agentmods.dev

vhk AGENTS.md

vhk AGENTS.md is an instructions file for Codex, OpenCode from byh3071-cpu/vhk. It costs 2,568 tokens per session, scanned A, original, MIT.

Agent operating instructions for vhk, including a loop for reading context, choosing the next goal, making changes, checking results, and completing the goal. They also define project rules and required quality gates.

In plain words
What is it for?
Use them at the start of vhk coding sessions and when planning work, updating goals, recording project knowledge, or running type checks, tests, and builds.
Why use it?
They help agents preserve project state, stop when a hard-stop file exists, avoid editing generated files directly, and finish only after checks pass.

Instructions file for CodexOpenCode

not rated 12 2d ago A scan 2,568 tokens original MIT
View the source file byh3071-cpu/vhk
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/byh3071-cpu/vhk/agents-md
Clone the repo
git clone --depth 1 https://github.com/byh3071-cpu/vhk

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for vhk AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/byh3071-cpu/vhk/agents-md.svg)](https://agentmods.dev/instructions/byh3071-cpu/vhk/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/byh3071-cpu/vhk/agents-md"><img src="https://agentmods.dev/badge/instructions/byh3071-cpu/vhk/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,568 This file is loaded in full into every session.
When invoked 2,568 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.02568 $0.02568
Opus 5 $0.01284 $0.01284
Sonnet 5 $0.00514 $0.00514
Haiku 4.5 $0.00257 $0.00257

Measured 5d ago against content hash db7e0ce5b7a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vhk AGENTS.md scanned grade A with 1 finding 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 5d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- `execSync` 신규 사용 금지 → `safeExecFile` 사용 <!-- vhk:check=no-exec-sync -->
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vhk — AGENTS.md (에이전트 작동 규약)

⚡ 이 파일은 RULES.md에서 자동 생성됨 (vhk sync). 직접 수정 금지. 빠른 시작(토큰 절감): docs/context/agent-compact.md 를 먼저 읽으세요.

Loop Protocol

  • 루프: context → goal next → 작업 → goal check → goal done
  • 작업 시작 시 .vhk/HARD_STOP 확인 — 있으면 모든 자동화 즉시 중단.
  • 작업 정의·수용 기준은 RULES.md가 지정한 추적 원본을 따른다. Goal 카드는 로컬 실행 상태다.
  • .vhk/context.md·docs/state/next-task.md는 파생 스냅샷. blockers만 append-only 로컬 기록이다.
  • 교훈·결정·실패·성공은 vhk memory(memory v2 4버킷, 단일 출처).
  • 게이트(tsc / test:run / build) 통과해야만 vhk goal done.

VHK Project Rules

Project rules are generated from RULES.md; optional user rules use the generic rules-file contract.

  • Cursor: .cursor/rules/ecosystem.mdc (vhk inject-bootstrap)
  • Optional rules: VHK_RULES_FILE or vhk config set-rules-file <yaml>
  • 금지: AGENTS.md 손수 편집 → RULES.md + vhk sync

세션 시작 필독

이 절은 진입점이다. 어떤 도구로 세션을 열든 여기부터 읽는다 (ADR-010 §3).

  • 현 사이클 원본: docs/roadmap/2.x-roadmap.md — 작업 단위·순서·릴리스 종료 조건 전량. 작업 시작 전 여기부터 읽는다.
  • 수용 기준: docs/PRD-2.x.md
  • 실행 단위인 goals/*.md 카드와 scripts/check-goal-<번호>.mjs 는 위 원본에서 파생된 비추적 산출물이다. Goal 카드가 있으면 그 frontmatter가 로컬 실행 상태를 보존한다. 소실되면 정의·완료 조건은 원본에서 재생성하고 vhk goal sync 로 검사 스크립트를 백필한다. 단, 과거 로컬 진행 상태는 복구된 것으로 추측하지 않고 unknown으로 돌아간다.
  • .vhk/context.md 와 docs/state/next-task.md 는 현재 상태를 보기 쉽게 모은 파생 스냅샷이다. 작업 정의나 완료 조건의 원본으로 사용하지 않는다.
  • docs/state/blockers.md 는 로컬 차단 기록이다. append-only로 다루되 제품 작업 정의의 원본으로 승격하지 않는다.

기술 스택

변경 시 ADR(docs/adr/) 필수.

