build-and-runtime-verification

build-and-runtime-verification is a skill for Codex from hoatv2211/GameStudio-CodexKIT. It costs 41 tokens per session (786 once invoked), scanned A, original, MIT.

A repeatable checklist for checking whether code builds, tests, launches, or runs correctly, with the exact command, result, files produced, and limits recorded.

In plain words
What is it for?
Use it after implementation, when investigating build failures, during runtime smoke checks, when comparing generated files, or before a release.
Why use it?
It prevents a vague “it works” claim based on incomplete or stale evidence. It also makes clear what was checked and what was not.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions AGENTS.md.

Good fit Use it after implementation, when investigating build failures, during runtime smoke checks, when comparing generated files, or before a release.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hoatv2211/gamestudio-codexkit/build-and-runtime-verification
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.

Any agent
npx skills add hoatv2211/GameStudio-CodexKIT --skill build-and-runtime-verification
Clone the repo
git clone --depth 1 https://github.com/hoatv2211/GameStudio-CodexKIT

Made for: 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 build-and-runtime-verification

README.md
[![agentmods](https://agentmods.dev/badge/skills/hoatv2211/gamestudio-codexkit/build-and-runtime-verification.svg)](https://agentmods.dev/skills/hoatv2211/gamestudio-codexkit/build-and-runtime-verification)
Your own site
<a href="https://agentmods.dev/skills/hoatv2211/gamestudio-codexkit/build-and-runtime-verification"><img src="https://agentmods.dev/badge/skills/hoatv2211/gamestudio-codexkit/build-and-runtime-verification.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 786 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.
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 $0.00041 $0.00786
Opus 5 $0.00020 $0.00393
Sonnet 5 $0.00008 $0.00157
Haiku 4.5 $0.00004 $0.00079

Measured 8d ago against content hash d8ec67c023e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

build-and-runtime-verification 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 8d 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.

skills/build-and-runtime-verification/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build and Runtime Verification

Overview

Verification is a reproducible claim: exact command, environment, exit code, observable artifact, verdict, and limitations.

When to use

Use after implementation, before completion claims, for build failures, runtime smoke checks, script compilation, generated artifact comparison, or release preflight.

When NOT to use

Do not use a compile-only result to claim gameplay, performance, database, network, or regression safety that was not exercised.

Required inputs and context discovery

Collect repository root, expected command, prerequisites, environment/version snapshot, expected artifact, timeout, safe side effects, and what the check does not prove.

Safety and risk level

The gate is read-only with respect to source. If a command starts services, writes caches, imports data, opens an editor, or mutates external state, route through the relevant safety workflow first.

Workflow

  1. Define the claim and the single command or command sequence that proves it. Completion criterion: success and failure signals are explicit before execution.
  2. Verify prerequisites and capture environment versions without changing them. Completion criterion: missing dependencies are labeled BLOCKED.
  3. Run the narrowest check and capture stdout, stderr, duration, and exit code. Completion criterion: raw results are available even when the command fails.
  4. Inspect the expected artifact or runtime signal rather than relying on exit code alone. Completion criterion: artifact existence and relevant properties are recorded.
  5. Issue PASS, FAIL, or BLOCKED with limitations. Completion criterion: the verdict does not exceed what the evidence proves.

Evidence and output contract

Produce verdict.md or a summary JSON with claim, command, exit code, artifact path, environment snapshot, verdict, limitations, and reviewer when required.

Handoff contract

Include failing command, first actionable error, artifact/log paths, prerequisites, retries already attempted, and the safest next diagnostic step.

Read the full file on GitHub · 79 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 79 lines · 41 tokens per session scan A d8ec67c023e6

Subscribe to this mod's changes

build-and-runtime-verification is a skill published in the GitHub repository hoatv2211/GameStudio-CodexKIT (3 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 786 once invoked, about $0.0002 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.