본형:
- 문서 파일명:
task_{milestone}_{이슈번호}{_impl|_stage{N}|_report}?.md. 신규 문서는 마일스톤 포함 형식 강제. 상세:document_structure_guide.md - 모든 문서는 한국어 작성
핵심 강제 규칙 (변경 전 매뉴얼 확인 필수)
templates/안의 placeholder 표기(예:{REPO_SLUG})는 그대로 보존한다. 사용자가 자신의 저장소에 적용할 때 치환하므로 본 저장소에서는 치환하지 않는다.- SKILL이나 매뉴얼 본문을 변경할 때는
README.md의 "핵심 SKILL"·"도입 후 작업 흐름" 표와templates/mydocs/manual/task_workflow_guide.md의 "SKILL 호출 표시 안내"를 같은 PR에서 갱신한다. mydocs/skills와mydocs/manual심볼릭 링크 대상은 변경하지 않는다(templates/mydocs/skills,templates/mydocs/manual이 진실 원천).
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.
- 1mo ago First seen · 61 lines · 1,380 tokens per session scan A 876e9b654c85
hyper-waterfall AGENTS.md is an instructions file published in the GitHub repository postmelee/hyper-waterfall (82 stars, last pushed 3mo ago), licensed MIT. It adds 1,380 tokens to every session, about $0.0055 per session on Opus 5.5. 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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.