  • Node.js + TypeScript (strict)
  • commander (CLI) + inquirer (인터랙티브) + chalk (출력)
  • tsup (빌드) + vitest (테스트)
  • @modelcontextprotocol/sdk + zod (MCP)
  • pnpm (패키지 매니저)
  • src/i18n/ko.ts (한국어 i18n)
  • src/lib/nlp-router.ts (자연어 라우팅)

코딩 규칙

  • TypeScript strict (any 금지)
  • try-catch 필수, 빈 catch 금지
  • console.log 프로덕션 제거
  • 실행 위치가 바뀌어도 같아야 하는 로컬 전용 경로는 저장 전에 절대경로로 바꾼다. 공개 파일에는 로컬 절대경로를 기록하지 않는다.
  • 사람에게 보여주는 날짜는 로컬 날짜를, 기계가 읽는 정확한 시각은 UTC ISO 형식을 쓴다.
  • 질문이 필요한 명령은 시작할 때 TTY를 확인한다. 입력할 수 없거나 입력이 끝나면 실행 방법을 안내하고 실패로 끝낸다.
  • 셸 명령의 따옴표와 여러 줄 문법은 실제 실행 셸에 맞춘다. Bash와 PowerShell 문법을 섞지 않는다.
  • 외부 입력이나 시각으로 파일·폴더명을 만들 때는 공통 헬퍼로 운영체제 금지문자를 바꾸고, 빈 이름과 중복을 확인한다.
  • execSync 신규 사용 금지 → safeExecFile 사용
  • fs.rmSync 신규 사용 금지 → removeFileSync·removeDirSync 사용 (비ASCII 경로에서 프로세스 즉사·조용한 삭제 누락, TS-005). src 는 0건, tests 는 scripts/rmsync-baseline.json 잔존분만 허용하며 늘리면 차단
  • 모든 커맨드 파일에 printNextStep() 패턴 사용
  • 한국어 별칭 .alias() + ko.ts 메시지 필수
  • 신규 커맨드 시 nlp-router.ts 키워드 추가 필수
  • 주석: 복잡 로직(git porcelain·drift·sync 등)은 why 블록주석 / 자명한 코드엔 주석 금지 / JSDoc 지양(타입이 말함) / 트러블 우회 코드는 원인 #이슈 참조
  • 신규 명령 체크리스트: 등록 4지점(index.ts + command-registry TOP_LEVEL·CONTAINER·한글별칭 + cli-args + ko.ts) 누락 = NL 라우터 가드 무력 — 영문·한글 별칭 둘 다 테스트. + COMMANDS.md·README 사용법 갱신

Read the full file on GitHub · 111 lines

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. 5d ago First seen · 111 lines · 2,568 tokens per session scan A db7e0ce5b7a8

Subscribe to this mod's changes

vhk AGENTS.md is an instructions file published in the GitHub repository byh3071-cpu/vhk (12 stars, last pushed 2d ago), licensed MIT. It adds 2,568 tokens to every session, about $0.0128 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agentsPlanningagentic-codingaiai-agentclaudeclaude-codecli
Related

Other instructions, from other repositories

nightshift AGENTS.md

AGENTS.md instructions for orwa-mahmoud/nightshift: AI-assisted contributions are welcome. The same correctness, security, licensing, testing, and quality standards apply regardless of which tools are used.

orwa-mahmoud/nightshift · 193 tokens

KDD AGENTS.md

AGENTS.md instructions for MauricioPerera/KDD: Este repositorio usa la metodología KDD (Knowledge-Driven Development). Las reglas obligatorias completas están en .agents/AGENTS.md y la skill local en .agents/skills/kdd-okf-ccdd-hybrid/SKILL.md.

MauricioPerera/KDD · 128 tokens

AmbyKit CLAUDE.md

Claude Code instructions for ambystechcom/AmbyKit, covering claude code — notes for the ambykit repo and claude-specific.

ambystechcom/AmbyKit · 257 tokens

lumen AGENTS.md

AGENTS.md instructions for ory/lumen, covering agents.md, repository expectations and commands.

ory/lumen · 259 tokens

eai-gofer GEMINI.md

Gemini CLI instructions for eai-support/eai-gofer, covering gemini.md and always-on eai contract.

eai-support/eai-gofer · 98 tokens

catalyst AGENTS.md

AGENTS.md instructions for coalesce-labs/catalyst, covering agents.md, what this repository is, agent philosophy, build & test and key principles.

coalesce-labs/catalyst · 6,878 tokens