validation-runner

validation-runner is a skill for Claude Code, Codex from mlopscommunity/Coding-Agents-Conference-skills. It costs 44 tokens per session (3,899 once invoked), scanned A, original, Apache-2.0.

An independent code-checking process that runs tests, code-style checks, and assumption reviews in a separate context from the coding agent.

In plain words
What is it for?
Use it before merging, deploying, or accepting work from several coding agents, especially when defects would be costly.
Why use it?
A fresh reviewer is less likely to repeat mistakes or approve code based on assumptions made during implementation.

Skill for Claude CodeCodex

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 skills/mlopscommunity/coding-agents-conference-skills/validation-runner
Any agent
npx skills add mlopscommunity/Coding-Agents-Conference-skills --skill validation-runner
Clone the repo
git clone --depth 1 https://github.com/mlopscommunity/Coding-Agents-Conference-skills

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 validation-runner

README.md
[![agentmods](https://agentmods.dev/badge/skills/mlopscommunity/coding-agents-conference-skills/validation-runner.svg)](https://agentmods.dev/skills/mlopscommunity/coding-agents-conference-skills/validation-runner)
Your own site
<a href="https://agentmods.dev/skills/mlopscommunity/coding-agents-conference-skills/validation-runner"><img src="https://agentmods.dev/badge/skills/mlopscommunity/coding-agents-conference-skills/validation-runner.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,899 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00044 $0.03899
Opus 5 $0.00022 $0.01950
Sonnet 5 $0.00009 $0.00780
Haiku 4.5 $0.00004 $0.00390

Measured 5d ago against content hash 81c54a8b6450, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

validation-runner 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 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.

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/validation-runner/SKILL.md · 540 lines

How it starts

The opening of the file, as written. The whole thing — 540 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Validation Runner

Overview

The Validation Runner Skill performs comprehensive validation in a separate context from the coding agent. This is critical because if an agent makes false assumptions during coding, it will bake those assumptions into its validation. By running validation as a sub-agent with fresh context, you catch issues that the coding agent missed and prevent flawed implementations from being considered "complete."

Core principle: Fresh validation context catches assumption-based bugs. If the coder made a false assumption, it contaminates their own validation. You need independent verification.

Dependency: Claude Code CLI with test infrastructure, linting tools, and the ability to run code.

When to Use

  • After each coding session: Before merging code to main
  • After parallelized agent work: Before merging multiple agents' code
  • Before deployment: Final validation before production
  • When you're uncertain about code quality: Get an independent assessment
  • For critical systems: MLOps pipelines, data processing, ML models where bugs are expensive

When NOT to Use

  • During live pairing or rapid iteration (too slow)
  • For trivial changes (typo fixes, comments, obvious improvements)
  • When you trust the coding agent's validation completely (you shouldn't)

Common Mistakes

Mistake Why it's wrong
Skipping validation because "code looks good" You can't see issues visually. Validation tools find real bugs.
Assuming the coding agent's validation is sufficient If the agent made assumptions, it validated the wrong thing. Fresh context is essential.
Not running tests because "we did linting" Linting catches style issues. Tests catch logic bugs. You need both.
Ignoring coverage drops If coverage dropped, code is untested. Untested code breaks in production.
Treating all test failures as "probably environmental" Test failures are real. Investigate them.
Skipping custom pattern checks Pattern checks catch domain-specific issues linters miss. They're often more valuable than linting.

Read the full file on GitHub · 540 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 · 540 lines · 44 tokens per session scan A 81c54a8b6450

Subscribe to this mod's changes

validation-runner is a skill published in the GitHub repository mlopscommunity/Coding-Agents-Conference-skills (37 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 44 tokens to every session and 3,899 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens