vhk: Skill for Claude Code

.agents/skills/vhk-gate/SKILL.md

vhk-gate is a skill for Claude Code, Codex from byh3071-cpu/vhk. It costs 26 tokens per session (376 once invoked), scanned A, original, MIT.

A completion checklist that runs VHK's verification, receipt, and review checks in order. A receipt records whether the current work was checked against the right project state.

In plain words
What is it for?
Use it after code changes or a finished goal to diagnose failed checks, handle dirty or outdated work, and confirm completion.
Why use it?
It prevents the agent from declaring work complete when tests, recorded changes, or review conditions have not passed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is byh3071-cpu/vhk's own configuration. It tells Claude Code and Codex how to work on vhk itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything vhk configures →

Reuse

Borrowing it

Nothing to install: this file belongs to byh3071-cpu/vhk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/byh3071-cpu/vhk/main/.agents/skills/vhk-gate/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/byh3071-cpu/vhk

Made for: Claude Code, Codex.

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-gate

README.md
[![agentmods](https://agentmods.dev/badge/skills/byh3071-cpu/vhk/vhk-gate/github.svg)](https://agentmods.dev/skills/byh3071-cpu/vhk/vhk-gate)
Your own site
<a href="https://agentmods.dev/skills/byh3071-cpu/vhk/vhk-gate"><img src="https://agentmods.dev/badge/skills/byh3071-cpu/vhk/vhk-gate/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.

agentmods 80×15 button for vhk-gate

Your own site · 80×15
<a href="https://agentmods.dev/skills/byh3071-cpu/vhk/vhk-gate"><img src="https://agentmods.dev/badge/skills/byh3071-cpu/vhk/vhk-gate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 376 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00026 $0.00376
Opus 5 $0.00013 $0.00188
Sonnet 5 $0.00005 $0.00075
Haiku 4.5 $0.00003 $0.00038

Measured 10d ago against content hash 6fa1ed84aaff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

vhk-gate 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 10d 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.

.agents/skills/vhk-gate/SKILL.md · 34 lines

What it actually says

VHK Gate

코드 변경이나 Goal 완료를 주장하기 전에 다음 순서로 실행한다.

vhk verify
vhk receipt
vhk review

판정

결과 다음 행동
verify red .vhk/reports/latest.json에서 실패 원인을 확인하고 수정한 뒤 다시 검증
receipt BLOCK — dirty 변경을 확인·커밋한 뒤 receipt 재실행
receipt BLOCK — stale 현재 HEAD를 vhk verify로 다시 검증한 뒤 receipt 재실행
receipt BLOCK — forbidden 금지 경로 변경을 제거하거나 사람과 작업 범위를 재합의
receipt CAUTION — 작업 기준 미기록 현재 범위를 확인하고 다음 작업 전에 vhk receipt --mark-start
review exit 1 — Goal 스키마 오류·무시 파일 vhk goal list로 확인한 뒤 vhk-goal-health 사용
review exit 1 — 모든 Goal 정상 DONE 종료 인수인계에서는 review N/A; goal-health 호출 금지
review fail vhk-evolve-loop로 반복 원인을 기록하고 제품 결함이면 수정

VHK CLI 자체의 버그나 크래시는 vhk-dogfood-issue, 프로젝트의 반복 실수는 vhk-evolve-loop로 보낸다.

완료 조건은 verify exit 0, receipt pass/caution, active Goal의 review pass 또는 모든 Goal 정상 DONE 종료의 review N/A다. 그 전에는 완료를 선언하지 않는다.

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. 10d ago First seen · 34 lines · 26 tokens per session scan A 6fa1ed84aaff

Subscribe to this mod's changes

vhk-gate is a skill published in the GitHub repository byh3071-cpu/vhk (12 stars, last pushed 2d ago), licensed MIT. It adds 26 tokens to every session and 376 once invoked, about $0.0001 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 2026-08-30.