What is overnight-vhk-auto?

A conductor for running one VHK goal unattended overnight and stopping after opening a pull request. A pull request is a proposed code change submitted for review.

Running an overnight implementation task, committing verified changes, and opening an autonomous pull request for morning review.

It defines the repository wrapper and safety rules for implementing a goal and creating a pull request without merging it or changing protected branches.

How byh3071-cpu/vhk configures Claude Code and Codex

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/overnight-vhk-auto/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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/byh3071-cpu/vhk/overnight-vhk-auto/github.svg)](https://agentmods.dev/skills/byh3071-cpu/vhk/overnight-vhk-auto)

Your own site

<a href="https://agentmods.dev/skills/byh3071-cpu/vhk/overnight-vhk-auto"><img src="https://agentmods.dev/badge/skills/byh3071-cpu/vhk/overnight-vhk-auto/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/byh3071-cpu/vhk/overnight-vhk-auto"><img src="https://agentmods.dev/badge/skills/byh3071-cpu/vhk/overnight-vhk-auto.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 813 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 warn 7 Sept 2026

SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Agent Snooping · line 22
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
medium Agent Snooping · line 44
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00056	$0.00813
Opus 5.5	$0.00022	$0.00325
Sonnet 5.5	$0.00011	$0.00163
Haiku 4.5	$0.00006	$0.00081

Measured 26d ago against content hash 6e2e55f8fd51, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

overnight-vhk-auto 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 26d 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/overnight-vhk-auto/SKILL.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Overnight vhk-auto conductor

One goal per invocation. Different track from overnight-autoloop (do not mix).

Repository wrapper

Use the tracked scripts/auto_pr_goal.ps1 wrapper after the implementation commit. Its interface is fixed:

powershell -NoProfile -ExecutionPolicy Bypass -File scripts/auto_pr_goal.ps1 `
  -RepositoryRoot <repo-root> -BaseBranch main -Title <title> -BodyFile <body-file>

Prepare a temporary PR body file that follows AGENTS.md and includes the morning review questions. Do not commit that file.

Invariants

INV-A Follow .agents/skills/vhk-auto/SKILL.md INV-1..INV-11 for the implement loop. Commit only inside that loop (INV-7).
INV-B After green verify + commit, call scripts/auto_pr_goal.ps1. The wrapper supports a clean worktree with an unpushed commit; do not require dirty porcelain. Merge = 0. Never push main, force-push, publish, or change branch protection.
INV-B2 The autonomous label is attached idempotently by that script on both create and reuse paths (Goal 111 cohort secondary signal). Never add or remove it by hand — the primary signal is the terminal-SHA join, and signal mismatch is quarantined as unknown.
INV-C If autonomy-log start or terminal event is missing → write .vhk/HARD_STOP and stop. Same when a successful terminal event has no receipt for the same SHA — that run is recorded but never counts as verified completion, so it never enters the observation gate sample (vhk-auto INV-10).
INV-D Use the release order in docs/roadmap/2.x-roadmap.md and acceptance criteria in docs/PRD-2.x.md. Do not invent a queue from old Goal numbers.
INV-E Stop on HARD_STOP, verify 2× red, or open PR reported.

Loop

If .vhk/HARD_STOP exists → report and exit. Before any mutation, apply vhk-auto INV-11: require empty output from git -c core.quotepath=false status --porcelain=v1 -z --untracked-files=all and a named branch other than main or master; otherwise report and stop.
Run vhk goal next and select only the Goal it reports. If none is available or dependencies block it, report and stop. Preserve its local state as IN_PROGRESS; do not invent an order from old Goal numbers.
Run vhk-auto loop for that card (including INV-9 autonomy-log).
On success, require a clean worktree and a current branch other than main.
Call scripts/auto_pr_goal.ps1 with the repository root, base branch main, PR title, and temporary PR body file.
Optionally generate the morning report with node scripts/gen-autonomy-morning-report.mjs --date YYYY-MM-DD.
Report the PR URL (or HARD_STOP reason). Do not merge.

Read the full file on GitHub · 47 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.

26d ago Changed · +30 tokens per session 6e2e55f8fd51
1mo ago First seen · 47 lines · 26 tokens per session scan A 2e04ef5e4cb3

Subscribe to this mod's changes

overnight-vhk-auto is a skill published in the GitHub repository byh3071-cpu/vhk (12 stars, last pushed 6d ago), licensed MIT. It adds 56 tokens to every session and 813 once invoked, about $0.0002 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.

Building agents Claude Code agentic-coding ai ai-agent claude cli

crit-cli

Use when an agent needs to author or reply to crit inline comments programmatically (including multi-agent workflows commenting on shared code/plans/docs/proposals), publish or unpublish a crit review with crit share, sync a crit review to or from a GitHub PR or GitLab MR, or read/interpret a crit review JSON file.…

tomasz-tomczyk/crit · 110 tokens

crit

Review code changes, a plan, a live page (running dev server), or a local HTML file with Crit inline comments and structured human feedback. Use only when the user explicitly invokes /crit or directly asks to use Crit; a generic review request does not count.

tomasz-tomczyk/crit · 55 tokens

crit-story

Author a crit story and continue the interactive review loop only when the user explicitly invokes crit-story or directly asks you to generate a crit story. Do not infer this skill from generic review, PR, or diff-review requests.

tomasz-tomczyk/crit · 47 tokens

ospec

Document-driven OSpec workflow for initialization, change/goal routing, validation, archiving, and durable project knowledge.

clawplays/ospec · 26 tokens

ospec-change

Create or advance a lightweight OSpec change using the classic fast workflow.

clawplays/ospec · 18 tokens

test-harness

Install vigiles and test a Claude Code harness — hooks, skills, agents, settings, CLAUDE.md — by picking the right tier (unit / deterministic / eval) and writing a test that passes. Use to check that a hook fires or blocks, that a skill triggers, that injected context lands; or to observe a run — which tools it…

zernie/vigiles · 103 tokens

vhk: Skill for Claude Code